{"ok":true,"updated_at":"2026-05-09T05:33:57.694Z","models":{"google/gemini-3.1-flash-lite":{"id":"google/gemini-3.1-flash-lite","name":"Google: Gemini 3.1 Flash Lite","provider":"google","context_length":1048576,"created":1778168828,"price_in":0.25,"price_out":1.5,"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"description":"Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and i"},"openai/gpt-chat-latest":{"id":"openai/gpt-chat-latest","name":"OpenAI: GPT Chat Latest","provider":"openai","context_length":400000,"created":1778000212,"price_in":5,"price_out":30,"input_modalities":["text","image","file"],"output_modalities":["text"],"description":"GPT Chat Latest points to OpenAI's stable API alias `chat-latest` that always resolves to the latest Instant chat model used in ChatGPT. As OpenAI rolls out new Instant model updat"},"x-ai/grok-4.3":{"id":"x-ai/grok-4.3","name":"xAI: Grok 4.3","provider":"x-ai","context_length":1000000,"created":1777591821,"price_in":1.25,"price_out":2.5,"input_modalities":["text","image"],"output_modalities":["text"],"description":"Grok 4.3 is a reasoning model from xAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requir"},"ibm-granite/granite-4.1-8b":{"id":"ibm-granite/granite-4.1-8b","name":"IBM: Granite 4.1 8B","provider":"ibm-granite","context_length":131072,"created":1777577071,"price_in":0.049999999999999996,"price_out":0.09999999999999999,"input_modalities":["text"],"output_modalities":["text"],"description":"Granite 4.1 8B is a dense, decoder-only 8-billion-parameter language model from IBM, part of the Granite 4.1 family. It supports a 131K-token context window and is designed for ent"},"mistralai/mistral-medium-3-5":{"id":"mistralai/mistral-medium-3-5","name":"Mistral: Mistral Medium 3.5","provider":"mistralai","context_length":262144,"created":1777570439,"price_in":1.5,"price_out":7.5,"input_modalities":["text","image"],"output_modalities":["text"],"description":"Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, a"},"openrouter/owl-alpha":{"id":"openrouter/owl-alpha","name":"Owl Alpha","provider":"openrouter","context_length":1048756,"created":1777398589,"price_in":0,"price_out":0,"input_modalities":["text"],"output_modalities":["text"],"description":"Owl Alpha is a high-performance foundation model designed for agentic workloads. Natively supports tool use, and long-context tasks, with strong performance in code generation, aut"},"~anthropic/claude-haiku-latest":{"id":"~anthropic/claude-haiku-latest","name":"Anthropic Claude Haiku Latest","provider":"~anthropic","context_length":200000,"created":1777318492,"price_in":1,"price_out":5,"input_modalities":["image","text"],"output_modalities":["text"],"description":"This model always redirects to the latest model in the Anthropic Claude Haiku family."},"~openai/gpt-mini-latest":{"id":"~openai/gpt-mini-latest","name":"OpenAI GPT Mini Latest","provider":"~openai","context_length":400000,"created":1777318471,"price_in":0.75,"price_out":4.5,"input_modalities":["file","image","text"],"output_modalities":["text"],"description":"This model always redirects to the latest model in the OpenAI GPT Mini family."},"~google/gemini-pro-latest":{"id":"~google/gemini-pro-latest","name":"Google Gemini Pro Latest","provider":"~google","context_length":1048576,"created":1777318451,"price_in":2,"price_out":12,"input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"description":"This model always redirects to the latest model in the Google Gemini Pro family."},"~moonshotai/kimi-latest":{"id":"~moonshotai/kimi-latest","name":"MoonshotAI Kimi Latest","provider":"~moonshotai","context_length":262144,"created":1777318428,"price_in":0.75,"price_out":3.5,"input_modalities":["text","image"],"output_modalities":["text"],"description":"This model always redirects to the latest model in the MoonshotAI Kimi family."},"~google/gemini-flash-latest":{"id":"~google/gemini-flash-latest","name":"Google Gemini Flash Latest","provider":"~google","context_length":1048576,"created":1777318398,"price_in":0.5,"price_out":3,"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"description":"This model always redirects to the latest model in the Google Gemini Flash family."},"~anthropic/claude-sonnet-latest":{"id":"~anthropic/claude-sonnet-latest","name":"Anthropic Claude Sonnet Latest","provider":"~anthropic","context_length":1000000,"created":1777318368,"price_in":3,"price_out":15,"input_modalities":["text","image"],"output_modalities":["text"],"description":"This model always redirects to the latest model in the Anthropic Claude Sonnet family."},"~openai/gpt-latest":{"id":"~openai/gpt-latest","name":"OpenAI GPT Latest","provider":"~openai","context_length":1050000,"created":1777318334,"price_in":5,"price_out":30,"input_modalities":["file","image","text"],"output_modalities":["text"],"description":"This model always redirects to the latest model in the OpenAI GPT family."},"qwen/qwen3.5-plus-20260420":{"id":"qwen/qwen3.5-plus-20260420","name":"Qwen: Qwen3.5 Plus 2026-04-20","provider":"qwen","context_length":1000000,"created":1777261368,"price_in":0.39999999999999997,"price_out":2.4,"input_modalities":["text","image","video"],"output_modalities":["text"],"description":"Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text output, with a 1M token context window."},"qwen/qwen3.6-flash":{"id":"qwen/qwen3.6-flash","name":"Qwen: Qwen3.6 Flash","provider":"qwen","context_length":1000000,"created":1777261362,"price_in":0.25,"price_out":1.5,"input_modalities":["text","image","video"],"output_modalities":["text"],"description":"Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a 1M token context window. Tiered pricing kicks in.."},"qwen/qwen3.6-35b-a3b":{"id":"qwen/qwen3.6-35b-a3b","name":"Qwen: Qwen3.6 35B A3B","provider":"qwen","context_length":262144,"created":1777260255,"price_in":0.15,"price_out":1,"input_modalities":["text","image","video"],"output_modalities":["text"],"description":"Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of"},"qwen/qwen3.6-max-preview":{"id":"qwen/qwen3.6-max-preview","name":"Qwen: Qwen3.6 Max Preview","provider":"qwen","context_length":262144,"created":1777260242,"price_in":1.04,"price_out":6.24,"input_modalities":["text"],"output_modalities":["text"],"description":"Qwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse mixture-of-experts architecture with approximately 1 trillion total parameters. It is optim"},"qwen/qwen3.6-27b":{"id":"qwen/qwen3.6-27b","name":"Qwen: Qwen3.6 27B","provider":"qwen","context_length":262144,"created":1777255064,"price_in":0.32,"price_out":3.1999999999999997,"input_modalities":["text","image","video"],"output_modalities":["text"],"description":"Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text, image"},"openai/gpt-5.5-pro":{"id":"openai/gpt-5.5-pro","name":"OpenAI: GPT-5.5 Pro","provider":"openai","context_length":1050000,"created":1777051896,"price_in":30,"price_out":180,"input_modalities":["file","image","text"],"output_modalities":["text"],"description":"GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K "},"openai/gpt-5.5":{"id":"openai/gpt-5.5","name":"OpenAI: GPT-5.5","provider":"openai","context_length":1050000,"created":1777051893,"price_in":5,"price_out":30,"input_modalities":["file","image","text"],"output_modalities":["text"],"description":"GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on ha"},"deepseek/deepseek-v4-pro":{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek: DeepSeek V4 Pro","provider":"deepseek","context_length":1048576,"created":1777000679,"price_in":0.435,"price_out":0.87,"input_modalities":["text"],"output_modalities":["text"],"description":"DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designe"},"deepseek/deepseek-v4-flash":{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek: DeepSeek V4 Flash","provider":"deepseek","context_length":1048576,"created":1777000666,"price_in":0.14,"price_out":0.28,"input_modalities":["text"],"output_modalities":["text"],"description":"DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. I"},"inclusionai/ling-2.6-1t":{"id":"inclusionai/ling-2.6-1t","name":"inclusionAI: Ling-2.6-1T","provider":"inclusionai","context_length":262144,"created":1776948238,"price_in":0.3,"price_out":2.5,"input_modalities":["text"],"output_modalities":["text"],"description":"Ling-2.6-1T is an instant (instruct) model from inclusionAI and the company’s trillion-parameter flagship, designed for real-world agents that require fast execution and high effic"},"tencent/hy3-preview":{"id":"tencent/hy3-preview","name":"Tencent: Hy3 preview","provider":"tencent","context_length":262144,"created":1776878150,"price_in":0.06599999999999999,"price_out":0.26,"input_modalities":["text"],"output_modalities":["text"],"description":"Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled,"},"xiaomi/mimo-v2.5-pro":{"id":"xiaomi/mimo-v2.5-pro","name":"Xiaomi: MiMo-V2.5-Pro","provider":"xiaomi","context_length":1048576,"created":1776874273,"price_in":1,"price_out":3,"input_modalities":["text"],"output_modalities":["text"],"description":"MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on "},"xiaomi/mimo-v2.5":{"id":"xiaomi/mimo-v2.5","name":"Xiaomi: MiMo-V2.5","provider":"xiaomi","context_length":1048576,"created":1776874269,"price_in":0.39999999999999997,"price_out":2,"input_modalities":["text","audio","image","video"],"output_modalities":["text"],"description":"MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perceptio"},"openai/gpt-5.4-image-2":{"id":"openai/gpt-5.4-image-2","name":"OpenAI: GPT-5.4 Image 2","provider":"openai","context_length":272000,"created":1776797528,"price_in":8,"price_out":15,"input_modalities":["image","text","file"],"output_modalities":["image","text"],"description":"[GPT-5.4](https://openrouter.ai/openai/gpt-5.4) Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2. It enables rich multim"},"inclusionai/ling-2.6-flash":{"id":"inclusionai/ling-2.6-flash","name":"inclusionAI: Ling-2.6-flash","provider":"inclusionai","context_length":262144,"created":1776795886,"price_in":0.08,"price_out":0.24,"input_modalities":["text"],"output_modalities":["text"],"description":"Ling-2.6-flash is an instant (instruct) model from inclusionAI with 104B total parameters and 7.4B active parameters, designed for real-world agents that require fast responses, st"},"~anthropic/claude-opus-latest":{"id":"~anthropic/claude-opus-latest","name":"Anthropic: Claude Opus Latest","provider":"~anthropic","context_length":1000000,"created":1776795361,"price_in":5,"price_out":25,"input_modalities":["text","image"],"output_modalities":["text"],"description":"This model always redirects to the latest model in the Claude Opus family."},"openrouter/pareto-code":{"id":"openrouter/pareto-code","name":"Pareto Code Router","provider":"openrouter","context_length":200000,"created":1776747900,"price_in":-1000000,"price_out":-1000000,"input_modalities":["text"],"output_modalities":["text"],"description":"The Pareto Router maintains a tiered shortlist of strong coding models, ranked by [Artificial Analysis](https://artificialanalysis.ai/) coding percentiles. Set min_coding_score bet"},"moonshotai/kimi-k2.6":{"id":"moonshotai/kimi-k2.6","name":"MoonshotAI: Kimi K2.6","provider":"moonshotai","context_length":262144,"created":1776699402,"price_in":0.75,"price_out":3.5,"input_modalities":["text","image"],"output_modalities":["text"],"description":"Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end"},"anthropic/claude-opus-4.7":{"id":"anthropic/claude-opus-4.7","name":"Anthropic: Claude Opus 4.7","provider":"anthropic","context_length":1000000,"created":1776351100,"price_in":5,"price_out":25,"input_modalities":["text","image"],"output_modalities":["text"],"description":"Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stron"},"anthropic/claude-opus-4.6-fast":{"id":"anthropic/claude-opus-4.6-fast","name":"Anthropic: Claude Opus 4.6 (Fast)","provider":"anthropic","context_length":1000000,"created":1775592472,"price_in":30,"price_out":150,"input_modalities":["text","image"],"output_modalities":["text"],"description":"Fast-mode variant of [Opus 4.6](/anthropic/claude-opus-4.6) - identical capabilities with higher output speed at premium 6x pricing.\n\nLearn more in Anthropic's docs: https://platfo"},"z-ai/glm-5.1":{"id":"z-ai/glm-5.1","name":"Z.ai: GLM 5.1","provider":"z-ai","context_length":202752,"created":1775578025,"price_in":1.0499999999999998,"price_out":3.5,"input_modalities":["text"],"output_modalities":["text"],"description":"GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interaction"},"google/gemma-4-26b-a4b-it":{"id":"google/gemma-4-26b-a4b-it","name":"Google: Gemma 4 26B A4B ","provider":"google","context_length":262144,"created":1775227989,"price_in":0.06,"price_out":0.33,"input_modalities":["image","text","video"],"output_modalities":["text"],"description":"Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — deli"},"google/gemma-4-31b-it":{"id":"google/gemma-4-31b-it","name":"Google: Gemma 4 31B","provider":"google","context_length":262144,"created":1775148486,"price_in":0.13,"price_out":0.38,"input_modalities":["image","text","video"],"output_modalities":["text"],"description":"Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking"},"qwen/qwen3.6-plus":{"id":"qwen/qwen3.6-plus","name":"Qwen: Qwen3.6 Plus","provider":"qwen","context_length":1000000,"created":1775133557,"price_in":0.325,"price_out":1.95,"input_modalities":["text","image","video"],"output_modalities":["text"],"description":"Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance infe"},"z-ai/glm-5v-turbo":{"id":"z-ai/glm-5v-turbo","name":"Z.ai: GLM 5V Turbo","provider":"z-ai","context_length":202752,"created":1775061458,"price_in":1.2,"price_out":4,"input_modalities":["image","text","video"],"output_modalities":["text"],"description":"GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, exce"},"arcee-ai/trinity-large-thinking":{"id":"arcee-ai/trinity-large-thinking","name":"Arcee AI: Trinity Large Thinking","provider":"arcee-ai","context_length":262144,"created":1775058318,"price_in":0.22,"price_out":0.85,"input_modalities":["text"],"output_modalities":["text"],"description":"Trinity Large Thinking is a powerful open source reasoning model from the team at Arcee AI. It shows strong performance in PinchBench, agentic workloads, and reasoning tasks. Launc"},"x-ai/grok-4.20-multi-agent":{"id":"x-ai/grok-4.20-multi-agent","name":"xAI: Grok 4.20 Multi-Agent","provider":"x-ai","context_length":2000000,"created":1774979158,"price_in":2,"price_out":6,"input_modalities":["text","image","file"],"output_modalities":["text"],"description":"Grok 4.20 Multi-Agent is a variant of xAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate to"},"x-ai/grok-4.20":{"id":"x-ai/grok-4.20","name":"xAI: Grok 4.20","provider":"x-ai","context_length":2000000,"created":1774979019,"price_in":1.25,"price_out":2.5,"input_modalities":["text","image","file"],"output_modalities":["text"],"description":"Grok 4.20 is a reasoning model from xAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict promp"},"google/lyria-3-pro-preview":{"id":"google/lyria-3-pro-preview","name":"Google: Lyria 3 Pro Preview","provider":"google","context_length":1048576,"created":1774907286,"price_in":0,"price_out":0,"input_modalities":["text","image"],"output_modalities":["text","audio"],"description":"Full-length songs are priced at $0.08 per song. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate high-quality"},"google/lyria-3-clip-preview":{"id":"google/lyria-3-clip-preview","name":"Google: Lyria 3 Clip Preview","provider":"google","context_length":1048576,"created":1774907255,"price_in":0,"price_out":0,"input_modalities":["text","image"],"output_modalities":["text","audio"],"description":"30 second duration clips are priced at $0.04 per clip. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate..."},"kwaipilot/kat-coder-pro-v2":{"id":"kwaipilot/kat-coder-pro-v2","name":"Kwaipilot: KAT-Coder-Pro V2","provider":"kwaipilot","context_length":256000,"created":1774649310,"price_in":0.3,"price_out":1.2,"input_modalities":["text"],"output_modalities":["text"],"description":"KAT-Coder-Pro V2 is the latest high-performance model in KwaiKAT’s KAT-Coder series, designed for complex enterprise-grade software engineering and SaaS integration. It builds on t"},"rekaai/reka-edge":{"id":"rekaai/reka-edge","name":"Reka Edge","provider":"rekaai","context_length":16384,"created":1774026965,"price_in":0.09999999999999999,"price_out":0.09999999999999999,"input_modalities":["image","text","video"],"output_modalities":["text"],"description":"Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is optimized specifically to del"},"xiaomi/mimo-v2-omni":{"id":"xiaomi/mimo-v2-omni","name":"Xiaomi: MiMo-V2-Omni","provider":"xiaomi","context_length":262144,"created":1773863703,"price_in":0.39999999999999997,"price_out":2,"input_modalities":["text","audio","image","video"],"output_modalities":["text"],"description":"MiMo-V2-Omni is a frontier omni-modal model that natively processes image, video, and audio inputs within a unified architecture. It combines strong multimodal perception with agen"},"xiaomi/mimo-v2-pro":{"id":"xiaomi/mimo-v2-pro","name":"Xiaomi: MiMo-V2-Pro","provider":"xiaomi","context_length":1048576,"created":1773863643,"price_in":1,"price_out":3,"input_modalities":["text"],"output_modalities":["text"],"description":"MiMo-V2-Pro is Xiaomi's flagship foundation model, featuring over 1T total parameters and a 1M context length, deeply optimized for agentic scenarios. It is highly adaptable to gen"},"minimax/minimax-m2.7":{"id":"minimax/minimax-m2.7","name":"MiniMax: MiniMax M2.7","provider":"minimax","context_length":196608,"created":1773836697,"price_in":0.29900000000000004,"price_out":1.2,"input_modalities":["text"],"output_modalities":["text"],"description":"MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evoluti"},"openai/gpt-5.4-nano":{"id":"openai/gpt-5.4-nano","name":"OpenAI: GPT-5.4 Nano","provider":"openai","context_length":400000,"created":1773748187,"price_in":0.19999999999999998,"price_out":1.25,"input_modalities":["file","image","text"],"output_modalities":["text"],"description":"GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is "},"openai/gpt-5.4-mini":{"id":"openai/gpt-5.4-mini","name":"OpenAI: GPT-5.4 Mini","provider":"openai","context_length":400000,"created":1773748178,"price_in":0.75,"price_out":4.5,"input_modalities":["file","image","text"],"output_modalities":["text"],"description":"GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong perfor"},"mistralai/mistral-small-2603":{"id":"mistralai/mistral-small-2603","name":"Mistral: Mistral Small 4","provider":"mistralai","context_length":262144,"created":1773695685,"price_in":0.15,"price_out":0.6,"input_modalities":["text","image"],"output_modalities":["text"],"description":"Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoni"},"z-ai/glm-5-turbo":{"id":"z-ai/glm-5-turbo","name":"Z.ai: GLM 5 Turbo","provider":"z-ai","context_length":202752,"created":1773583573,"price_in":1.2,"price_out":4,"input_modalities":["text"],"output_modalities":["text"],"description":"GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for real-wor"},"nvidia/nemotron-3-super-120b-a12b":{"id":"nvidia/nemotron-3-super-120b-a12b","name":"NVIDIA: Nemotron 3 Super","provider":"nvidia","context_length":262144,"created":1773245239,"price_in":0.09,"price_out":0.44999999999999996,"input_modalities":["text"],"output_modalities":["text"],"description":"NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. B"},"bytedance-seed/seed-2.0-lite":{"id":"bytedance-seed/seed-2.0-lite","name":"ByteDance Seed: Seed-2.0-Lite","provider":"bytedance-seed","context_length":262144,"created":1773157231,"price_in":0.25,"price_out":2,"input_modalities":["text","image","video"],"output_modalities":["text"],"description":"Seed-2.0-Lite is a versatile, cost‑efficient enterprise workhorse that delivers strong multimodal and agent capabilities while offering noticeably lower latency, making it a practi"},"qwen/qwen3.5-9b":{"id":"qwen/qwen3.5-9b","name":"Qwen: Qwen3.5-9B","provider":"qwen","context_length":262144,"created":1773152396,"price_in":0.04,"price_out":0.15,"input_modalities":["text","image","video"],"output_modalities":["text"],"description":"Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architectur"},"openai/gpt-5.4-pro":{"id":"openai/gpt-5.4-pro","name":"OpenAI: GPT-5.4 Pro","provider":"openai","context_length":1050000,"created":1772734366,"price_in":30,"price_out":180,"input_modalities":["text","image","file"],"output_modalities":["text"],"description":"GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token"},"openai/gpt-5.4":{"id":"openai/gpt-5.4","name":"OpenAI: GPT-5.4","provider":"openai","context_length":1050000,"created":1772734352,"price_in":2.5,"price_out":15,"input_modalities":["text","image","file"],"output_modalities":["text"],"description":"GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for."},"inception/mercury-2":{"id":"inception/mercury-2","name":"Inception: Mercury 2","provider":"inception","context_length":128000,"created":1772636275,"price_in":0.25,"price_out":0.75,"input_modalities":["text"],"output_modalities":["text"],"description":"Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercury 2 produces and refines multiple token"},"openai/gpt-5.3-chat":{"id":"openai/gpt-5.3-chat","name":"OpenAI: GPT-5.3 Chat","provider":"openai","context_length":128000,"created":1772564061,"price_in":1.75,"price_out":14,"input_modalities":["text","image","file"],"output_modalities":["text"],"description":"GPT-5.3 Chat is an update to ChatGPT's most-used model that makes everyday conversations smoother, more useful, and more directly helpful. It delivers more accurate answers with be"},"google/gemini-3.1-flash-lite-preview":{"id":"google/gemini-3.1-flash-lite-preview","name":"Google: Gemini 3.1 Flash Lite Preview","provider":"google","context_length":1048576,"created":1772512673,"price_in":0.25,"price_out":1.5,"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"description":"Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality and approaches Gemini 2"},"bytedance-seed/seed-2.0-mini":{"id":"bytedance-seed/seed-2.0-mini","name":"ByteDance Seed: Seed-2.0-Mini","provider":"bytedance-seed","context_length":262144,"created":1772131107,"price_in":0.09999999999999999,"price_out":0.39999999999999997,"input_modalities":["text","image","video"],"output_modalities":["text"],"description":"Seed-2.0-mini targets latency-sensitive, high-concurrency, and cost-sensitive scenarios, emphasizing fast response and flexible inference deployment. It delivers performance compar"},"google/gemini-3.1-flash-image-preview":{"id":"google/gemini-3.1-flash-image-preview","name":"Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)","provider":"google","context_length":65536,"created":1772119558,"price_in":0.5,"price_out":3,"input_modalities":["image","text"],"output_modalities":["image","text"],"description":"Gemini 3.1 Flash Image Preview, a.k.a. \"Nano Banana 2,\" is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. "},"qwen/qwen3.5-35b-a3b":{"id":"qwen/qwen3.5-35b-a3b","name":"Qwen: Qwen3.5-35B-A3B","provider":"qwen","context_length":262144,"created":1772053822,"price_in":0.14,"price_out":1,"input_modalities":["text","image","video"],"output_modalities":["text"],"description":"The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, "},"qwen/qwen3.5-27b":{"id":"qwen/qwen3.5-27b","name":"Qwen: Qwen3.5-27B","provider":"qwen","context_length":262144,"created":1772053810,"price_in":0.195,"price_out":1.56,"input_modalities":["text","image","video"],"output_modalities":["text"],"description":"The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its ov"},"qwen/qwen3.5-122b-a10b":{"id":"qwen/qwen3.5-122b-a10b","name":"Qwen: Qwen3.5-122B-A10B","provider":"qwen","context_length":262144,"created":1772053789,"price_in":0.26,"price_out":2.08,"input_modalities":["text","image","video"],"output_modalities":["text"],"description":"The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving "},"qwen/qwen3.5-flash-02-23":{"id":"qwen/qwen3.5-flash-02-23","name":"Qwen: Qwen3.5-Flash","provider":"qwen","context_length":1000000,"created":1772053776,"price_in":0.065,"price_out":0.26,"input_modalities":["text","image","video"],"output_modalities":["text"],"description":"The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving hi"},"liquid/lfm-2-24b-a2b":{"id":"liquid/lfm-2-24b-a2b","name":"LiquidAI: LFM2-24B-A2B","provider":"liquid","context_length":32768,"created":1772048711,"price_in":0.03,"price_out":0.12,"input_modalities":["text"],"output_modalities":["text"],"description":"LFM2-24B-A2B is the largest model in the LFM2 family of hybrid architectures designed for efficient on-device deployment. Built as a 24B parameter Mixture-of-Experts model with onl"},"google/gemini-3.1-pro-preview-customtools":{"id":"google/gemini-3.1-pro-preview-customtools","name":"Google: Gemini 3.1 Pro Preview Custom Tools","provider":"google","context_length":1048576,"created":1772045923,"price_in":2,"price_out":12,"input_modalities":["text","audio","image","video","file"],"output_modalities":["text"],"description":"Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection behavior by preventing overuse of a general bash tool when more efficient third-part"},"openai/gpt-5.3-codex":{"id":"openai/gpt-5.3-codex","name":"OpenAI: GPT-5.3-Codex","provider":"openai","context_length":400000,"created":1771959164,"price_in":1.75,"price_out":14,"input_modalities":["text","image","file"],"output_modalities":["text"],"description":"GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional k"},"aion-labs/aion-2.0":{"id":"aion-labs/aion-2.0","name":"AionLabs: Aion-2.0","provider":"aion-labs","context_length":131072,"created":1771881306,"price_in":0.7999999999999999,"price_out":1.5999999999999999,"input_modalities":["text"],"output_modalities":["text"],"description":"Aion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling. It is particularly strong at introducing tension, crises, and conflict into stories, ma"},"google/gemini-3.1-pro-preview":{"id":"google/gemini-3.1-pro-preview","name":"Google: Gemini 3.1 Pro Preview","provider":"google","context_length":1048576,"created":1771509627,"price_in":2,"price_out":12,"input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"description":"Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage acro"},"anthropic/claude-sonnet-4.6":{"id":"anthropic/claude-sonnet-4.6","name":"Anthropic: Claude Sonnet 4.6","provider":"anthropic","context_length":1000000,"created":1771342990,"price_in":3,"price_out":15,"input_modalities":["text","image"],"output_modalities":["text"],"description":"Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex c"},"qwen/qwen3.5-plus-02-15":{"id":"qwen/qwen3.5-plus-02-15","name":"Qwen: Qwen3.5 Plus 2026-02-15","provider":"qwen","context_length":1000000,"created":1771229416,"price_in":0.26,"price_out":1.56,"input_modalities":["text","image","video"],"output_modalities":["text"],"description":"The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achievin"},"qwen/qwen3.5-397b-a17b":{"id":"qwen/qwen3.5-397b-a17b","name":"Qwen: Qwen3.5 397B A17B","provider":"qwen","context_length":262144,"created":1771223018,"price_in":0.39,"price_out":2.34,"input_modalities":["text","image","video"],"output_modalities":["text"],"description":"The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, ach"},"minimax/minimax-m2.5":{"id":"minimax/minimax-m2.5","name":"MiniMax: MiniMax M2.5","provider":"minimax","context_length":196608,"created":1770908502,"price_in":0.15,"price_out":1.15,"input_modalities":["text"],"output_modalities":["text"],"description":"MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon th"},"z-ai/glm-5":{"id":"z-ai/glm-5","name":"Z.ai: GLM 5","provider":"z-ai","context_length":202752,"created":1770829182,"price_in":0.6,"price_out":1.92,"input_modalities":["text"],"output_modalities":["text"],"description":"GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-gr"},"qwen/qwen3-max-thinking":{"id":"qwen/qwen3-max-thinking","name":"Qwen: Qwen3 Max Thinking","provider":"qwen","context_length":262144,"created":1770671901,"price_in":0.78,"price_out":3.9,"input_modalities":["text"],"output_modalities":["text"],"description":"Qwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series, designed for high-stakes cognitive tasks that require deep, multi-step reasoning. By significantly scaling m"},"anthropic/claude-opus-4.6":{"id":"anthropic/claude-opus-4.6","name":"Anthropic: Claude Opus 4.6","provider":"anthropic","context_length":1000000,"created":1770219050,"price_in":5,"price_out":25,"input_modalities":["text","image"],"output_modalities":["text"],"description":"Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, maki"},"qwen/qwen3-coder-next":{"id":"qwen/qwen3-coder-next","name":"Qwen: Qwen3 Coder Next","provider":"qwen","context_length":262144,"created":1770164101,"price_in":0.11,"price_out":0.7999999999999999,"input_modalities":["text"],"output_modalities":["text"],"description":"Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only"},"openrouter/free":{"id":"openrouter/free","name":"Free Models Router","provider":"openrouter","context_length":200000,"created":1769917427,"price_in":0,"price_out":0,"input_modalities":["text","image"],"output_modalities":["text"],"description":"The simplest way to get free inference. openrouter/free is a router that selects free models at random from the models available on OpenRouter. The router smartly filters for model"},"stepfun/step-3.5-flash":{"id":"stepfun/step-3.5-flash","name":"StepFun: Step 3.5 Flash","provider":"stepfun","context_length":262144,"created":1769728337,"price_in":0.09999999999999999,"price_out":0.3,"input_modalities":["text"],"output_modalities":["text"],"description":"Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parame"},"arcee-ai/trinity-large-preview":{"id":"arcee-ai/trinity-large-preview","name":"Arcee AI: Trinity Large Preview","provider":"arcee-ai","context_length":131000,"created":1769552670,"price_in":0.15,"price_out":0.44999999999999996,"input_modalities":["text"],"output_modalities":["text"],"description":"Trinity-Large-Preview is a frontier-scale open-weight language model from Arcee, built as a 400B-parameter sparse Mixture-of-Experts with 13B active parameters per token using 4-of"},"moonshotai/kimi-k2.5":{"id":"moonshotai/kimi-k2.5","name":"MoonshotAI: Kimi K2.5","provider":"moonshotai","context_length":262144,"created":1769487076,"price_in":0.44,"price_out":2,"input_modalities":["text","image"],"output_modalities":["text"],"description":"Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued p"},"upstage/solar-pro-3":{"id":"upstage/solar-pro-3","name":"Upstage: Solar Pro 3","provider":"upstage","context_length":128000,"created":1769481200,"price_in":0.15,"price_out":0.6,"input_modalities":["text"],"output_modalities":["text"],"description":"Solar Pro 3 is Upstage's powerful Mixture-of-Experts (MoE) language model. With 102B total parameters and 12B active parameters per forward pass, it delivers exceptional performanc"},"minimax/minimax-m2-her":{"id":"minimax/minimax-m2-her","name":"MiniMax: MiniMax M2-her","provider":"minimax","context_length":65536,"created":1769177239,"price_in":0.3,"price_out":1.2,"input_modalities":["text"],"output_modalities":["text"],"description":"MiniMax M2-her is a dialogue-first large language model built for immersive roleplay, character-driven chat, and expressive multi-turn conversations. Designed to stay consistent in"},"writer/palmyra-x5":{"id":"writer/palmyra-x5","name":"Writer: Palmyra X5","provider":"writer","context_length":1040000,"created":1769003823,"price_in":0.6,"price_out":6,"input_modalities":["text"],"output_modalities":["text"],"description":"Palmyra X5 is Writer's most advanced model, purpose-built for building and scaling AI agents across the enterprise. It delivers industry-leading speed and efficiency on context win"},"openai/gpt-audio":{"id":"openai/gpt-audio","name":"OpenAI: GPT Audio","provider":"openai","context_length":128000,"created":1768862569,"price_in":2.5,"price_out":10,"input_modalities":["text","audio"],"output_modalities":["text","audio"],"description":"The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice con"},"openai/gpt-audio-mini":{"id":"openai/gpt-audio-mini","name":"OpenAI: GPT Audio Mini","provider":"openai","context_length":128000,"created":1768859419,"price_in":0.6,"price_out":2.4,"input_modalities":["text","audio"],"output_modalities":["text","audio"],"description":"A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Input is priced at $0."},"z-ai/glm-4.7-flash":{"id":"z-ai/glm-4.7-flash","name":"Z.ai: GLM 4.7 Flash","provider":"z-ai","context_length":202752,"created":1768833913,"price_in":0.06,"price_out":0.39999999999999997,"input_modalities":["text"],"output_modalities":["text"],"description":"As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding ca"},"openai/gpt-5.2-codex":{"id":"openai/gpt-5.2-codex","name":"OpenAI: GPT-5.2-Codex","provider":"openai","context_length":400000,"created":1768409315,"price_in":1.75,"price_out":14,"input_modalities":["text","image"],"output_modalities":["text"],"description":"GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, in"},"bytedance-seed/seed-1.6-flash":{"id":"bytedance-seed/seed-1.6-flash","name":"ByteDance Seed: Seed 1.6 Flash","provider":"bytedance-seed","context_length":262144,"created":1766505011,"price_in":0.075,"price_out":0.3,"input_modalities":["image","text","video"],"output_modalities":["text"],"description":"Seed 1.6 Flash is an ultra-fast multimodal deep thinking model by ByteDance Seed, supporting both text and visual understanding. It features a 256k context window and can generate "},"bytedance-seed/seed-1.6":{"id":"bytedance-seed/seed-1.6","name":"ByteDance Seed: Seed 1.6","provider":"bytedance-seed","context_length":262144,"created":1766504997,"price_in":0.25,"price_out":2,"input_modalities":["image","text","video"],"output_modalities":["text"],"description":"Seed 1.6 is a general-purpose model released by the ByteDance Seed team. It incorporates multimodal capabilities and adaptive deep thinking with a 256K context window."},"minimax/minimax-m2.1":{"id":"minimax/minimax-m2.1","name":"MiniMax: MiniMax M2.1","provider":"minimax","context_length":196608,"created":1766454997,"price_in":0.29,"price_out":0.95,"input_modalities":["text"],"output_modalities":["text"],"description":"MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated par"},"z-ai/glm-4.7":{"id":"z-ai/glm-4.7","name":"Z.ai: GLM 4.7","provider":"z-ai","context_length":202752,"created":1766378014,"price_in":0.39999999999999997,"price_out":1.75,"input_modalities":["text"],"output_modalities":["text"],"description":"GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates sign"},"google/gemini-3-flash-preview":{"id":"google/gemini-3-flash-preview","name":"Google: Gemini 3 Flash Preview","provider":"google","context_length":1048576,"created":1765987078,"price_in":0.5,"price_out":3,"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"description":"Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and t"},"xiaomi/mimo-v2-flash":{"id":"xiaomi/mimo-v2-flash","name":"Xiaomi: MiMo-V2-Flash","provider":"xiaomi","context_length":262144,"created":1765731308,"price_in":0.09999999999999999,"price_out":0.3,"input_modalities":["text"],"output_modalities":["text"],"description":"MiMo-V2-Flash is an open-source foundation language model developed by Xiaomi. It is a Mixture-of-Experts model with 309B total parameters and 15B active parameters, adopting hybri"},"nvidia/nemotron-3-nano-30b-a3b":{"id":"nvidia/nemotron-3-nano-30b-a3b","name":"NVIDIA: Nemotron 3 Nano 30B A3B","provider":"nvidia","context_length":262144,"created":1765731275,"price_in":0.049999999999999996,"price_out":0.19999999999999998,"input_modalities":["text"],"output_modalities":["text"],"description":"NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully"},"openai/gpt-5.2-chat":{"id":"openai/gpt-5.2-chat","name":"OpenAI: GPT-5.2 Chat","provider":"openai","context_length":128000,"created":1765389783,"price_in":1.75,"price_out":14,"input_modalities":["file","image","text"],"output_modalities":["text"],"description":"GPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning"},"openai/gpt-5.2-pro":{"id":"openai/gpt-5.2-pro","name":"OpenAI: GPT-5.2 Pro","provider":"openai","context_length":400000,"created":1765389780,"price_in":21,"price_out":168,"input_modalities":["image","text","file"],"output_modalities":["text"],"description":"GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that requi"},"openai/gpt-5.2":{"id":"openai/gpt-5.2","name":"OpenAI: GPT-5.2","provider":"openai","context_length":400000,"created":1765389775,"price_in":1.75,"price_out":14,"input_modalities":["file","image","text"],"output_modalities":["text"],"description":"GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate co"},"mistralai/devstral-2512":{"id":"mistralai/devstral-2512","name":"Mistral: Devstral 2 2512","provider":"mistralai","context_length":262144,"created":1765285419,"price_in":0.39999999999999997,"price_out":2,"input_modalities":["text"],"output_modalities":["text"],"description":"Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. De"},"relace/relace-search":{"id":"relace/relace-search","name":"Relace: Relace Search","provider":"relace","context_length":256000,"created":1765213560,"price_in":1,"price_out":3,"input_modalities":["text"],"output_modalities":["text"],"description":"The relace-search model uses 4-12 `view_file` and `grep` tools in parallel to explore a codebase and return relevant files to the user request. In contrast to RAG, relace-search pe"},"z-ai/glm-4.6v":{"id":"z-ai/glm-4.6v","name":"Z.ai: GLM 4.6V","provider":"z-ai","context_length":131072,"created":1765207462,"price_in":0.3,"price_out":0.8999999999999999,"input_modalities":["image","text","video"],"output_modalities":["text"],"description":"GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K to"},"nex-agi/deepseek-v3.1-nex-n1":{"id":"nex-agi/deepseek-v3.1-nex-n1","name":"Nex AGI: DeepSeek V3.1 Nex N1","provider":"nex-agi","context_length":131072,"created":1765204393,"price_in":0.135,"price_out":0.5,"input_modalities":["text"],"output_modalities":["text"],"description":"DeepSeek V3.1 Nex-N1 is the flagship release of the Nex-N1 series — a post-trained model designed to highlight agent autonomy, tool use, and real-world productivity. Nex-N1 demonst"},"essentialai/rnj-1-instruct":{"id":"essentialai/rnj-1-instruct","name":"EssentialAI: Rnj 1 Instruct","provider":"essentialai","context_length":32768,"created":1765094847,"price_in":0.15,"price_out":0.15,"input_modalities":["text"],"output_modalities":["text"],"description":"Rnj-1 is an 8B-parameter, dense, open-weight model family developed by Essential AI and trained from scratch with a focus on programming, math, and scientific reasoning. The model "},"openrouter/bodybuilder":{"id":"openrouter/bodybuilder","name":"Body Builder (beta)","provider":"openrouter","context_length":128000,"created":1764903653,"price_in":-1000000,"price_out":-1000000,"input_modalities":["text"],"output_modalities":["text"],"description":"Transform your natural language requests into structured OpenRouter API request objects. Describe what you want to accomplish with AI models, and Body Builder will construct the ap"},"openai/gpt-5.1-codex-max":{"id":"openai/gpt-5.1-codex-max","name":"OpenAI: GPT-5.1-Codex-Max","provider":"openai","context_length":400000,"created":1764878934,"price_in":1.25,"price_out":10,"input_modalities":["text","image"],"output_modalities":["text"],"description":"GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is based on an updated version of the 5.1 reasonin"},"amazon/nova-2-lite-v1":{"id":"amazon/nova-2-lite-v1","name":"Amazon: Nova 2 Lite","provider":"amazon","context_length":1000000,"created":1764696672,"price_in":0.3,"price_out":2.5,"input_modalities":["text","image","video","file"],"output_modalities":["text"],"description":"Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. Nova 2 Lite demonstrates standout capabilit"},"mistralai/ministral-14b-2512":{"id":"mistralai/ministral-14b-2512","name":"Mistral: Ministral 3 14B 2512","provider":"mistralai","context_length":262144,"created":1764681735,"price_in":0.19999999999999998,"price_out":0.19999999999999998,"input_modalities":["text","image"],"output_modalities":["text"],"description":"The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and"},"mistralai/ministral-8b-2512":{"id":"mistralai/ministral-8b-2512","name":"Mistral: Ministral 3 8B 2512","provider":"mistralai","context_length":262144,"created":1764681654,"price_in":0.15,"price_out":0.15,"input_modalities":["text","image"],"output_modalities":["text"],"description":"A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities."},"mistralai/ministral-3b-2512":{"id":"mistralai/ministral-3b-2512","name":"Mistral: Ministral 3 3B 2512","provider":"mistralai","context_length":131072,"created":1764681560,"price_in":0.09999999999999999,"price_out":0.09999999999999999,"input_modalities":["text","image"],"output_modalities":["text"],"description":"The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities."},"mistralai/mistral-large-2512":{"id":"mistralai/mistral-large-2512","name":"Mistral: Mistral Large 3 2512","provider":"mistralai","context_length":262144,"created":1764624472,"price_in":0.5,"price_out":1.5,"input_modalities":["text","image"],"output_modalities":["text"],"description":"Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apa"},"arcee-ai/trinity-mini":{"id":"arcee-ai/trinity-mini","name":"Arcee AI: Trinity Mini","provider":"arcee-ai","context_length":131072,"created":1764601720,"price_in":0.045,"price_out":0.15,"input_modalities":["text"],"output_modalities":["text"],"description":"Trinity Mini is a 26B-parameter (3B active) sparse mixture-of-experts language model featuring 128 experts with 8 active per token. Engineered for efficient reasoning over long con"},"deepseek/deepseek-v3.2-speciale":{"id":"deepseek/deepseek-v3.2-speciale","name":"DeepSeek: DeepSeek V3.2 Speciale","provider":"deepseek","context_length":163840,"created":1764594837,"price_in":0.28700000000000003,"price_out":0.431,"input_modalities":["text"],"output_modalities":["text"],"description":"DeepSeek-V3.2-Speciale is a high-compute variant of DeepSeek-V3.2 optimized for maximum reasoning and agentic performance. It builds on DeepSeek Sparse Attention (DSA) for efficien"},"deepseek/deepseek-v3.2":{"id":"deepseek/deepseek-v3.2","name":"DeepSeek: DeepSeek V3.2","provider":"deepseek","context_length":131072,"created":1764594642,"price_in":0.252,"price_out":0.378,"input_modalities":["text"],"output_modalities":["text"],"description":"DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse At"},"prime-intellect/intellect-3":{"id":"prime-intellect/intellect-3","name":"Prime Intellect: INTELLECT-3","provider":"prime-intellect","context_length":131072,"created":1764212534,"price_in":0.19999999999999998,"price_out":1.1,"input_modalities":["text"],"output_modalities":["text"],"description":"INTELLECT-3 is a 106B-parameter Mixture-of-Experts model (12B active) post-trained from GLM-4.5-Air-Base using supervised fine-tuning (SFT) followed by large-scale reinforcement le"},"anthropic/claude-opus-4.5":{"id":"anthropic/claude-opus-4.5","name":"Anthropic: Claude Opus 4.5","provider":"anthropic","context_length":200000,"created":1764010580,"price_in":5,"price_out":25,"input_modalities":["file","image","text"],"output_modalities":["text"],"description":"Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal ca"},"allenai/olmo-3-32b-think":{"id":"allenai/olmo-3-32b-think","name":"AllenAI: Olmo 3 32B Think","provider":"allenai","context_length":65536,"created":1763758276,"price_in":0.15,"price_out":0.5,"input_modalities":["text"],"output_modalities":["text"],"description":"Olmo 3 32B Think is a large-scale, 32-billion-parameter model purpose-built for deep reasoning, complex logic chains and advanced instruction-following scenarios. Its capacity enab"},"google/gemini-3-pro-image-preview":{"id":"google/gemini-3-pro-image-preview","name":"Google: Nano Banana Pro (Gemini 3 Pro Image Preview)","provider":"google","context_length":65536,"created":1763653797,"price_in":2,"price_out":12,"input_modalities":["image","text"],"output_modalities":["image","text"],"description":"Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reas"},"x-ai/grok-4.1-fast":{"id":"x-ai/grok-4.1-fast","name":"xAI: Grok 4.1 Fast","provider":"x-ai","context_length":2000000,"created":1763587502,"price_in":0.19999999999999998,"price_out":0.5,"input_modalities":["text","image","file"],"output_modalities":["text"],"description":"Grok 4.1 Fast is xAI's best agentic tool calling model that shines in real-world use cases like customer support and deep research. 2M context window. Reasoning can be enabled/disa"},"deepcogito/cogito-v2.1-671b":{"id":"deepcogito/cogito-v2.1-671b","name":"Deep Cogito: Cogito v2.1 671B","provider":"deepcogito","context_length":128000,"created":1763071233,"price_in":1.25,"price_out":1.25,"input_modalities":["text"],"output_modalities":["text"],"description":"Cogito v2.1 671B MoE represents one of the strongest open models globally, matching performance of frontier closed and open models. This model is trained using self play with reinf"},"openai/gpt-5.1":{"id":"openai/gpt-5.1","name":"OpenAI: GPT-5.1","provider":"openai","context_length":400000,"created":1763060305,"price_in":1.25,"price_out":10,"input_modalities":["image","text","file"],"output_modalities":["text"],"description":"GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style"},"openai/gpt-5.1-chat":{"id":"openai/gpt-5.1-chat","name":"OpenAI: GPT-5.1 Chat","provider":"openai","context_length":128000,"created":1763060302,"price_in":1.25,"price_out":10,"input_modalities":["file","image","text"],"output_modalities":["text"],"description":"GPT-5.1 Chat (AKA Instant is the fast, lightweight member of the 5.1 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning "},"openai/gpt-5.1-codex":{"id":"openai/gpt-5.1-codex","name":"OpenAI: GPT-5.1-Codex","provider":"openai","context_length":400000,"created":1763060298,"price_in":1.25,"price_out":10,"input_modalities":["text","image"],"output_modalities":["text"],"description":"GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, indepe"},"openai/gpt-5.1-codex-mini":{"id":"openai/gpt-5.1-codex-mini","name":"OpenAI: GPT-5.1-Codex-Mini","provider":"openai","context_length":400000,"created":1763057820,"price_in":0.25,"price_out":2,"input_modalities":["image","text"],"output_modalities":["text"],"description":"GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex"},"moonshotai/kimi-k2-thinking":{"id":"moonshotai/kimi-k2-thinking","name":"MoonshotAI: Kimi K2 Thinking","provider":"moonshotai","context_length":262144,"created":1762440622,"price_in":0.6,"price_out":2.5,"input_modalities":["text"],"output_modalities":["text"],"description":"Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-"},"amazon/nova-premier-v1":{"id":"amazon/nova-premier-v1","name":"Amazon: Nova Premier 1.0","provider":"amazon","context_length":1000000,"created":1761950332,"price_in":2.5,"price_out":12.5,"input_modalities":["text","image"],"output_modalities":["text"],"description":"Amazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks and for use as the best teacher for distilling custom models."},"perplexity/sonar-pro-search":{"id":"perplexity/sonar-pro-search","name":"Perplexity: Sonar Pro Search","provider":"perplexity","context_length":200000,"created":1761854366,"price_in":3,"price_out":15,"input_modalities":["text","image"],"output_modalities":["text"],"description":"Exclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system. It is designed for deeper reasoning and analysis. "},"mistralai/voxtral-small-24b-2507":{"id":"mistralai/voxtral-small-24b-2507","name":"Mistral: Voxtral Small 24B 2507","provider":"mistralai","context_length":32000,"created":1761835144,"price_in":0.09999999999999999,"price_out":0.3,"input_modalities":["text","audio"],"output_modalities":["text"],"description":"Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech tran"},"openai/gpt-oss-safeguard-20b":{"id":"openai/gpt-oss-safeguard-20b","name":"OpenAI: gpt-oss-safeguard-20b","provider":"openai","context_length":131072,"created":1761752836,"price_in":0.075,"price_out":0.3,"input_modalities":["text"],"output_modalities":["text"],"description":"gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety"},"minimax/minimax-m2":{"id":"minimax/minimax-m2","name":"MiniMax: MiniMax M2","provider":"minimax","context_length":196608,"created":1761252093,"price_in":0.255,"price_out":1,"input_modalities":["text"],"output_modalities":["text"],"description":"MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it de"},"qwen/qwen3-vl-32b-instruct":{"id":"qwen/qwen3-vl-32b-instruct","name":"Qwen: Qwen3 VL 32B Instruct","provider":"qwen","context_length":131072,"created":1761231332,"price_in":0.10400000000000001,"price_out":0.41600000000000004,"input_modalities":["text","image"],"output_modalities":["text"],"description":"Qwen3-VL-32B-Instruct is a large-scale multimodal vision-language model designed for high-precision understanding and reasoning across text, images, and video. With 32 billion para"},"ibm-granite/granite-4.0-h-micro":{"id":"ibm-granite/granite-4.0-h-micro","name":"IBM: Granite 4.0 Micro","provider":"ibm-granite","context_length":131000,"created":1760927695,"price_in":0.017,"price_out":0.11,"input_modalities":["text"],"output_modalities":["text"],"description":"Granite-4.0-H-Micro is a 3B parameter from the Granite 4 family of models. These models are the latest in a series of models released by IBM. They are fine-tuned for long..."},"microsoft/phi-4-mini-instruct":{"id":"microsoft/phi-4-mini-instruct","name":"Microsoft: Phi 4 Mini Instruct","provider":"microsoft","context_length":128000,"created":1760726049,"price_in":0.08,"price_out":0.35,"input_modalities":["text"],"output_modalities":["text"],"description":"Phi-4-mini-instruct is a lightweight open model built upon synthetic data and filtered publicly available websites - with a focus on high-quality, reasoning dense data. The model b"},"openai/gpt-5-image-mini":{"id":"openai/gpt-5-image-mini","name":"OpenAI: GPT-5 Image Mini","provider":"openai","context_length":400000,"created":1760624583,"price_in":2.5,"price_out":2,"input_modalities":["file","image","text"],"output_modalities":["image","text"],"description":"GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by [GPT-5 Mini](https://openrouter.ai/openai/gpt-5-mini), with GPT Image 1 Mini for efficient image gener"},"anthropic/claude-haiku-4.5":{"id":"anthropic/claude-haiku-4.5","name":"Anthropic: Claude Haiku 4.5","provider":"anthropic","context_length":200000,"created":1760547638,"price_in":1,"price_out":5,"input_modalities":["image","text"],"output_modalities":["text"],"description":"Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Clau"},"qwen/qwen3-vl-8b-thinking":{"id":"qwen/qwen3-vl-8b-thinking","name":"Qwen: Qwen3 VL 8B Thinking","provider":"qwen","context_length":131072,"created":1760463746,"price_in":0.117,"price_out":1.365,"input_modalities":["image","text"],"output_modalities":["text"],"description":"Qwen3-VL-8B-Thinking is the reasoning-optimized variant of the Qwen3-VL-8B multimodal model, designed for advanced visual and textual reasoning across complex scenes, documents, an"},"qwen/qwen3-vl-8b-instruct":{"id":"qwen/qwen3-vl-8b-instruct","name":"Qwen: Qwen3 VL 8B Instruct","provider":"qwen","context_length":131072,"created":1760463308,"price_in":0.08,"price_out":0.5,"input_modalities":["image","text"],"output_modalities":["text"],"description":"Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features"},"openai/gpt-5-image":{"id":"openai/gpt-5-image","name":"OpenAI: GPT-5 Image","provider":"openai","context_length":400000,"created":1760447986,"price_in":10,"price_out":10,"input_modalities":["image","text","file"],"output_modalities":["image","text"],"description":"[GPT-5](https://openrouter.ai/openai/gpt-5) Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities. It offers major improvements in reasoning, code"},"openai/o3-deep-research":{"id":"openai/o3-deep-research","name":"OpenAI: o3 Deep Research","provider":"openai","context_length":200000,"created":1760129661,"price_in":10,"price_out":40,"input_modalities":["image","text","file"],"output_modalities":["text"],"description":"o3-deep-research is OpenAI's advanced model for deep research, designed to tackle complex, multi-step research tasks.\n\nNote: This model always uses the 'web_search' tool which adds"},"openai/o4-mini-deep-research":{"id":"openai/o4-mini-deep-research","name":"OpenAI: o4 Mini Deep Research","provider":"openai","context_length":200000,"created":1760129642,"price_in":2,"price_out":8,"input_modalities":["file","image","text"],"output_modalities":["text"],"description":"o4-mini-deep-research is OpenAI's faster, more affordable deep research model—ideal for tackling complex, multi-step research tasks.\n\nNote: This model always uses the 'web_search' "},"nvidia/llama-3.3-nemotron-super-49b-v1.5":{"id":"nvidia/llama-3.3-nemotron-super-49b-v1.5","name":"NVIDIA: Llama 3.3 Nemotron Super 49B V1.5","provider":"nvidia","context_length":131072,"created":1760101395,"price_in":0.09999999999999999,"price_out":0.39999999999999997,"input_modalities":["text"],"output_modalities":["text"],"description":"Llama-3.3-Nemotron-Super-49B-v1.5 is a 49B-parameter, English-centric reasoning/chat model derived from Meta’s Llama-3.3-70B-Instruct with a 128K context. It’s post-trained for age"},"baidu/ernie-4.5-21b-a3b-thinking":{"id":"baidu/ernie-4.5-21b-a3b-thinking","name":"Baidu: ERNIE 4.5 21B A3B Thinking","provider":"baidu","context_length":131072,"created":1760048887,"price_in":0.07,"price_out":0.28,"input_modalities":["text"],"output_modalities":["text"],"description":"ERNIE-4.5-21B-A3B-Thinking is Baidu's upgraded lightweight MoE model, refined to boost reasoning depth and quality for top-tier performance in logical puzzles, math, science, codin"},"google/gemini-2.5-flash-image":{"id":"google/gemini-2.5-flash-image","name":"Google: Nano Banana (Gemini 2.5 Flash Image)","provider":"google","context_length":32768,"created":1759870431,"price_in":0.3,"price_out":2.5,"input_modalities":["image","text"],"output_modalities":["image","text"],"description":"Gemini 2.5 Flash Image, a.k.a. \"Nano Banana,\" is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image gene"},"qwen/qwen3-vl-30b-a3b-thinking":{"id":"qwen/qwen3-vl-30b-a3b-thinking","name":"Qwen: Qwen3 VL 30B A3B Thinking","provider":"qwen","context_length":131072,"created":1759794479,"price_in":0.13,"price_out":1.56,"input_modalities":["text","image"],"output_modalities":["text"],"description":"Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM"},"qwen/qwen3-vl-30b-a3b-instruct":{"id":"qwen/qwen3-vl-30b-a3b-instruct","name":"Qwen: Qwen3 VL 30B A3B Instruct","provider":"qwen","context_length":131072,"created":1759794476,"price_in":0.13,"price_out":0.52,"input_modalities":["text","image"],"output_modalities":["text"],"description":"Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-foll"},"openai/gpt-5-pro":{"id":"openai/gpt-5-pro","name":"OpenAI: GPT-5 Pro","provider":"openai","context_length":400000,"created":1759776663,"price_in":15,"price_out":120,"input_modalities":["image","text","file"],"output_modalities":["text"],"description":"GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step "},"z-ai/glm-4.6":{"id":"z-ai/glm-4.6","name":"Z.ai: GLM 4.6","provider":"z-ai","context_length":204800,"created":1759235576,"price_in":0.39,"price_out":1.9,"input_modalities":["text"],"output_modalities":["text"],"description":"Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to "},"anthropic/claude-sonnet-4.5":{"id":"anthropic/claude-sonnet-4.5","name":"Anthropic: Claude Sonnet 4.5","provider":"anthropic","context_length":1000000,"created":1759161676,"price_in":3,"price_out":15,"input_modalities":["text","image","file"],"output_modalities":["text"],"description":"Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchm"},"deepseek/deepseek-v3.2-exp":{"id":"deepseek/deepseek-v3.2-exp","name":"DeepSeek: DeepSeek V3.2 Exp","provider":"deepseek","context_length":163840,"created":1759150481,"price_in":0.27,"price_out":0.41,"input_modalities":["text"],"output_modalities":["text"],"description":"DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attentio"},"thedrummer/cydonia-24b-v4.1":{"id":"thedrummer/cydonia-24b-v4.1","name":"TheDrummer: Cydonia 24B V4.1","provider":"thedrummer","context_length":131072,"created":1758931878,"price_in":0.3,"price_out":0.5,"input_modalities":["text"],"output_modalities":["text"],"description":"Uncensored and creative writing model based on Mistral Small 3.2 24B with good recall, prompt adherence, and intelligence."},"relace/relace-apply-3":{"id":"relace/relace-apply-3","name":"Relace: Relace Apply 3","provider":"relace","context_length":256000,"created":1758891572,"price_in":0.85,"price_out":1.25,"input_modalities":["text"],"output_modalities":["text"],"description":"Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from GPT-4o, Claude, and others into your fil"},"google/gemini-2.5-flash-lite-preview-09-2025":{"id":"google/gemini-2.5-flash-lite-preview-09-2025","name":"Google: Gemini 2.5 Flash Lite Preview 09-2025","provider":"google","context_length":1048576,"created":1758819686,"price_in":0.09999999999999999,"price_out":0.39999999999999997,"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"description":"Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token ge"},"qwen/qwen3-vl-235b-a22b-thinking":{"id":"qwen/qwen3-vl-235b-a22b-thinking","name":"Qwen: Qwen3 VL 235B A22B Thinking","provider":"qwen","context_length":131072,"created":1758668690,"price_in":0.26,"price_out":2.6,"input_modalities":["text","image"],"output_modalities":["text"],"description":"Qwen3-VL-235B-A22B Thinking is a multimodal model that unifies strong text generation with visual understanding across images and video. The Thinking model is optimized for multimo"},"qwen/qwen3-vl-235b-a22b-instruct":{"id":"qwen/qwen3-vl-235b-a22b-instruct","name":"Qwen: Qwen3 VL 235B A22B Instruct","provider":"qwen","context_length":262144,"created":1758668687,"price_in":0.19999999999999998,"price_out":0.88,"input_modalities":["text","image"],"output_modalities":["text"],"description":"Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets gen"},"qwen/qwen3-max":{"id":"qwen/qwen3-max","name":"Qwen: Qwen3 Max","provider":"qwen","context_length":262144,"created":1758662808,"price_in":0.78,"price_out":3.9,"input_modalities":["text"],"output_modalities":["text"],"description":"Qwen3-Max is an updated release built on the Qwen3 series, offering major improvements in reasoning, instruction following, multilingual support, and long-tail knowledge coverage c"},"qwen/qwen3-coder-plus":{"id":"qwen/qwen3-coder-plus","name":"Qwen: Qwen3 Coder Plus","provider":"qwen","context_length":1000000,"created":1758662707,"price_in":0.65,"price_out":3.25,"input_modalities":["text"],"output_modalities":["text"],"description":"Qwen3 Coder Plus is Alibaba's proprietary version of the Open Source Qwen3 Coder 480B A35B. It is a powerful coding agent model specializing in autonomous programming via tool call"},"openai/gpt-5-codex":{"id":"openai/gpt-5-codex","name":"OpenAI: GPT-5 Codex","provider":"openai","context_length":400000,"created":1758643403,"price_in":1.25,"price_out":10,"input_modalities":["text","image"],"output_modalities":["text"],"description":"GPT-5-Codex is a specialized version of GPT-5 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independen"},"deepseek/deepseek-v3.1-terminus":{"id":"deepseek/deepseek-v3.1-terminus","name":"DeepSeek: DeepSeek V3.1 Terminus","provider":"deepseek","context_length":163840,"created":1758548275,"price_in":0.27,"price_out":0.95,"input_modalities":["text"],"output_modalities":["text"],"description":"DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, inc"},"x-ai/grok-4-fast":{"id":"x-ai/grok-4-fast","name":"xAI: Grok 4 Fast","provider":"x-ai","context_length":2000000,"created":1758240090,"price_in":0.19999999999999998,"price_out":0.5,"input_modalities":["text","image","file"],"output_modalities":["text"],"description":"Grok 4 Fast is xAI's latest multimodal model with SOTA cost-efficiency and a 2M token context window. It comes in two flavors: non-reasoning and reasoning. Read more about the mode"},"alibaba/tongyi-deepresearch-30b-a3b":{"id":"alibaba/tongyi-deepresearch-30b-a3b","name":"Tongyi DeepResearch 30B A3B","provider":"alibaba","context_length":131072,"created":1758210804,"price_in":0.09,"price_out":0.44999999999999996,"input_modalities":["text"],"output_modalities":["text"],"description":"Tongyi DeepResearch is an agentic large language model developed by Tongyi Lab, with 30 billion total parameters activating only 3 billion per token. It's optimized for long-horizo"},"qwen/qwen3-coder-flash":{"id":"qwen/qwen3-coder-flash","name":"Qwen: Qwen3 Coder Flash","provider":"qwen","context_length":1000000,"created":1758115536,"price_in":0.195,"price_out":0.975,"input_modalities":["text"],"output_modalities":["text"],"description":"Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus. It is a powerful coding agent model specializing in autonomous programming via"},"qwen/qwen3-next-80b-a3b-thinking":{"id":"qwen/qwen3-next-80b-a3b-thinking","name":"Qwen: Qwen3 Next 80B A3B Thinking","provider":"qwen","context_length":131072,"created":1757612284,"price_in":0.0975,"price_out":0.78,"input_modalities":["text"],"output_modalities":["text"],"description":"Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems;"},"qwen/qwen3-next-80b-a3b-instruct":{"id":"qwen/qwen3-next-80b-a3b-instruct","name":"Qwen: Qwen3 Next 80B A3B Instruct","provider":"qwen","context_length":262144,"created":1757612213,"price_in":0.09,"price_out":1.1,"input_modalities":["text"],"output_modalities":["text"],"description":"Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks acr"},"qwen/qwen-plus-2025-07-28:thinking":{"id":"qwen/qwen-plus-2025-07-28:thinking","name":"Qwen: Qwen Plus 0728 (thinking)","provider":"qwen","context_length":1000000,"created":1757347599,"price_in":0.26,"price_out":0.78,"input_modalities":["text"],"output_modalities":["text"],"description":"Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination."},"qwen/qwen-plus-2025-07-28":{"id":"qwen/qwen-plus-2025-07-28","name":"Qwen: Qwen Plus 0728","provider":"qwen","context_length":1000000,"created":1757347599,"price_in":0.26,"price_out":0.78,"input_modalities":["text"],"output_modalities":["text"],"description":"Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination."},"nvidia/nemotron-nano-9b-v2":{"id":"nvidia/nemotron-nano-9b-v2","name":"NVIDIA: Nemotron Nano 9B V2","provider":"nvidia","context_length":131072,"created":1757106807,"price_in":0.04,"price_out":0.16,"input_modalities":["text"],"output_modalities":["text"],"description":"NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds t"},"moonshotai/kimi-k2-0905":{"id":"moonshotai/kimi-k2-0905","name":"MoonshotAI: Kimi K2 0905","provider":"moonshotai","context_length":262144,"created":1757021147,"price_in":0.39999999999999997,"price_out":2,"input_modalities":["text"],"output_modalities":["text"],"description":"Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trilli"},"qwen/qwen3-30b-a3b-thinking-2507":{"id":"qwen/qwen3-30b-a3b-thinking-2507","name":"Qwen: Qwen3 30B A3B Thinking 2507","provider":"qwen","context_length":131072,"created":1756399192,"price_in":0.08,"price_out":0.39999999999999997,"input_modalities":["text"],"output_modalities":["text"],"description":"Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specific"},"x-ai/grok-code-fast-1":{"id":"x-ai/grok-code-fast-1","name":"xAI: Grok Code Fast 1","provider":"x-ai","context_length":256000,"created":1756238927,"price_in":0.19999999999999998,"price_out":1.5,"input_modalities":["text"],"output_modalities":["text"],"description":"Grok Code Fast 1 is a speedy and economical reasoning model that excels at agentic coding. With reasoning traces visible in the response, developers can steer Grok Code for high-qu"},"nousresearch/hermes-4-70b":{"id":"nousresearch/hermes-4-70b","name":"Nous: Hermes 4 70B","provider":"nousresearch","context_length":131072,"created":1756236182,"price_in":0.13,"price_out":0.39999999999999997,"input_modalities":["text"],"output_modalities":["text"],"description":"Hermes 4 70B is a hybrid reasoning model from Nous Research, built on Meta-Llama-3.1-70B. It introduces the same hybrid mode as the larger 405B release, allowing the model to eithe"},"nousresearch/hermes-4-405b":{"id":"nousresearch/hermes-4-405b","name":"Nous: Hermes 4 405B","provider":"nousresearch","context_length":131072,"created":1756235463,"price_in":1,"price_out":3,"input_modalities":["text"],"output_modalities":["text"],"description":"Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberat"},"deepseek/deepseek-chat-v3.1":{"id":"deepseek/deepseek-chat-v3.1","name":"DeepSeek: DeepSeek V3.1","provider":"deepseek","context_length":32768,"created":1755779628,"price_in":0.15,"price_out":0.75,"input_modalities":["text"],"output_modalities":["text"],"description":"DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 ba"},"openai/gpt-4o-audio-preview":{"id":"openai/gpt-4o-audio-preview","name":"OpenAI: GPT-4o Audio","provider":"openai","context_length":128000,"created":1755233061,"price_in":2.5,"price_out":10,"input_modalities":["audio","text"],"output_modalities":["text","audio"],"description":"The gpt-4o-audio-preview model adds support for audio inputs as prompts. This enhancement allows the model to detect nuances within audio recordings and add depth to generated user"},"mistralai/mistral-medium-3.1":{"id":"mistralai/mistral-medium-3.1","name":"Mistral: Mistral Medium 3.1","provider":"mistralai","context_length":131072,"created":1755095639,"price_in":0.39999999999999997,"price_out":2,"input_modalities":["text","image"],"output_modalities":["text"],"description":"Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at signifi"},"baidu/ernie-4.5-21b-a3b":{"id":"baidu/ernie-4.5-21b-a3b","name":"Baidu: ERNIE 4.5 21B A3B","provider":"baidu","context_length":120000,"created":1755034167,"price_in":0.07,"price_out":0.28,"input_modalities":["text"],"output_modalities":["text"],"description":"A sophisticated text-based Mixture-of-Experts (MoE) model featuring 21B total parameters with 3B activated per token, delivering exceptional multimodal understanding and generation"},"baidu/ernie-4.5-vl-28b-a3b":{"id":"baidu/ernie-4.5-vl-28b-a3b","name":"Baidu: ERNIE 4.5 VL 28B A3B","provider":"baidu","context_length":30000,"created":1755032836,"price_in":0.14,"price_out":0.56,"input_modalities":["text","image"],"output_modalities":["text"],"description":"A powerful multimodal Mixture-of-Experts chat model featuring 28B total parameters with 3B activated per token, delivering exceptional text and vision understanding through its inn"},"z-ai/glm-4.5v":{"id":"z-ai/glm-4.5v","name":"Z.ai: GLM 4.5V","provider":"z-ai","context_length":65536,"created":1754922288,"price_in":0.6,"price_out":1.7999999999999998,"input_modalities":["text","image"],"output_modalities":["text"],"description":"GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters"},"ai21/jamba-large-1.7":{"id":"ai21/jamba-large-1.7","name":"AI21: Jamba Large 1.7","provider":"ai21","context_length":256000,"created":1754669020,"price_in":2,"price_out":8,"input_modalities":["text"],"output_modalities":["text"],"description":"Jamba Large 1.7 is the latest model in the Jamba open family, offering improvements in grounding, instruction-following, and overall efficiency. Built on a hybrid SSM-Transformer a"},"openai/gpt-5-chat":{"id":"openai/gpt-5-chat","name":"OpenAI: GPT-5 Chat","provider":"openai","context_length":128000,"created":1754587837,"price_in":1.25,"price_out":10,"input_modalities":["file","image","text"],"output_modalities":["text"],"description":"GPT-5 Chat is designed for advanced, natural, multimodal, and context-aware conversations for enterprise applications."},"openai/gpt-5":{"id":"openai/gpt-5","name":"OpenAI: GPT-5","provider":"openai","context_length":400000,"created":1754587413,"price_in":1.25,"price_out":10,"input_modalities":["text","image","file"],"output_modalities":["text"],"description":"GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reas"},"openai/gpt-5-mini":{"id":"openai/gpt-5-mini","name":"OpenAI: GPT-5 Mini","provider":"openai","context_length":400000,"created":1754587407,"price_in":0.25,"price_out":2,"input_modalities":["text","image","file"],"output_modalities":["text"],"description":"GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but wit"},"openai/gpt-5-nano":{"id":"openai/gpt-5-nano","name":"OpenAI: GPT-5 Nano","provider":"openai","context_length":400000,"created":1754587402,"price_in":0.049999999999999996,"price_out":0.39999999999999997,"input_modalities":["text","image","file"],"output_modalities":["text"],"description":"GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasonin"},"openai/gpt-oss-120b":{"id":"openai/gpt-oss-120b","name":"OpenAI: gpt-oss-120b","provider":"openai","context_length":131072,"created":1754414231,"price_in":0.039,"price_out":0.18,"input_modalities":["text"],"output_modalities":["text"],"description":"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. I"},"openai/gpt-oss-20b":{"id":"openai/gpt-oss-20b","name":"OpenAI: gpt-oss-20b","provider":"openai","context_length":131072,"created":1754414229,"price_in":0.03,"price_out":0.14,"input_modalities":["text"],"output_modalities":["text"],"description":"gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per f"},"anthropic/claude-opus-4.1":{"id":"anthropic/claude-opus-4.1","name":"Anthropic: Claude Opus 4.1","provider":"anthropic","context_length":200000,"created":1754411591,"price_in":15,"price_out":75,"input_modalities":["image","text","file"],"output_modalities":["text"],"description":"Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified "},"mistralai/codestral-2508":{"id":"mistralai/codestral-2508","name":"Mistral: Codestral 2508","provider":"mistralai","context_length":256000,"created":1754079630,"price_in":0.3,"price_out":0.8999999999999999,"input_modalities":["text"],"output_modalities":["text"],"description":"Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correc"},"qwen/qwen3-coder-30b-a3b-instruct":{"id":"qwen/qwen3-coder-30b-a3b-instruct","name":"Qwen: Qwen3 Coder 30B A3B Instruct","provider":"qwen","context_length":160000,"created":1753972379,"price_in":0.07,"price_out":0.27,"input_modalities":["text"],"output_modalities":["text"],"description":"Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-sca"},"qwen/qwen3-30b-a3b-instruct-2507":{"id":"qwen/qwen3-30b-a3b-instruct-2507","name":"Qwen: Qwen3 30B A3B Instruct 2507","provider":"qwen","context_length":262144,"created":1753806965,"price_in":0.09,"price_out":0.3,"input_modalities":["text"],"output_modalities":["text"],"description":"Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is des"},"z-ai/glm-4.5":{"id":"z-ai/glm-4.5","name":"Z.ai: GLM 4.5","provider":"z-ai","context_length":131072,"created":1753471347,"price_in":0.6,"price_out":2.2,"input_modalities":["text"],"output_modalities":["text"],"description":"GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of u"},"z-ai/glm-4.5-air":{"id":"z-ai/glm-4.5-air","name":"Z.ai: GLM 4.5 Air","provider":"z-ai","context_length":131072,"created":1753471258,"price_in":0.13,"price_out":0.85,"input_modalities":["text"],"output_modalities":["text"],"description":"GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) "},"qwen/qwen3-235b-a22b-thinking-2507":{"id":"qwen/qwen3-235b-a22b-thinking-2507","name":"Qwen: Qwen3 235B A22B Thinking 2507","provider":"qwen","context_length":131072,"created":1753449557,"price_in":0.14950000000000002,"price_out":1.495,"input_modalities":["text"],"output_modalities":["text"],"description":"Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B paramet"},"z-ai/glm-4-32b":{"id":"z-ai/glm-4-32b","name":"Z.ai: GLM 4 32B ","provider":"z-ai","context_length":128000,"created":1753376617,"price_in":0.09999999999999999,"price_out":0.09999999999999999,"input_modalities":["text"],"output_modalities":["text"],"description":"GLM 4 32B is a cost-effective foundation language model. It can efficiently perform complex tasks and has significantly enhanced capabilities in tool use, online search, and code-r"},"qwen/qwen3-coder":{"id":"qwen/qwen3-coder","name":"Qwen: Qwen3 Coder 480B A35B","provider":"qwen","context_length":262144,"created":1753230546,"price_in":0.22,"price_out":1.7999999999999998,"input_modalities":["text"],"output_modalities":["text"],"description":"Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, to"},"bytedance/ui-tars-1.5-7b":{"id":"bytedance/ui-tars-1.5-7b","name":"ByteDance: UI-TARS 7B ","provider":"bytedance","context_length":128000,"created":1753205056,"price_in":0.09999999999999999,"price_out":0.19999999999999998,"input_modalities":["image","text"],"output_modalities":["text"],"description":"UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems, and games. Built by ByteDance, i"},"google/gemini-2.5-flash-lite":{"id":"google/gemini-2.5-flash-lite","name":"Google: Gemini 2.5 Flash Lite","provider":"google","context_length":1048576,"created":1753200276,"price_in":0.09999999999999999,"price_out":0.39999999999999997,"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"description":"Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token ge"},"qwen/qwen3-235b-a22b-2507":{"id":"qwen/qwen3-235b-a22b-2507","name":"Qwen: Qwen3 235B A22B Instruct 2507","provider":"qwen","context_length":262144,"created":1753119555,"price_in":0.071,"price_out":0.09999999999999999,"input_modalities":["text"],"output_modalities":["text"],"description":"Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pa"},"switchpoint/router":{"id":"switchpoint/router","name":"Switchpoint Router","provider":"switchpoint","context_length":131072,"created":1752272899,"price_in":0.85,"price_out":3.4,"input_modalities":["text"],"output_modalities":["text"],"description":"Switchpoint AI's router instantly analyzes your request and directs it to the optimal AI from an ever-evolving library. As the world of LLMs advances, our router gets smarter, ensu"},"moonshotai/kimi-k2":{"id":"moonshotai/kimi-k2","name":"MoonshotAI: Kimi K2 0711","provider":"moonshotai","context_length":131072,"created":1752263252,"price_in":0.5700000000000001,"price_out":2.3,"input_modalities":["text"],"output_modalities":["text"],"description":"Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. I"},"mistralai/devstral-medium":{"id":"mistralai/devstral-medium","name":"Mistral: Devstral Medium","provider":"mistralai","context_length":131072,"created":1752161321,"price_in":0.39999999999999997,"price_out":2,"input_modalities":["text"],"output_modalities":["text"],"description":"Devstral Medium is a high-performance code generation and agentic reasoning model developed jointly by Mistral AI and All Hands AI. Positioned as a step up from Devstral Small, it "},"mistralai/devstral-small":{"id":"mistralai/devstral-small","name":"Mistral: Devstral Small 1.1","provider":"mistralai","context_length":131072,"created":1752160751,"price_in":0.09999999999999999,"price_out":0.3,"input_modalities":["text"],"output_modalities":["text"],"description":"Devstral Small 1.1 is a 24B parameter open-weight language model for software engineering agents, developed by Mistral AI in collaboration with All Hands AI. Finetuned from Mistral"},"x-ai/grok-4":{"id":"x-ai/grok-4","name":"xAI: Grok 4","provider":"x-ai","context_length":256000,"created":1752087689,"price_in":3,"price_out":15,"input_modalities":["image","text","file"],"output_modalities":["text"],"description":"Grok 4 is xAI's latest reasoning model with a 256k context window. It supports parallel tool calling, structured outputs, and both image and text inputs. Note that reasoning is not"},"tencent/hunyuan-a13b-instruct":{"id":"tencent/hunyuan-a13b-instruct","name":"Tencent: Hunyuan A13B Instruct","provider":"tencent","context_length":131072,"created":1751987664,"price_in":0.14,"price_out":0.5700000000000001,"input_modalities":["text"],"output_modalities":["text"],"description":"Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thou"},"morph/morph-v3-large":{"id":"morph/morph-v3-large","name":"Morph: Morph V3 Large","provider":"morph","context_length":262144,"created":1751910858,"price_in":0.8999999999999999,"price_out":1.9,"input_modalities":["text"],"output_modalities":["text"],"description":"Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for precise code transformations. The model requires the prompt to be in the following"},"morph/morph-v3-fast":{"id":"morph/morph-v3-fast","name":"Morph: Morph V3 Fast","provider":"morph","context_length":81920,"created":1751910002,"price_in":0.7999999999999999,"price_out":1.2,"input_modalities":["text"],"output_modalities":["text"],"description":"Morph's fastest apply model for code edits. ~10,500 tokens/sec with 96% accuracy for rapid code transformations. The model requires the prompt to be in the following format: <instr"},"baidu/ernie-4.5-vl-424b-a47b":{"id":"baidu/ernie-4.5-vl-424b-a47b","name":"Baidu: ERNIE 4.5 VL 424B A47B ","provider":"baidu","context_length":123000,"created":1751300903,"price_in":0.42,"price_out":1.25,"input_modalities":["image","text"],"output_modalities":["text"],"description":"ERNIE-4.5-VL-424B-A47B is a multimodal Mixture-of-Experts (MoE) model from Baidu’s ERNIE 4.5 series, featuring 424B total parameters with 47B active per token. It is trained jointl"},"baidu/ernie-4.5-300b-a47b":{"id":"baidu/ernie-4.5-300b-a47b","name":"Baidu: ERNIE 4.5 300B A47B ","provider":"baidu","context_length":123000,"created":1751300139,"price_in":0.28,"price_out":1.1,"input_modalities":["text"],"output_modalities":["text"],"description":"ERNIE-4.5-300B-A47B is a 300B parameter Mixture-of-Experts (MoE) language model developed by Baidu as part of the ERNIE 4.5 series. It activates 47B parameters per token and suppor"},"mistralai/mistral-small-3.2-24b-instruct":{"id":"mistralai/mistral-small-3.2-24b-instruct","name":"Mistral: Mistral Small 3.2 24B","provider":"mistralai","context_length":128000,"created":1750443016,"price_in":0.075,"price_out":0.19999999999999998,"input_modalities":["image","text"],"output_modalities":["text"],"description":"Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compare"},"minimax/minimax-m1":{"id":"minimax/minimax-m1","name":"MiniMax: MiniMax M1","provider":"minimax","context_length":1000000,"created":1750200414,"price_in":0.39999999999999997,"price_out":2.2,"input_modalities":["text"],"output_modalities":["text"],"description":"MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture pa"},"google/gemini-2.5-flash":{"id":"google/gemini-2.5-flash","name":"Google: Gemini 2.5 Flash","provider":"google","context_length":1048576,"created":1750172488,"price_in":0.3,"price_out":2.5,"input_modalities":["file","image","text","audio","video"],"output_modalities":["text"],"description":"Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in \"thinki"},"google/gemini-2.5-pro":{"id":"google/gemini-2.5-pro","name":"Google: Gemini 2.5 Pro","provider":"google","context_length":1048576,"created":1750169544,"price_in":1.25,"price_out":10,"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to "},"openai/o3-pro":{"id":"openai/o3-pro","name":"OpenAI: o3 Pro","provider":"openai","context_length":200000,"created":1749598352,"price_in":20,"price_out":80,"input_modalities":["text","file","image"],"output_modalities":["text"],"description":"The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and pro"},"x-ai/grok-3-mini":{"id":"x-ai/grok-3-mini","name":"xAI: Grok 3 Mini","provider":"x-ai","context_length":131072,"created":1749583245,"price_in":0.3,"price_out":0.5,"input_modalities":["text"],"output_modalities":["text"],"description":"A lightweight model that thinks before responding. Fast, smart, and great for logic-based tasks that do not require deep domain knowledge. The raw thinking traces are accessible."},"x-ai/grok-3":{"id":"x-ai/grok-3","name":"xAI: Grok 3","provider":"x-ai","context_length":131072,"created":1749582908,"price_in":3,"price_out":15,"input_modalities":["text"],"output_modalities":["text"],"description":"Grok 3 is the latest model from xAI. It's their flagship model that excels at enterprise use cases like data extraction, coding, and text summarization. Possesses deep domain knowl"},"google/gemini-2.5-pro-preview":{"id":"google/gemini-2.5-pro-preview","name":"Google: Gemini 2.5 Pro Preview 06-05","provider":"google","context_length":1048576,"created":1749137257,"price_in":1.25,"price_out":10,"input_modalities":["file","image","text","audio"],"output_modalities":["text"],"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to "},"deepseek/deepseek-r1-0528":{"id":"deepseek/deepseek-r1-0528","name":"DeepSeek: R1 0528","provider":"deepseek","context_length":163840,"created":1748455170,"price_in":0.5,"price_out":2.1500000000000004,"input_modalities":["text"],"output_modalities":["text"],"description":"May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 67"},"anthropic/claude-opus-4":{"id":"anthropic/claude-opus-4","name":"Anthropic: Claude Opus 4","provider":"anthropic","context_length":200000,"created":1747931245,"price_in":15,"price_out":75,"input_modalities":["image","text","file"],"output_modalities":["text"],"description":"Claude Opus 4 is benchmarked as the world’s best coding model, at time of release, bringing sustained performance on complex, long-running tasks and agent workflows. It sets new be"},"anthropic/claude-sonnet-4":{"id":"anthropic/claude-sonnet-4","name":"Anthropic: Claude Sonnet 4","provider":"anthropic","context_length":1000000,"created":1747930371,"price_in":3,"price_out":15,"input_modalities":["image","text","file"],"output_modalities":["text"],"description":"Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Ac"},"google/gemma-3n-e4b-it":{"id":"google/gemma-3n-e4b-it","name":"Google: Gemma 3n 4B","provider":"google","context_length":32768,"created":1747776824,"price_in":0.06,"price_out":0.12,"input_modalities":["text"],"output_modalities":["text"],"description":"Gemma 3n E4B-it is optimized for efficient execution on mobile and low-resource devices, such as phones, laptops, and tablets. It supports multimodal inputs—including text, visual "},"mistralai/mistral-medium-3":{"id":"mistralai/mistral-medium-3","name":"Mistral: Mistral Medium 3","provider":"mistralai","context_length":131072,"created":1746627341,"price_in":0.39999999999999997,"price_out":2,"input_modalities":["text","image"],"output_modalities":["text"],"description":"Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-"},"google/gemini-2.5-pro-preview-05-06":{"id":"google/gemini-2.5-pro-preview-05-06","name":"Google: Gemini 2.5 Pro Preview 05-06","provider":"google","context_length":1048576,"created":1746578513,"price_in":1.25,"price_out":10,"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to "},"arcee-ai/spotlight":{"id":"arcee-ai/spotlight","name":"Arcee AI: Spotlight","provider":"arcee-ai","context_length":131072,"created":1746481552,"price_in":0.18,"price_out":0.18,"input_modalities":["image","text"],"output_modalities":["text"],"description":"Spotlight is a 7‑billion‑parameter vision‑language model derived from Qwen 2.5‑VL and fine‑tuned by Arcee AI for tight image‑text grounding tasks. It offers a 32 k‑token context wi"},"arcee-ai/maestro-reasoning":{"id":"arcee-ai/maestro-reasoning","name":"Arcee AI: Maestro Reasoning","provider":"arcee-ai","context_length":131072,"created":1746481269,"price_in":0.8999999999999999,"price_out":3.3000000000000003,"input_modalities":["text"],"output_modalities":["text"],"description":"Maestro Reasoning is Arcee's flagship analysis model: a 32 B‑parameter derivative of Qwen 2.5‑32 B tuned with DPO and chain‑of‑thought RL for step‑by‑step logic. Compared to the ea"},"arcee-ai/virtuoso-large":{"id":"arcee-ai/virtuoso-large","name":"Arcee AI: Virtuoso Large","provider":"arcee-ai","context_length":131072,"created":1746478885,"price_in":0.75,"price_out":1.2,"input_modalities":["text"],"output_modalities":["text"],"description":"Virtuoso‑Large is Arcee's top‑tier general‑purpose LLM at 72 B parameters, tuned to tackle cross‑domain reasoning, creative writing and enterprise QA. Unlike many 70 B peers, it re"},"arcee-ai/coder-large":{"id":"arcee-ai/coder-large","name":"Arcee AI: Coder Large","provider":"arcee-ai","context_length":32768,"created":1746478663,"price_in":0.5,"price_out":0.7999999999999999,"input_modalities":["text"],"output_modalities":["text"],"description":"Coder‑Large is a 32 B‑parameter offspring of Qwen 2.5‑Instruct that has been further trained on permissively‑licensed GitHub, CodeSearchNet and synthetic bug‑fix corpora. It suppor"},"meta-llama/llama-guard-4-12b":{"id":"meta-llama/llama-guard-4-12b","name":"Meta: Llama Guard 4 12B","provider":"meta-llama","context_length":163840,"created":1745975193,"price_in":0.18,"price_out":0.18,"input_modalities":["image","text"],"output_modalities":["text"],"description":"Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content"},"qwen/qwen3-30b-a3b":{"id":"qwen/qwen3-30b-a3b","name":"Qwen: Qwen3 30B A3B","provider":"qwen","context_length":40960,"created":1745878604,"price_in":0.09,"price_out":0.44999999999999996,"input_modalities":["text"],"output_modalities":["text"],"description":"Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, an"},"qwen/qwen3-8b":{"id":"qwen/qwen3-8b","name":"Qwen: Qwen3 8B","provider":"qwen","context_length":40960,"created":1745876632,"price_in":0.049999999999999996,"price_out":0.39999999999999997,"input_modalities":["text"],"output_modalities":["text"],"description":"Qwen3-8B is a dense 8.2B parameter causal language model from the Qwen3 series, designed for both reasoning-heavy tasks and efficient dialogue. It supports seamless switching betwe"},"qwen/qwen3-14b":{"id":"qwen/qwen3-14b","name":"Qwen: Qwen3 14B","provider":"qwen","context_length":40960,"created":1745876478,"price_in":0.06,"price_out":0.24,"input_modalities":["text"],"output_modalities":["text"],"description":"Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between"},"qwen/qwen3-32b":{"id":"qwen/qwen3-32b","name":"Qwen: Qwen3 32B","provider":"qwen","context_length":40960,"created":1745875945,"price_in":0.08,"price_out":0.28,"input_modalities":["text"],"output_modalities":["text"],"description":"Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching betwee"},"qwen/qwen3-235b-a22b":{"id":"qwen/qwen3-235b-a22b","name":"Qwen: Qwen3 235B A22B","provider":"qwen","context_length":131072,"created":1745875757,"price_in":0.45499999999999996,"price_out":1.8199999999999998,"input_modalities":["text"],"output_modalities":["text"],"description":"Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a \"thinking"},"openai/o4-mini-high":{"id":"openai/o4-mini-high","name":"OpenAI: o4 Mini High","provider":"openai","context_length":200000,"created":1744824212,"price_in":1.1,"price_out":4.4,"input_modalities":["image","text","file"],"output_modalities":["text"],"description":"OpenAI o4-mini-high is the same model as [o4-mini](/openai/o4-mini) with reasoning_effort set to high. OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fa"},"openai/o3":{"id":"openai/o3","name":"OpenAI: o3","provider":"openai","context_length":200000,"created":1744823457,"price_in":2,"price_out":8,"input_modalities":["image","text","file"],"output_modalities":["text"],"description":"o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instru"},"openai/o4-mini":{"id":"openai/o4-mini","name":"OpenAI: o4 Mini","provider":"openai","context_length":200000,"created":1744820942,"price_in":1.1,"price_out":4.4,"input_modalities":["image","text","file"],"output_modalities":["text"],"description":"OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports "},"openai/gpt-4.1":{"id":"openai/gpt-4.1","name":"OpenAI: GPT-4.1","provider":"openai","context_length":1047576,"created":1744651385,"price_in":2,"price_out":8,"input_modalities":["image","text","file"],"output_modalities":["text"],"description":"GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token "},"openai/gpt-4.1-mini":{"id":"openai/gpt-4.1-mini","name":"OpenAI: GPT-4.1 Mini","provider":"openai","context_length":1047576,"created":1744651381,"price_in":0.39999999999999997,"price_out":1.5999999999999999,"input_modalities":["image","text","file"],"output_modalities":["text"],"description":"GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45."},"openai/gpt-4.1-nano":{"id":"openai/gpt-4.1-nano","name":"OpenAI: GPT-4.1 Nano","provider":"openai","context_length":1047576,"created":1744651369,"price_in":0.09999999999999999,"price_out":0.39999999999999997,"input_modalities":["image","text","file"],"output_modalities":["text"],"description":"For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million..."},"alfredpros/codellama-7b-instruct-solidity":{"id":"alfredpros/codellama-7b-instruct-solidity","name":"AlfredPros: CodeLLaMa 7B Instruct Solidity","provider":"alfredpros","context_length":4096,"created":1744641874,"price_in":0.7999999999999999,"price_out":1.2,"input_modalities":["text"],"output_modalities":["text"],"description":"A finetuned 7 billion parameters Code LLaMA - Instruct model to generate Solidity smart contract using 4-bit QLoRA finetuning provided by PEFT library."},"x-ai/grok-3-mini-beta":{"id":"x-ai/grok-3-mini-beta","name":"xAI: Grok 3 Mini Beta","provider":"x-ai","context_length":131072,"created":1744240195,"price_in":0.3,"price_out":0.5,"input_modalities":["text"],"output_modalities":["text"],"description":"Grok 3 Mini is a lightweight, smaller thinking model. Unlike traditional models that generate answers immediately, Grok 3 Mini thinks before responding. It’s ideal for reasoning-he"},"x-ai/grok-3-beta":{"id":"x-ai/grok-3-beta","name":"xAI: Grok 3 Beta","provider":"x-ai","context_length":131072,"created":1744240068,"price_in":3,"price_out":15,"input_modalities":["text"],"output_modalities":["text"],"description":"Grok 3 is the latest model from xAI. It's their flagship model that excels at enterprise use cases like data extraction, coding, and text summarization. Possesses deep domain knowl"},"meta-llama/llama-4-maverick":{"id":"meta-llama/llama-4-maverick","name":"Meta: Llama 4 Maverick","provider":"meta-llama","context_length":1048576,"created":1743881822,"price_in":0.15,"price_out":0.6,"input_modalities":["text","image"],"output_modalities":["text"],"description":"Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active"},"meta-llama/llama-4-scout":{"id":"meta-llama/llama-4-scout","name":"Meta: Llama 4 Scout","provider":"meta-llama","context_length":327680,"created":1743881519,"price_in":0.08,"price_out":0.3,"input_modalities":["text","image"],"output_modalities":["text"],"description":"Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimo"},"deepseek/deepseek-chat-v3-0324":{"id":"deepseek/deepseek-chat-v3-0324","name":"DeepSeek: DeepSeek V3 0324","provider":"deepseek","context_length":163840,"created":1742824755,"price_in":0.19999999999999998,"price_out":0.77,"input_modalities":["text"],"output_modalities":["text"],"description":"DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/d"},"openai/o1-pro":{"id":"openai/o1-pro","name":"OpenAI: o1-pro","provider":"openai","context_length":200000,"created":1742423211,"price_in":150,"price_out":600,"input_modalities":["text","image","file"],"output_modalities":["text"],"description":"The o1 series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o1-pro model uses more compute to think harder and pr"},"mistralai/mistral-small-3.1-24b-instruct":{"id":"mistralai/mistral-small-3.1-24b-instruct","name":"Mistral: Mistral Small 3.1 24B","provider":"mistralai","context_length":128000,"created":1742238937,"price_in":0.35,"price_out":0.56,"input_modalities":["text","image"],"output_modalities":["text"],"description":"Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art"},"google/gemma-3-4b-it":{"id":"google/gemma-3-4b-it","name":"Google: Gemma 3 4B","provider":"google","context_length":131072,"created":1741905510,"price_in":0.04,"price_out":0.08,"input_modalities":["text","image"],"output_modalities":["text"],"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improv"},"google/gemma-3-12b-it":{"id":"google/gemma-3-12b-it","name":"Google: Gemma 3 12B","provider":"google","context_length":131072,"created":1741902625,"price_in":0.04,"price_out":0.13,"input_modalities":["text","image"],"output_modalities":["text"],"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improv"},"cohere/command-a":{"id":"cohere/command-a","name":"Cohere: Command A","provider":"cohere","context_length":256000,"created":1741894342,"price_in":2.5,"price_out":10,"input_modalities":["text"],"output_modalities":["text"],"description":"Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to"},"openai/gpt-4o-mini-search-preview":{"id":"openai/gpt-4o-mini-search-preview","name":"OpenAI: GPT-4o-mini Search Preview","provider":"openai","context_length":128000,"created":1741818122,"price_in":0.15,"price_out":0.6,"input_modalities":["text"],"output_modalities":["text"],"description":"GPT-4o mini Search Preview is a specialized model for web search in Chat Completions. It is trained to understand and execute web search queries."},"openai/gpt-4o-search-preview":{"id":"openai/gpt-4o-search-preview","name":"OpenAI: GPT-4o Search Preview","provider":"openai","context_length":128000,"created":1741817949,"price_in":2.5,"price_out":10,"input_modalities":["text"],"output_modalities":["text"],"description":"GPT-4o Search Previewis a specialized model for web search in Chat Completions. It is trained to understand and execute web search queries."},"rekaai/reka-flash-3":{"id":"rekaai/reka-flash-3","name":"Reka Flash 3","provider":"rekaai","context_length":65536,"created":1741812813,"price_in":0.09999999999999999,"price_out":0.19999999999999998,"input_modalities":["text"],"output_modalities":["text"],"description":"Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka. It excels at general chat, coding tasks, instruction-follow"},"google/gemma-3-27b-it":{"id":"google/gemma-3-27b-it","name":"Google: Gemma 3 27B","provider":"google","context_length":131072,"created":1741756359,"price_in":0.08,"price_out":0.16,"input_modalities":["text","image"],"output_modalities":["text"],"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improv"},"thedrummer/skyfall-36b-v2":{"id":"thedrummer/skyfall-36b-v2","name":"TheDrummer: Skyfall 36B V2","provider":"thedrummer","context_length":32768,"created":1741636566,"price_in":0.55,"price_out":0.7999999999999999,"input_modalities":["text"],"output_modalities":["text"],"description":"Skyfall 36B v2 is an enhanced iteration of Mistral Small 2501, specifically fine-tuned for improved creativity, nuanced writing, role-playing, and coherent storytelling."},"perplexity/sonar-reasoning-pro":{"id":"perplexity/sonar-reasoning-pro","name":"Perplexity: Sonar Reasoning Pro","provider":"perplexity","context_length":128000,"created":1741313308,"price_in":2,"price_out":8,"input_modalities":["text","image"],"output_modalities":["text"],"description":"Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sona"},"perplexity/sonar-pro":{"id":"perplexity/sonar-pro","name":"Perplexity: Sonar Pro","provider":"perplexity","context_length":200000,"created":1741312423,"price_in":3,"price_out":15,"input_modalities":["text","image"],"output_modalities":["text"],"description":"Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sona"},"perplexity/sonar-deep-research":{"id":"perplexity/sonar-deep-research","name":"Perplexity: Sonar Deep Research","provider":"perplexity","context_length":128000,"created":1741311246,"price_in":2,"price_out":8,"input_modalities":["text"],"output_modalities":["text"],"description":"Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates so"},"google/gemini-2.0-flash-lite-001":{"id":"google/gemini-2.0-flash-lite-001","name":"Google: Gemini 2.0 Flash Lite","provider":"google","context_length":1048576,"created":1740506212,"price_in":0.075,"price_out":0.3,"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"description":"Gemini 2.0 Flash Lite offers a significantly faster time to first token (TTFT) compared to [Gemini Flash 1.5](/google/gemini-flash-1.5), while maintaining quality on par with large"},"anthropic/claude-3.7-sonnet":{"id":"anthropic/claude-3.7-sonnet","name":"Anthropic: Claude 3.7 Sonnet","provider":"anthropic","context_length":200000,"created":1740422110,"price_in":3,"price_out":15,"input_modalities":["text","image","file"],"output_modalities":["text"],"description":"Claude 3.7 Sonnet is an advanced large language model with improved reasoning, coding, and problem-solving capabilities. It introduces a hybrid reasoning approach, allowing users t"},"anthropic/claude-3.7-sonnet:thinking":{"id":"anthropic/claude-3.7-sonnet:thinking","name":"Anthropic: Claude 3.7 Sonnet (thinking)","provider":"anthropic","context_length":200000,"created":1740422110,"price_in":3,"price_out":15,"input_modalities":["text","image","file"],"output_modalities":["text"],"description":"Claude 3.7 Sonnet is an advanced large language model with improved reasoning, coding, and problem-solving capabilities. It introduces a hybrid reasoning approach, allowing users t"},"mistralai/mistral-saba":{"id":"mistralai/mistral-saba","name":"Mistral: Saba","provider":"mistralai","context_length":32768,"created":1739803239,"price_in":0.19999999999999998,"price_out":0.6,"input_modalities":["text"],"output_modalities":["text"],"description":"Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining e"},"meta-llama/llama-guard-3-8b":{"id":"meta-llama/llama-guard-3-8b","name":"Llama Guard 3 8B","provider":"meta-llama","context_length":131072,"created":1739401318,"price_in":0.48,"price_out":0.03,"input_modalities":["text"],"output_modalities":["text"],"description":"Llama Guard 3 is a Llama-3.1-8B pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM inputs "},"openai/o3-mini-high":{"id":"openai/o3-mini-high","name":"OpenAI: o3 Mini High","provider":"openai","context_length":200000,"created":1739372611,"price_in":1.1,"price_out":4.4,"input_modalities":["text","file"],"output_modalities":["text"],"description":"OpenAI o3-mini-high is the same model as [o3-mini](/openai/o3-mini) with reasoning_effort set to high. o3-mini is a cost-efficient language model optimized for STEM reasoning tasks"},"google/gemini-2.0-flash-001":{"id":"google/gemini-2.0-flash-001","name":"Google: Gemini 2.0 Flash","provider":"google","context_length":1000000,"created":1738769413,"price_in":0.09999999999999999,"price_out":0.39999999999999997,"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"description":"Gemini Flash 2.0 offers a significantly faster time to first token (TTFT) compared to [Gemini Flash 1.5](/google/gemini-flash-1.5), while maintaining quality on par with larger mod"},"qwen/qwen-vl-plus":{"id":"qwen/qwen-vl-plus","name":"Qwen: Qwen VL Plus","provider":"qwen","context_length":131072,"created":1738731255,"price_in":0.1365,"price_out":0.40950000000000003,"input_modalities":["text","image"],"output_modalities":["text"],"description":"Qwen's Enhanced Large Visual Language Model. Significantly upgraded for detailed recognition capabilities and text recognition abilities, supporting ultra-high pixel resolutions up"},"aion-labs/aion-1.0":{"id":"aion-labs/aion-1.0","name":"AionLabs: Aion-1.0","provider":"aion-labs","context_length":131072,"created":1738697557,"price_in":4,"price_out":8,"input_modalities":["text"],"output_modalities":["text"],"description":"Aion-1.0 is a multi-model system designed for high performance across various tasks, including reasoning and coding. It is built on DeepSeek-R1, augmented with additional models an"},"aion-labs/aion-1.0-mini":{"id":"aion-labs/aion-1.0-mini","name":"AionLabs: Aion-1.0-Mini","provider":"aion-labs","context_length":131072,"created":1738697107,"price_in":0.7,"price_out":1.4,"input_modalities":["text"],"output_modalities":["text"],"description":"Aion-1.0-Mini 32B parameter model is a distilled version of the DeepSeek-R1 model, designed for strong performance in reasoning domains such as mathematics, coding, and logic. It i"},"aion-labs/aion-rp-llama-3.1-8b":{"id":"aion-labs/aion-rp-llama-3.1-8b","name":"AionLabs: Aion-RP 1.0 (8B)","provider":"aion-labs","context_length":32768,"created":1738696718,"price_in":0.7999999999999999,"price_out":1.5999999999999999,"input_modalities":["text"],"output_modalities":["text"],"description":"Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate eac"},"qwen/qwen-vl-max":{"id":"qwen/qwen-vl-max","name":"Qwen: Qwen VL Max","provider":"qwen","context_length":131072,"created":1738434304,"price_in":0.52,"price_out":2.08,"input_modalities":["text","image"],"output_modalities":["text"],"description":"Qwen VL Max is a visual understanding model with 7500 tokens context length. It excels in delivering optimal performance for a broader spectrum of complex tasks.\n"},"qwen/qwen-turbo":{"id":"qwen/qwen-turbo","name":"Qwen: Qwen-Turbo","provider":"qwen","context_length":131072,"created":1738410974,"price_in":0.0325,"price_out":0.13,"input_modalities":["text"],"output_modalities":["text"],"description":"Qwen-Turbo, based on Qwen2.5, is a 1M context model that provides fast speed and low cost, suitable for simple tasks."},"qwen/qwen2.5-vl-72b-instruct":{"id":"qwen/qwen2.5-vl-72b-instruct","name":"Qwen: Qwen2.5 VL 72B Instruct","provider":"qwen","context_length":32000,"created":1738410311,"price_in":0.25,"price_out":0.75,"input_modalities":["text","image"],"output_modalities":["text"],"description":"Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts"},"qwen/qwen-plus":{"id":"qwen/qwen-plus","name":"Qwen: Qwen-Plus","provider":"qwen","context_length":1000000,"created":1738409840,"price_in":0.26,"price_out":0.78,"input_modalities":["text"],"output_modalities":["text"],"description":"Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination."},"qwen/qwen-max":{"id":"qwen/qwen-max","name":"Qwen: Qwen-Max ","provider":"qwen","context_length":32768,"created":1738402289,"price_in":1.04,"price_out":4.16,"input_modalities":["text"],"output_modalities":["text"],"description":"Qwen-Max, based on Qwen2.5, provides the best inference performance among [Qwen models](/qwen), especially for complex multi-step tasks. It's a large-scale MoE model that has been "},"openai/o3-mini":{"id":"openai/o3-mini","name":"OpenAI: o3 Mini","provider":"openai","context_length":200000,"created":1738351721,"price_in":1.1,"price_out":4.4,"input_modalities":["text","file"],"output_modalities":["text"],"description":"OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. This model supports the `reasoning"},"mistralai/mistral-small-24b-instruct-2501":{"id":"mistralai/mistral-small-24b-instruct-2501","name":"Mistral: Mistral Small 3","provider":"mistralai","context_length":32768,"created":1738255409,"price_in":0.049999999999999996,"price_out":0.08,"input_modalities":["text"],"output_modalities":["text"],"description":"Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained "},"deepseek/deepseek-r1-distill-qwen-32b":{"id":"deepseek/deepseek-r1-distill-qwen-32b","name":"DeepSeek: R1 Distill Qwen 32B","provider":"deepseek","context_length":32768,"created":1738194830,"price_in":0.29,"price_out":0.29,"input_modalities":["text"],"output_modalities":["text"],"description":"DeepSeek R1 Distill Qwen 32B is a distilled large language model based on [Qwen 2.5 32B](https://huggingface.co/Qwen/Qwen2.5-32B), using outputs from [DeepSeek R1](/deepseek/deepse"},"perplexity/sonar":{"id":"perplexity/sonar","name":"Perplexity: Sonar","provider":"perplexity","context_length":127072,"created":1738013808,"price_in":1,"price_out":1,"input_modalities":["text","image"],"output_modalities":["text"],"description":"Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightwei"},"deepseek/deepseek-r1-distill-llama-70b":{"id":"deepseek/deepseek-r1-distill-llama-70b","name":"DeepSeek: R1 Distill Llama 70B","provider":"deepseek","context_length":131072,"created":1737663169,"price_in":0.7,"price_out":0.7999999999999999,"input_modalities":["text"],"output_modalities":["text"],"description":"DeepSeek R1 Distill Llama 70B is a distilled large language model based on [Llama-3.3-70B-Instruct](/meta-llama/llama-3.3-70b-instruct), using outputs from [DeepSeek R1](/deepseek/"},"deepseek/deepseek-r1":{"id":"deepseek/deepseek-r1","name":"DeepSeek: R1","provider":"deepseek","context_length":64000,"created":1737381095,"price_in":0.7,"price_out":2.5,"input_modalities":["text"],"output_modalities":["text"],"description":"DeepSeek R1 is here: Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inf"},"minimax/minimax-01":{"id":"minimax/minimax-01","name":"MiniMax: MiniMax-01","provider":"minimax","context_length":1000192,"created":1736915462,"price_in":0.19999999999999998,"price_out":1.1,"input_modalities":["text","image"],"output_modalities":["text"],"description":"MiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding. It has 456 billion parameters, with 45.9 billion parameters activated per in"},"microsoft/phi-4":{"id":"microsoft/phi-4","name":"Microsoft: Phi 4","provider":"microsoft","context_length":16384,"created":1736489872,"price_in":0.065,"price_out":0.14,"input_modalities":["text"],"output_modalities":["text"],"description":"[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses"},"sao10k/l3.1-70b-hanami-x1":{"id":"sao10k/l3.1-70b-hanami-x1","name":"Sao10K: Llama 3.1 70B Hanami x1","provider":"sao10k","context_length":16000,"created":1736302854,"price_in":3,"price_out":3,"input_modalities":["text"],"output_modalities":["text"],"description":"This is [Sao10K](/sao10k)'s experiment over [Euryale v2.2](/sao10k/l3.1-euryale-70b)."},"deepseek/deepseek-chat":{"id":"deepseek/deepseek-chat","name":"DeepSeek: DeepSeek V3","provider":"deepseek","context_length":163840,"created":1735241320,"price_in":0.32,"price_out":0.8899999999999999,"input_modalities":["text"],"output_modalities":["text"],"description":"DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tok"},"sao10k/l3.3-euryale-70b":{"id":"sao10k/l3.3-euryale-70b","name":"Sao10K: Llama 3.3 Euryale 70B","provider":"sao10k","context_length":131072,"created":1734535928,"price_in":0.65,"price_out":0.75,"input_modalities":["text"],"output_modalities":["text"],"description":"Euryale L3.3 70B is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70B v2.2](/models/sao10k/l3-euryale-70b)."},"openai/o1":{"id":"openai/o1","name":"OpenAI: o1","provider":"openai","context_length":200000,"created":1734459999,"price_in":15,"price_out":60,"input_modalities":["text","image","file"],"output_modalities":["text"],"description":"The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trained with large-scale reinforcement learn"},"cohere/command-r7b-12-2024":{"id":"cohere/command-r7b-12-2024","name":"Cohere: Command R7B (12-2024)","provider":"cohere","context_length":128000,"created":1734158152,"price_in":0.0375,"price_out":0.15,"input_modalities":["text"],"output_modalities":["text"],"description":"Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning"},"meta-llama/llama-3.3-70b-instruct":{"id":"meta-llama/llama-3.3-70b-instruct","name":"Meta: Llama 3.3 70B Instruct","provider":"meta-llama","context_length":131072,"created":1733506137,"price_in":0.09999999999999999,"price_out":0.32,"input_modalities":["text"],"output_modalities":["text"],"description":"The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text on"},"amazon/nova-lite-v1":{"id":"amazon/nova-lite-v1","name":"Amazon: Nova Lite 1.0","provider":"amazon","context_length":300000,"created":1733437363,"price_in":0.06,"price_out":0.24,"input_modalities":["text","image"],"output_modalities":["text"],"description":"Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite..."},"amazon/nova-micro-v1":{"id":"amazon/nova-micro-v1","name":"Amazon: Nova Micro 1.0","provider":"amazon","context_length":128000,"created":1733437237,"price_in":0.035,"price_out":0.14,"input_modalities":["text"],"output_modalities":["text"],"description":"Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost. With a context length..."},"amazon/nova-pro-v1":{"id":"amazon/nova-pro-v1","name":"Amazon: Nova Pro 1.0","provider":"amazon","context_length":300000,"created":1733436303,"price_in":0.7999999999999999,"price_out":3.1999999999999997,"input_modalities":["text","image"],"output_modalities":["text"],"description":"Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December..."},"openai/gpt-4o-2024-11-20":{"id":"openai/gpt-4o-2024-11-20","name":"OpenAI: GPT-4o (2024-11-20)","provider":"openai","context_length":128000,"created":1732127594,"price_in":2.5,"price_out":10,"input_modalities":["text","image","file"],"output_modalities":["text"],"description":"The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance & readability. It’s also better"},"mistralai/mistral-large-2411":{"id":"mistralai/mistral-large-2411","name":"Mistral Large 2411","provider":"mistralai","context_length":131072,"created":1731978685,"price_in":2,"price_out":6,"input_modalities":["text"],"output_modalities":["text"],"description":"Mistral Large 2 2411 is an update of [Mistral Large 2](/mistralai/mistral-large) released together with [Pixtral Large 2411](/mistralai/pixtral-large-2411) It provides a significan"},"mistralai/mistral-large-2407":{"id":"mistralai/mistral-large-2407","name":"Mistral Large 2407","provider":"mistralai","context_length":131072,"created":1731978415,"price_in":2,"price_out":6,"input_modalities":["text"],"output_modalities":["text"],"description":"This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. R"},"mistralai/pixtral-large-2411":{"id":"mistralai/pixtral-large-2411","name":"Mistral: Pixtral Large 2411","provider":"mistralai","context_length":131072,"created":1731977388,"price_in":2,"price_out":6,"input_modalities":["text","image"],"output_modalities":["text"],"description":"Pixtral Large is a 124B parameter, open-weight, multimodal model built on top of [Mistral Large 2](/mistralai/mistral-large-2411). The model is able to understand documents, charts"},"qwen/qwen-2.5-coder-32b-instruct":{"id":"qwen/qwen-2.5-coder-32b-instruct","name":"Qwen2.5 Coder 32B Instruct","provider":"qwen","context_length":32768,"created":1731368400,"price_in":0.66,"price_out":1,"input_modalities":["text"],"output_modalities":["text"],"description":"Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: - Sig"},"thedrummer/unslopnemo-12b":{"id":"thedrummer/unslopnemo-12b","name":"TheDrummer: UnslopNemo 12B","provider":"thedrummer","context_length":32768,"created":1731103448,"price_in":0.39999999999999997,"price_out":0.39999999999999997,"input_modalities":["text"],"output_modalities":["text"],"description":"UnslopNemo v4.1 is the latest addition from the creator of Rocinante, designed for adventure writing and role-play scenarios."},"anthropic/claude-3.5-haiku":{"id":"anthropic/claude-3.5-haiku","name":"Anthropic: Claude 3.5 Haiku","provider":"anthropic","context_length":200000,"created":1730678400,"price_in":0.7999999999999999,"price_out":4,"input_modalities":["text","image"],"output_modalities":["text"],"description":"Claude 3.5 Haiku features offers enhanced capabilities in speed, coding accuracy, and tool use. Engineered to excel in real-time applications, it delivers quick response times that"},"anthracite-org/magnum-v4-72b":{"id":"anthracite-org/magnum-v4-72b","name":"Magnum v4 72B","provider":"anthracite-org","context_length":16384,"created":1729555200,"price_in":3,"price_out":5,"input_modalities":["text"],"output_modalities":["text"],"description":"This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anthropic/claude-3.5-sonnet) and Opus(https://o"},"qwen/qwen-2.5-7b-instruct":{"id":"qwen/qwen-2.5-7b-instruct","name":"Qwen: Qwen2.5 7B Instruct","provider":"qwen","context_length":32768,"created":1729036800,"price_in":0.04,"price_out":0.09999999999999999,"input_modalities":["text"],"output_modalities":["text"],"description":"Qwen2.5 7B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabil"},"inflection/inflection-3-productivity":{"id":"inflection/inflection-3-productivity","name":"Inflection: Inflection 3 Productivity","provider":"inflection","context_length":8000,"created":1728604800,"price_in":2.5,"price_out":10,"input_modalities":["text"],"output_modalities":["text"],"description":"Inflection 3 Productivity is optimized for following instructions. It is better for tasks requiring JSON output or precise adherence to provided guidelines. It has access to recent"},"inflection/inflection-3-pi":{"id":"inflection/inflection-3-pi","name":"Inflection: Inflection 3 Pi","provider":"inflection","context_length":8000,"created":1728604800,"price_in":2.5,"price_out":10,"input_modalities":["text"],"output_modalities":["text"],"description":"Inflection 3 Pi powers Inflection's [Pi](https://pi.ai) chatbot, including backstory, emotional intelligence, productivity, and safety. It has access to recent news, and excels in "},"thedrummer/rocinante-12b":{"id":"thedrummer/rocinante-12b","name":"TheDrummer: Rocinante 12B","provider":"thedrummer","context_length":32768,"created":1727654400,"price_in":0.16999999999999998,"price_out":0.43,"input_modalities":["text"],"output_modalities":["text"],"description":"Rocinante 12B is designed for engaging storytelling and rich prose. Early testers have reported: - Expanded vocabulary with unique and expressive word choices - Enhanced creativity"},"meta-llama/llama-3.2-3b-instruct":{"id":"meta-llama/llama-3.2-3b-instruct","name":"Meta: Llama 3.2 3B Instruct","provider":"meta-llama","context_length":80000,"created":1727222400,"price_in":0.051,"price_out":0.33999999999999997,"input_modalities":["text"],"output_modalities":["text"],"description":"Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summariza"},"meta-llama/llama-3.2-1b-instruct":{"id":"meta-llama/llama-3.2-1b-instruct","name":"Meta: Llama 3.2 1B Instruct","provider":"meta-llama","context_length":60000,"created":1727222400,"price_in":0.027,"price_out":0.19999999999999998,"input_modalities":["text"],"output_modalities":["text"],"description":"Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its "},"meta-llama/llama-3.2-11b-vision-instruct":{"id":"meta-llama/llama-3.2-11b-vision-instruct","name":"Meta: Llama 3.2 11B Vision Instruct","provider":"meta-llama","context_length":131072,"created":1727222400,"price_in":0.245,"price_out":0.245,"input_modalities":["text","image"],"output_modalities":["text"],"description":"Llama 3.2 11B Vision is a multimodal model with 11 billion parameters, designed to handle tasks combining visual and textual data. It excels in tasks such as image captioning and.."},"qwen/qwen-2.5-72b-instruct":{"id":"qwen/qwen-2.5-72b-instruct","name":"Qwen2.5 72B Instruct","provider":"qwen","context_length":32768,"created":1726704000,"price_in":0.36,"price_out":0.39999999999999997,"input_modalities":["text"],"output_modalities":["text"],"description":"Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabi"},"cohere/command-r-plus-08-2024":{"id":"cohere/command-r-plus-08-2024","name":"Cohere: Command R+ (08-2024)","provider":"cohere","context_length":128000,"created":1724976000,"price_in":2.5,"price_out":10,"input_modalities":["text"],"output_modalities":["text"],"description":"command-r-plus-08-2024 is an update of the [Command R+](/models/cohere/command-r-plus) with roughly 50% higher throughput and 25% lower latencies as compared to the previous Comman"},"cohere/command-r-08-2024":{"id":"cohere/command-r-08-2024","name":"Cohere: Command R (08-2024)","provider":"cohere","context_length":128000,"created":1724976000,"price_in":0.15,"price_out":0.6,"input_modalities":["text"],"output_modalities":["text"],"description":"command-r-08-2024 is an update of the [Command R](/models/cohere/command-r) with improved performance for multilingual retrieval-augmented generation (RAG) and tool use. More broad"},"sao10k/l3.1-euryale-70b":{"id":"sao10k/l3.1-euryale-70b","name":"Sao10K: Llama 3.1 Euryale 70B v2.2","provider":"sao10k","context_length":131072,"created":1724803200,"price_in":0.85,"price_out":0.85,"input_modalities":["text"],"output_modalities":["text"],"description":"Euryale L3.1 70B v2.2 is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70B v2.1](/models/sao10k/l3-euryale-70b)."},"nousresearch/hermes-3-llama-3.1-70b":{"id":"nousresearch/hermes-3-llama-3.1-70b","name":"Nous: Hermes 3 70B Instruct","provider":"nousresearch","context_length":131072,"created":1723939200,"price_in":0.3,"price_out":0.3,"input_modalities":["text"],"output_modalities":["text"],"description":"Hermes 3 is a generalist language model with many improvements over [Hermes 2](/models/nousresearch/nous-hermes-2-mistral-7b-dpo), including advanced agentic capabilities, much bet"},"nousresearch/hermes-3-llama-3.1-405b":{"id":"nousresearch/hermes-3-llama-3.1-405b","name":"Nous: Hermes 3 405B Instruct","provider":"nousresearch","context_length":131072,"created":1723766400,"price_in":1,"price_out":1,"input_modalities":["text"],"output_modalities":["text"],"description":"Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, "},"sao10k/l3-lunaris-8b":{"id":"sao10k/l3-lunaris-8b","name":"Sao10K: Llama 3 8B Lunaris","provider":"sao10k","context_length":8192,"created":1723507200,"price_in":0.04,"price_out":0.049999999999999996,"input_modalities":["text"],"output_modalities":["text"],"description":"Lunaris 8B is a versatile generalist and roleplaying model based on Llama 3. It's a strategic merge of multiple models, designed to balance creativity with improved logic and gener"},"openai/gpt-4o-2024-08-06":{"id":"openai/gpt-4o-2024-08-06","name":"OpenAI: GPT-4o (2024-08-06)","provider":"openai","context_length":128000,"created":1722902400,"price_in":2.5,"price_out":10,"input_modalities":["text","image","file"],"output_modalities":["text"],"description":"The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format. Read more [here](https://openai."},"meta-llama/llama-3.1-8b-instruct":{"id":"meta-llama/llama-3.1-8b-instruct","name":"Meta: Llama 3.1 8B Instruct","provider":"meta-llama","context_length":16384,"created":1721692800,"price_in":0.02,"price_out":0.049999999999999996,"input_modalities":["text"],"output_modalities":["text"],"description":"Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance co"},"meta-llama/llama-3.1-70b-instruct":{"id":"meta-llama/llama-3.1-70b-instruct","name":"Meta: Llama 3.1 70B Instruct","provider":"meta-llama","context_length":131072,"created":1721692800,"price_in":0.39999999999999997,"price_out":0.39999999999999997,"input_modalities":["text"],"output_modalities":["text"],"description":"Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases. It has demonst"},"mistralai/mistral-nemo":{"id":"mistralai/mistral-nemo","name":"Mistral: Mistral Nemo","provider":"mistralai","context_length":131072,"created":1721347200,"price_in":0.02,"price_out":0.03,"input_modalities":["text"],"output_modalities":["text"],"description":"A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italia"},"openai/gpt-4o-mini-2024-07-18":{"id":"openai/gpt-4o-mini-2024-07-18","name":"OpenAI: GPT-4o-mini (2024-07-18)","provider":"openai","context_length":128000,"created":1721260800,"price_in":0.15,"price_out":0.6,"input_modalities":["text","image","file"],"output_modalities":["text"],"description":"GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is m"},"openai/gpt-4o-mini":{"id":"openai/gpt-4o-mini","name":"OpenAI: GPT-4o-mini","provider":"openai","context_length":128000,"created":1721260800,"price_in":0.15,"price_out":0.6,"input_modalities":["text","image","file"],"output_modalities":["text"],"description":"GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is m"},"google/gemma-2-27b-it":{"id":"google/gemma-2-27b-it","name":"Google: Gemma 2 27B","provider":"google","context_length":8192,"created":1720828800,"price_in":0.65,"price_out":0.65,"input_modalities":["text"],"output_modalities":["text"],"description":"Gemma 2 27B by Google is an open model built from the same research and technology used to create the [Gemini models](/models?q=gemini). Gemma models are well-suited for a variety "},"sao10k/l3-euryale-70b":{"id":"sao10k/l3-euryale-70b","name":"Sao10k: Llama 3 Euryale 70B v2.1","provider":"sao10k","context_length":8192,"created":1718668800,"price_in":1.48,"price_out":1.48,"input_modalities":["text"],"output_modalities":["text"],"description":"Euryale 70B v2.1 is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). - Better prompt adherence. - Better anatomy / spatial awareness. - Adapts much bet"},"nousresearch/hermes-2-pro-llama-3-8b":{"id":"nousresearch/hermes-2-pro-llama-3-8b","name":"NousResearch: Hermes 2 Pro - Llama-3 8B","provider":"nousresearch","context_length":8192,"created":1716768000,"price_in":0.14,"price_out":0.14,"input_modalities":["text"],"output_modalities":["text"],"description":"Hermes 2 Pro is an upgraded, retrained version of Nous Hermes 2, consisting of an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced..."},"openai/gpt-4o-2024-05-13":{"id":"openai/gpt-4o-2024-05-13","name":"OpenAI: GPT-4o (2024-05-13)","provider":"openai","context_length":128000,"created":1715558400,"price_in":5,"price_out":15,"input_modalities":["text","image","file"],"output_modalities":["text"],"description":"GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gp"},"openai/gpt-4o":{"id":"openai/gpt-4o","name":"OpenAI: GPT-4o","provider":"openai","context_length":128000,"created":1715558400,"price_in":2.5,"price_out":10,"input_modalities":["text","image","file"],"output_modalities":["text"],"description":"GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gp"},"meta-llama/llama-3-8b-instruct":{"id":"meta-llama/llama-3-8b-instruct","name":"Meta: Llama 3 8B Instruct","provider":"meta-llama","context_length":8192,"created":1713398400,"price_in":0.04,"price_out":0.04,"input_modalities":["text"],"output_modalities":["text"],"description":"Meta's latest class of model (Llama 3) launched with a variety of sizes & flavors. This 8B instruct-tuned version was optimized for high quality dialogue usecases. It has demonstra"},"meta-llama/llama-3-70b-instruct":{"id":"meta-llama/llama-3-70b-instruct","name":"Meta: Llama 3 70B Instruct","provider":"meta-llama","context_length":8192,"created":1713398400,"price_in":0.51,"price_out":0.74,"input_modalities":["text"],"output_modalities":["text"],"description":"Meta's latest class of model (Llama 3) launched with a variety of sizes & flavors. This 70B instruct-tuned version was optimized for high quality dialogue usecases. It has demonstr"},"mistralai/mixtral-8x22b-instruct":{"id":"mistralai/mixtral-8x22b-instruct","name":"Mistral: Mixtral 8x22B Instruct","provider":"mistralai","context_length":65536,"created":1713312000,"price_in":2,"price_out":6,"input_modalities":["text"],"output_modalities":["text"],"description":"Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency"},"microsoft/wizardlm-2-8x22b":{"id":"microsoft/wizardlm-2-8x22b","name":"WizardLM-2 8x22B","provider":"microsoft","context_length":65535,"created":1713225600,"price_in":0.62,"price_out":0.62,"input_modalities":["text"],"output_modalities":["text"],"description":"WizardLM-2 8x22B is Microsoft AI's most advanced Wizard model. It demonstrates highly competitive performance compared to leading proprietary models, and it consistently outperform"},"openai/gpt-4-turbo":{"id":"openai/gpt-4-turbo","name":"OpenAI: GPT-4 Turbo","provider":"openai","context_length":128000,"created":1712620800,"price_in":10,"price_out":30,"input_modalities":["text","image"],"output_modalities":["text"],"description":"The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling.\n\nTraining data: up to December 2023."},"anthropic/claude-3-haiku":{"id":"anthropic/claude-3-haiku","name":"Anthropic: Claude 3 Haiku","provider":"anthropic","context_length":200000,"created":1710288000,"price_in":0.25,"price_out":1.25,"input_modalities":["text","image"],"output_modalities":["text"],"description":"Claude 3 Haiku is Anthropic's fastest and most compact model for\nnear-instant responsiveness. Quick and accurate targeted performance.\n\nSee the launch announcement and benchmark re"},"mistralai/mistral-large":{"id":"mistralai/mistral-large","name":"Mistral Large","provider":"mistralai","context_length":128000,"created":1708905600,"price_in":2,"price_out":6,"input_modalities":["text"],"output_modalities":["text"],"description":"This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more."},"openai/gpt-4-turbo-preview":{"id":"openai/gpt-4-turbo-preview","name":"OpenAI: GPT-4 Turbo Preview","provider":"openai","context_length":128000,"created":1706140800,"price_in":10,"price_out":30,"input_modalities":["text"],"output_modalities":["text"],"description":"The preview GPT-4 model with improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more. Training data: up to Dec 2023. **Note:** heavily "},"openai/gpt-3.5-turbo-0613":{"id":"openai/gpt-3.5-turbo-0613","name":"OpenAI: GPT-3.5 Turbo (older v0613)","provider":"openai","context_length":4095,"created":1706140800,"price_in":1,"price_out":2,"input_modalities":["text"],"output_modalities":["text"],"description":"GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.\n\nTraining data up to S"},"alpindale/goliath-120b":{"id":"alpindale/goliath-120b","name":"Goliath 120B","provider":"alpindale","context_length":6144,"created":1699574400,"price_in":3.75,"price_out":7.5,"input_modalities":["text"],"output_modalities":["text"],"description":"A large LLM created by combining two fine-tuned Llama 70B models into one 120B model. Combines Xwin and Euryale. Credits to - [@chargoddard](https://huggingface.co/chargoddard) for"},"openrouter/auto":{"id":"openrouter/auto","name":"Auto Router","provider":"openrouter","context_length":2000000,"created":1699401600,"price_in":-1000000,"price_out":-1000000,"input_modalities":["text","image","audio","file","video"],"output_modalities":["text","image"],"description":"\"Your prompt will be processed by a meta-model and routed to one of dozens of models (see below), optimizing for the best possible output.\\n\\nTo see which model was used, visit..."},"openai/gpt-4-1106-preview":{"id":"openai/gpt-4-1106-preview","name":"OpenAI: GPT-4 Turbo (older v1106)","provider":"openai","context_length":128000,"created":1699228800,"price_in":10,"price_out":30,"input_modalities":["text"],"output_modalities":["text"],"description":"The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling.\n\nTraining data: up to April 2023."},"openai/gpt-3.5-turbo-instruct":{"id":"openai/gpt-3.5-turbo-instruct","name":"OpenAI: GPT-3.5 Turbo Instruct","provider":"openai","context_length":4095,"created":1695859200,"price_in":1.5,"price_out":2,"input_modalities":["text"],"output_modalities":["text"],"description":"This model is a variant of GPT-3.5 Turbo tuned for instructional prompts and omitting chat-related optimizations. Training data: up to Sep 2021."},"mistralai/mistral-7b-instruct-v0.1":{"id":"mistralai/mistral-7b-instruct-v0.1","name":"Mistral: Mistral 7B Instruct v0.1","provider":"mistralai","context_length":2824,"created":1695859200,"price_in":0.11,"price_out":0.19,"input_modalities":["text"],"output_modalities":["text"],"description":"A 7.3B parameter model that outperforms Llama 2 13B on all benchmarks, with optimizations for speed and context length."},"openai/gpt-3.5-turbo-16k":{"id":"openai/gpt-3.5-turbo-16k","name":"OpenAI: GPT-3.5 Turbo 16k","provider":"openai","context_length":16385,"created":1693180800,"price_in":3,"price_out":4,"input_modalities":["text"],"output_modalities":["text"],"description":"This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost. Training data: up..."},"mancer/weaver":{"id":"mancer/weaver","name":"Mancer: Weaver (alpha)","provider":"mancer","context_length":8000,"created":1690934400,"price_in":0.75,"price_out":1,"input_modalities":["text"],"output_modalities":["text"],"description":"An attempt to recreate Claude-style verbosity, but don't expect the same level of coherence or memory. Meant for use in roleplay/narrative situations."},"undi95/remm-slerp-l2-13b":{"id":"undi95/remm-slerp-l2-13b","name":"ReMM SLERP 13B","provider":"undi95","context_length":6144,"created":1689984000,"price_in":0.44999999999999996,"price_out":0.65,"input_modalities":["text"],"output_modalities":["text"],"description":"A recreation trial of the original MythoMax-L2-B13 but with updated models. #merge"},"gryphe/mythomax-l2-13b":{"id":"gryphe/mythomax-l2-13b","name":"MythoMax 13B","provider":"gryphe","context_length":4096,"created":1688256000,"price_in":0.06,"price_out":0.06,"input_modalities":["text"],"output_modalities":["text"],"description":"One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay. #merge"},"openai/gpt-4-0314":{"id":"openai/gpt-4-0314","name":"OpenAI: GPT-4 (older v0314)","provider":"openai","context_length":8191,"created":1685232000,"price_in":30,"price_out":60,"input_modalities":["text"],"output_modalities":["text"],"description":"GPT-4-0314 is the first version of GPT-4 released, with a context length of 8,192 tokens, and was supported until June 14. Training data: up to Sep 2021."},"openai/gpt-4":{"id":"openai/gpt-4","name":"OpenAI: GPT-4","provider":"openai","context_length":8191,"created":1685232000,"price_in":30,"price_out":60,"input_modalities":["text"],"output_modalities":["text"],"description":"OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader genera"},"openai/gpt-3.5-turbo":{"id":"openai/gpt-3.5-turbo","name":"OpenAI: GPT-3.5 Turbo","provider":"openai","context_length":16385,"created":1685232000,"price_in":0.5,"price_out":1.5,"input_modalities":["text"],"output_modalities":["text"],"description":"GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.\n\nTraining data up to S"}},"groups":{"text":["google/gemini-3.1-flash-lite","openai/gpt-chat-latest","x-ai/grok-4.3","ibm-granite/granite-4.1-8b","mistralai/mistral-medium-3-5","openrouter/owl-alpha","~anthropic/claude-haiku-latest","~openai/gpt-mini-latest","~google/gemini-pro-latest","~moonshotai/kimi-latest","~google/gemini-flash-latest","~anthropic/claude-sonnet-latest","~openai/gpt-latest","qwen/qwen3.5-plus-20260420","qwen/qwen3.6-flash","qwen/qwen3.6-35b-a3b","qwen/qwen3.6-max-preview","qwen/qwen3.6-27b","openai/gpt-5.5-pro","openai/gpt-5.5","deepseek/deepseek-v4-pro","deepseek/deepseek-v4-flash","inclusionai/ling-2.6-1t","tencent/hy3-preview","xiaomi/mimo-v2.5-pro","xiaomi/mimo-v2.5","openai/gpt-5.4-image-2","inclusionai/ling-2.6-flash","~anthropic/claude-opus-latest","openrouter/pareto-code","moonshotai/kimi-k2.6","anthropic/claude-opus-4.7","anthropic/claude-opus-4.6-fast","z-ai/glm-5.1","google/gemma-4-26b-a4b-it","google/gemma-4-31b-it","qwen/qwen3.6-plus","z-ai/glm-5v-turbo","arcee-ai/trinity-large-thinking","x-ai/grok-4.20-multi-agent","x-ai/grok-4.20","google/lyria-3-pro-preview","google/lyria-3-clip-preview","kwaipilot/kat-coder-pro-v2","rekaai/reka-edge","xiaomi/mimo-v2-omni","xiaomi/mimo-v2-pro","minimax/minimax-m2.7","openai/gpt-5.4-nano","openai/gpt-5.4-mini","mistralai/mistral-small-2603","z-ai/glm-5-turbo","nvidia/nemotron-3-super-120b-a12b","bytedance-seed/seed-2.0-lite","qwen/qwen3.5-9b","openai/gpt-5.4-pro","openai/gpt-5.4","inception/mercury-2","openai/gpt-5.3-chat","google/gemini-3.1-flash-lite-preview","bytedance-seed/seed-2.0-mini","google/gemini-3.1-flash-image-preview","qwen/qwen3.5-35b-a3b","qwen/qwen3.5-27b","qwen/qwen3.5-122b-a10b","qwen/qwen3.5-flash-02-23","liquid/lfm-2-24b-a2b","google/gemini-3.1-pro-preview-customtools","openai/gpt-5.3-codex","aion-labs/aion-2.0","google/gemini-3.1-pro-preview","anthropic/claude-sonnet-4.6","qwen/qwen3.5-plus-02-15","qwen/qwen3.5-397b-a17b","minimax/minimax-m2.5","z-ai/glm-5","qwen/qwen3-max-thinking","anthropic/claude-opus-4.6","qwen/qwen3-coder-next","openrouter/free","stepfun/step-3.5-flash","arcee-ai/trinity-large-preview","moonshotai/kimi-k2.5","upstage/solar-pro-3","minimax/minimax-m2-her","writer/palmyra-x5","openai/gpt-audio","openai/gpt-audio-mini","z-ai/glm-4.7-flash","openai/gpt-5.2-codex","bytedance-seed/seed-1.6-flash","bytedance-seed/seed-1.6","minimax/minimax-m2.1","z-ai/glm-4.7","google/gemini-3-flash-preview","xiaomi/mimo-v2-flash","nvidia/nemotron-3-nano-30b-a3b","openai/gpt-5.2-chat","openai/gpt-5.2-pro","openai/gpt-5.2","mistralai/devstral-2512","relace/relace-search","z-ai/glm-4.6v","nex-agi/deepseek-v3.1-nex-n1","essentialai/rnj-1-instruct","openrouter/bodybuilder","openai/gpt-5.1-codex-max","amazon/nova-2-lite-v1","mistralai/ministral-14b-2512","mistralai/ministral-8b-2512","mistralai/ministral-3b-2512","mistralai/mistral-large-2512","arcee-ai/trinity-mini","deepseek/deepseek-v3.2-speciale","deepseek/deepseek-v3.2","prime-intellect/intellect-3","anthropic/claude-opus-4.5","allenai/olmo-3-32b-think","google/gemini-3-pro-image-preview","x-ai/grok-4.1-fast","deepcogito/cogito-v2.1-671b","openai/gpt-5.1","openai/gpt-5.1-chat","openai/gpt-5.1-codex","openai/gpt-5.1-codex-mini","moonshotai/kimi-k2-thinking","amazon/nova-premier-v1","perplexity/sonar-pro-search","mistralai/voxtral-small-24b-2507","openai/gpt-oss-safeguard-20b","minimax/minimax-m2","qwen/qwen3-vl-32b-instruct","ibm-granite/granite-4.0-h-micro","microsoft/phi-4-mini-instruct","openai/gpt-5-image-mini","anthropic/claude-haiku-4.5","qwen/qwen3-vl-8b-thinking","qwen/qwen3-vl-8b-instruct","openai/gpt-5-image","openai/o3-deep-research","openai/o4-mini-deep-research","nvidia/llama-3.3-nemotron-super-49b-v1.5","baidu/ernie-4.5-21b-a3b-thinking","google/gemini-2.5-flash-image","qwen/qwen3-vl-30b-a3b-thinking","qwen/qwen3-vl-30b-a3b-instruct","openai/gpt-5-pro","z-ai/glm-4.6","anthropic/claude-sonnet-4.5","deepseek/deepseek-v3.2-exp","thedrummer/cydonia-24b-v4.1","relace/relace-apply-3","google/gemini-2.5-flash-lite-preview-09-2025","qwen/qwen3-vl-235b-a22b-thinking","qwen/qwen3-vl-235b-a22b-instruct","qwen/qwen3-max","qwen/qwen3-coder-plus","openai/gpt-5-codex","deepseek/deepseek-v3.1-terminus","x-ai/grok-4-fast","alibaba/tongyi-deepresearch-30b-a3b","qwen/qwen3-coder-flash","qwen/qwen3-next-80b-a3b-thinking","qwen/qwen3-next-80b-a3b-instruct","qwen/qwen-plus-2025-07-28:thinking","qwen/qwen-plus-2025-07-28","nvidia/nemotron-nano-9b-v2","moonshotai/kimi-k2-0905","qwen/qwen3-30b-a3b-thinking-2507","x-ai/grok-code-fast-1","nousresearch/hermes-4-70b","nousresearch/hermes-4-405b","deepseek/deepseek-chat-v3.1","openai/gpt-4o-audio-preview","mistralai/mistral-medium-3.1","baidu/ernie-4.5-21b-a3b","baidu/ernie-4.5-vl-28b-a3b","z-ai/glm-4.5v","ai21/jamba-large-1.7","openai/gpt-5-chat","openai/gpt-5","openai/gpt-5-mini","openai/gpt-5-nano","openai/gpt-oss-120b","openai/gpt-oss-20b","anthropic/claude-opus-4.1","mistralai/codestral-2508","qwen/qwen3-coder-30b-a3b-instruct","qwen/qwen3-30b-a3b-instruct-2507","z-ai/glm-4.5","z-ai/glm-4.5-air","qwen/qwen3-235b-a22b-thinking-2507","z-ai/glm-4-32b","qwen/qwen3-coder","bytedance/ui-tars-1.5-7b","google/gemini-2.5-flash-lite","qwen/qwen3-235b-a22b-2507","switchpoint/router","moonshotai/kimi-k2","mistralai/devstral-medium","mistralai/devstral-small","x-ai/grok-4","tencent/hunyuan-a13b-instruct","morph/morph-v3-large","morph/morph-v3-fast","baidu/ernie-4.5-vl-424b-a47b","baidu/ernie-4.5-300b-a47b","mistralai/mistral-small-3.2-24b-instruct","minimax/minimax-m1","google/gemini-2.5-flash","google/gemini-2.5-pro","openai/o3-pro","x-ai/grok-3-mini","x-ai/grok-3","google/gemini-2.5-pro-preview","deepseek/deepseek-r1-0528","anthropic/claude-opus-4","anthropic/claude-sonnet-4","google/gemma-3n-e4b-it","mistralai/mistral-medium-3","google/gemini-2.5-pro-preview-05-06","arcee-ai/spotlight","arcee-ai/maestro-reasoning","arcee-ai/virtuoso-large","arcee-ai/coder-large","meta-llama/llama-guard-4-12b","qwen/qwen3-30b-a3b","qwen/qwen3-8b","qwen/qwen3-14b","qwen/qwen3-32b","qwen/qwen3-235b-a22b","openai/o4-mini-high","openai/o3","openai/o4-mini","openai/gpt-4.1","openai/gpt-4.1-mini","openai/gpt-4.1-nano","alfredpros/codellama-7b-instruct-solidity","x-ai/grok-3-mini-beta","x-ai/grok-3-beta","meta-llama/llama-4-maverick","meta-llama/llama-4-scout","deepseek/deepseek-chat-v3-0324","openai/o1-pro","mistralai/mistral-small-3.1-24b-instruct","google/gemma-3-4b-it","google/gemma-3-12b-it","cohere/command-a","openai/gpt-4o-mini-search-preview","openai/gpt-4o-search-preview","rekaai/reka-flash-3","google/gemma-3-27b-it","thedrummer/skyfall-36b-v2","perplexity/sonar-reasoning-pro","perplexity/sonar-pro","perplexity/sonar-deep-research","google/gemini-2.0-flash-lite-001","anthropic/claude-3.7-sonnet","anthropic/claude-3.7-sonnet:thinking","mistralai/mistral-saba","meta-llama/llama-guard-3-8b","openai/o3-mini-high","google/gemini-2.0-flash-001","qwen/qwen-vl-plus","aion-labs/aion-1.0","aion-labs/aion-1.0-mini","aion-labs/aion-rp-llama-3.1-8b","qwen/qwen-vl-max","qwen/qwen-turbo","qwen/qwen2.5-vl-72b-instruct","qwen/qwen-plus","qwen/qwen-max","openai/o3-mini","mistralai/mistral-small-24b-instruct-2501","deepseek/deepseek-r1-distill-qwen-32b","perplexity/sonar","deepseek/deepseek-r1-distill-llama-70b","deepseek/deepseek-r1","minimax/minimax-01","microsoft/phi-4","sao10k/l3.1-70b-hanami-x1","deepseek/deepseek-chat","sao10k/l3.3-euryale-70b","openai/o1","cohere/command-r7b-12-2024","meta-llama/llama-3.3-70b-instruct","amazon/nova-lite-v1","amazon/nova-micro-v1","amazon/nova-pro-v1","openai/gpt-4o-2024-11-20","mistralai/mistral-large-2411","mistralai/mistral-large-2407","mistralai/pixtral-large-2411","qwen/qwen-2.5-coder-32b-instruct","thedrummer/unslopnemo-12b","anthropic/claude-3.5-haiku","anthracite-org/magnum-v4-72b","qwen/qwen-2.5-7b-instruct","inflection/inflection-3-productivity","inflection/inflection-3-pi","thedrummer/rocinante-12b","meta-llama/llama-3.2-3b-instruct","meta-llama/llama-3.2-1b-instruct","meta-llama/llama-3.2-11b-vision-instruct","qwen/qwen-2.5-72b-instruct","cohere/command-r-plus-08-2024","cohere/command-r-08-2024","sao10k/l3.1-euryale-70b","nousresearch/hermes-3-llama-3.1-70b","nousresearch/hermes-3-llama-3.1-405b","sao10k/l3-lunaris-8b","openai/gpt-4o-2024-08-06","meta-llama/llama-3.1-8b-instruct","meta-llama/llama-3.1-70b-instruct","mistralai/mistral-nemo","openai/gpt-4o-mini-2024-07-18","openai/gpt-4o-mini","google/gemma-2-27b-it","sao10k/l3-euryale-70b","nousresearch/hermes-2-pro-llama-3-8b","openai/gpt-4o-2024-05-13","openai/gpt-4o","meta-llama/llama-3-8b-instruct","meta-llama/llama-3-70b-instruct","mistralai/mixtral-8x22b-instruct","microsoft/wizardlm-2-8x22b","openai/gpt-4-turbo","anthropic/claude-3-haiku","mistralai/mistral-large","openai/gpt-4-turbo-preview","openai/gpt-3.5-turbo-0613","alpindale/goliath-120b","openrouter/auto","openai/gpt-4-1106-preview","openai/gpt-3.5-turbo-instruct","mistralai/mistral-7b-instruct-v0.1","openai/gpt-3.5-turbo-16k","mancer/weaver","undi95/remm-slerp-l2-13b","gryphe/mythomax-l2-13b","openai/gpt-4-0314","openai/gpt-4","openai/gpt-3.5-turbo"],"image":["google/gemini-3.1-flash-lite","openai/gpt-chat-latest","x-ai/grok-4.3","mistralai/mistral-medium-3-5","~anthropic/claude-haiku-latest","~openai/gpt-mini-latest","~google/gemini-pro-latest","~moonshotai/kimi-latest","~google/gemini-flash-latest","~anthropic/claude-sonnet-latest","~openai/gpt-latest","qwen/qwen3.5-plus-20260420","qwen/qwen3.6-flash","qwen/qwen3.6-35b-a3b","qwen/qwen3.6-27b","openai/gpt-5.5-pro","openai/gpt-5.5","xiaomi/mimo-v2.5","openai/gpt-5.4-image-2","~anthropic/claude-opus-latest","moonshotai/kimi-k2.6","anthropic/claude-opus-4.7","anthropic/claude-opus-4.6-fast","google/gemma-4-26b-a4b-it","google/gemma-4-31b-it","qwen/qwen3.6-plus","z-ai/glm-5v-turbo","x-ai/grok-4.20-multi-agent","x-ai/grok-4.20","google/lyria-3-pro-preview","google/lyria-3-clip-preview","rekaai/reka-edge","xiaomi/mimo-v2-omni","openai/gpt-5.4-nano","openai/gpt-5.4-mini","mistralai/mistral-small-2603","bytedance-seed/seed-2.0-lite","qwen/qwen3.5-9b","openai/gpt-5.4-pro","openai/gpt-5.4","openai/gpt-5.3-chat","google/gemini-3.1-flash-lite-preview","bytedance-seed/seed-2.0-mini","google/gemini-3.1-flash-image-preview","qwen/qwen3.5-35b-a3b","qwen/qwen3.5-27b","qwen/qwen3.5-122b-a10b","qwen/qwen3.5-flash-02-23","google/gemini-3.1-pro-preview-customtools","openai/gpt-5.3-codex","google/gemini-3.1-pro-preview","anthropic/claude-sonnet-4.6","qwen/qwen3.5-plus-02-15","qwen/qwen3.5-397b-a17b","anthropic/claude-opus-4.6","openrouter/free","moonshotai/kimi-k2.5","openai/gpt-5.2-codex","bytedance-seed/seed-1.6-flash","bytedance-seed/seed-1.6","google/gemini-3-flash-preview","openai/gpt-5.2-chat","openai/gpt-5.2-pro","openai/gpt-5.2","z-ai/glm-4.6v","openai/gpt-5.1-codex-max","amazon/nova-2-lite-v1","mistralai/ministral-14b-2512","mistralai/ministral-8b-2512","mistralai/ministral-3b-2512","mistralai/mistral-large-2512","anthropic/claude-opus-4.5","google/gemini-3-pro-image-preview","x-ai/grok-4.1-fast","openai/gpt-5.1","openai/gpt-5.1-chat","openai/gpt-5.1-codex","openai/gpt-5.1-codex-mini","amazon/nova-premier-v1","perplexity/sonar-pro-search","qwen/qwen3-vl-32b-instruct","openai/gpt-5-image-mini","anthropic/claude-haiku-4.5","qwen/qwen3-vl-8b-thinking","qwen/qwen3-vl-8b-instruct","openai/gpt-5-image","openai/o3-deep-research","openai/o4-mini-deep-research","google/gemini-2.5-flash-image","qwen/qwen3-vl-30b-a3b-thinking","qwen/qwen3-vl-30b-a3b-instruct","openai/gpt-5-pro","anthropic/claude-sonnet-4.5","google/gemini-2.5-flash-lite-preview-09-2025","qwen/qwen3-vl-235b-a22b-thinking","qwen/qwen3-vl-235b-a22b-instruct","openai/gpt-5-codex","x-ai/grok-4-fast","mistralai/mistral-medium-3.1","baidu/ernie-4.5-vl-28b-a3b","z-ai/glm-4.5v","openai/gpt-5-chat","openai/gpt-5","openai/gpt-5-mini","openai/gpt-5-nano","anthropic/claude-opus-4.1","bytedance/ui-tars-1.5-7b","google/gemini-2.5-flash-lite","x-ai/grok-4","baidu/ernie-4.5-vl-424b-a47b","mistralai/mistral-small-3.2-24b-instruct","google/gemini-2.5-flash","google/gemini-2.5-pro","openai/o3-pro","google/gemini-2.5-pro-preview","anthropic/claude-opus-4","anthropic/claude-sonnet-4","mistralai/mistral-medium-3","google/gemini-2.5-pro-preview-05-06","arcee-ai/spotlight","meta-llama/llama-guard-4-12b","openai/o4-mini-high","openai/o3","openai/o4-mini","openai/gpt-4.1","openai/gpt-4.1-mini","openai/gpt-4.1-nano","meta-llama/llama-4-maverick","meta-llama/llama-4-scout","openai/o1-pro","mistralai/mistral-small-3.1-24b-instruct","google/gemma-3-4b-it","google/gemma-3-12b-it","google/gemma-3-27b-it","perplexity/sonar-reasoning-pro","perplexity/sonar-pro","google/gemini-2.0-flash-lite-001","anthropic/claude-3.7-sonnet","anthropic/claude-3.7-sonnet:thinking","google/gemini-2.0-flash-001","qwen/qwen-vl-plus","qwen/qwen-vl-max","qwen/qwen2.5-vl-72b-instruct","perplexity/sonar","minimax/minimax-01","openai/o1","amazon/nova-lite-v1","amazon/nova-pro-v1","openai/gpt-4o-2024-11-20","mistralai/pixtral-large-2411","anthropic/claude-3.5-haiku","meta-llama/llama-3.2-11b-vision-instruct","openai/gpt-4o-2024-08-06","openai/gpt-4o-mini-2024-07-18","openai/gpt-4o-mini","openai/gpt-4o-2024-05-13","openai/gpt-4o","openai/gpt-4-turbo","anthropic/claude-3-haiku","openrouter/auto"],"file":["google/gemini-3.1-flash-lite","openai/gpt-chat-latest","~openai/gpt-mini-latest","~google/gemini-pro-latest","~google/gemini-flash-latest","~openai/gpt-latest","openai/gpt-5.5-pro","openai/gpt-5.5","openai/gpt-5.4-image-2","x-ai/grok-4.20-multi-agent","x-ai/grok-4.20","openai/gpt-5.4-nano","openai/gpt-5.4-mini","openai/gpt-5.4-pro","openai/gpt-5.4","openai/gpt-5.3-chat","google/gemini-3.1-flash-lite-preview","google/gemini-3.1-pro-preview-customtools","openai/gpt-5.3-codex","google/gemini-3.1-pro-preview","google/gemini-3-flash-preview","openai/gpt-5.2-chat","openai/gpt-5.2-pro","openai/gpt-5.2","amazon/nova-2-lite-v1","anthropic/claude-opus-4.5","x-ai/grok-4.1-fast","openai/gpt-5.1","openai/gpt-5.1-chat","openai/gpt-5-image-mini","openai/gpt-5-image","openai/o3-deep-research","openai/o4-mini-deep-research","openai/gpt-5-pro","anthropic/claude-sonnet-4.5","google/gemini-2.5-flash-lite-preview-09-2025","x-ai/grok-4-fast","openai/gpt-5-chat","openai/gpt-5","openai/gpt-5-mini","openai/gpt-5-nano","anthropic/claude-opus-4.1","google/gemini-2.5-flash-lite","x-ai/grok-4","google/gemini-2.5-flash","google/gemini-2.5-pro","openai/o3-pro","google/gemini-2.5-pro-preview","anthropic/claude-opus-4","anthropic/claude-sonnet-4","google/gemini-2.5-pro-preview-05-06","openai/o4-mini-high","openai/o3","openai/o4-mini","openai/gpt-4.1","openai/gpt-4.1-mini","openai/gpt-4.1-nano","openai/o1-pro","google/gemini-2.0-flash-lite-001","anthropic/claude-3.7-sonnet","anthropic/claude-3.7-sonnet:thinking","openai/o3-mini-high","google/gemini-2.0-flash-001","openai/o3-mini","openai/o1","openai/gpt-4o-2024-11-20","openai/gpt-4o-2024-08-06","openai/gpt-4o-mini-2024-07-18","openai/gpt-4o-mini","openai/gpt-4o-2024-05-13","openai/gpt-4o","openrouter/auto"],"audio":["google/gemini-3.1-flash-lite","~google/gemini-pro-latest","~google/gemini-flash-latest","xiaomi/mimo-v2.5","xiaomi/mimo-v2-omni","google/gemini-3.1-flash-lite-preview","google/gemini-3.1-pro-preview-customtools","google/gemini-3.1-pro-preview","openai/gpt-audio","openai/gpt-audio-mini","google/gemini-3-flash-preview","mistralai/voxtral-small-24b-2507","google/gemini-2.5-flash-lite-preview-09-2025","openai/gpt-4o-audio-preview","google/gemini-2.5-flash-lite","google/gemini-2.5-flash","google/gemini-2.5-pro","google/gemini-2.5-pro-preview","google/gemini-2.5-pro-preview-05-06","google/gemini-2.0-flash-lite-001","google/gemini-2.0-flash-001","openrouter/auto"],"video":["google/gemini-3.1-flash-lite","~google/gemini-pro-latest","~google/gemini-flash-latest","qwen/qwen3.5-plus-20260420","qwen/qwen3.6-flash","qwen/qwen3.6-35b-a3b","qwen/qwen3.6-27b","xiaomi/mimo-v2.5","google/gemma-4-26b-a4b-it","google/gemma-4-31b-it","qwen/qwen3.6-plus","z-ai/glm-5v-turbo","rekaai/reka-edge","xiaomi/mimo-v2-omni","bytedance-seed/seed-2.0-lite","qwen/qwen3.5-9b","google/gemini-3.1-flash-lite-preview","bytedance-seed/seed-2.0-mini","qwen/qwen3.5-35b-a3b","qwen/qwen3.5-27b","qwen/qwen3.5-122b-a10b","qwen/qwen3.5-flash-02-23","google/gemini-3.1-pro-preview-customtools","google/gemini-3.1-pro-preview","qwen/qwen3.5-plus-02-15","qwen/qwen3.5-397b-a17b","bytedance-seed/seed-1.6-flash","bytedance-seed/seed-1.6","google/gemini-3-flash-preview","z-ai/glm-4.6v","amazon/nova-2-lite-v1","google/gemini-2.5-flash-lite-preview-09-2025","google/gemini-2.5-flash-lite","google/gemini-2.5-flash","google/gemini-2.5-pro","google/gemini-2.5-pro-preview-05-06","google/gemini-2.0-flash-lite-001","google/gemini-2.0-flash-001","openrouter/auto"],"image_gen":["openai/gpt-5.4-image-2","google/gemini-3.1-flash-image-preview","google/gemini-3-pro-image-preview","openai/gpt-5-image-mini","openai/gpt-5-image","google/gemini-2.5-flash-image","openrouter/auto"],"speech":["google/lyria-3-pro-preview","google/lyria-3-clip-preview","openai/gpt-audio","openai/gpt-audio-mini","openai/gpt-4o-audio-preview"],"transcription":["google/gemini-3.1-flash-lite","~google/gemini-pro-latest","~google/gemini-flash-latest","xiaomi/mimo-v2.5","xiaomi/mimo-v2-omni","google/gemini-3.1-flash-lite-preview","google/gemini-3.1-pro-preview-customtools","google/gemini-3.1-pro-preview","google/gemini-3-flash-preview","mistralai/voxtral-small-24b-2507","google/gemini-2.5-flash-lite-preview-09-2025","google/gemini-2.5-flash-lite","google/gemini-2.5-flash","google/gemini-2.5-pro","google/gemini-2.5-pro-preview","google/gemini-2.5-pro-preview-05-06","google/gemini-2.0-flash-lite-001","google/gemini-2.0-flash-001"]}}