Models

Every model available through our OpenRouter connection — switch between language, image, and video.

  • Aion 3.5

    AionLabs ·aion-labs/aion-3.5

    $3.00/M in · $6.00/M out

    262K ctx

    Aion 3.5 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each...

  • Aion 3.5 Mini

    AionLabs ·aion-labs/aion-3.5-mini

    $0.700/M in · $1.40/M out

    262K ctx

    Aion 3.5 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It is the smaller, lower-cost sibling of Aion 3.5 and uses...

  • Aion-2.0

    AionLabs ·aion-labs/aion-2.0

    $0.800/M in · $1.60/M out

    131K ctx

    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, making narratives feel more engaging....

  • Aion-3.0

    AionLabs ·aion-labs/aion-3.0

    $3.00/M in · $6.00/M out

    131K ctx

    Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each contribute...

  • Aion-3.0-Mini

    AionLabs ·aion-labs/aion-3.0-mini

    $0.700/M in · $1.40/M out

    131K ctx

    Aion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. It uses a collaborative generation process in which multiple specialized models each...

  • Aion-RP 1.0 (8B)

    AionLabs ·aion-labs/aion-rp-llama-3.1-8b

    $0.800/M in · $1.60/M out

    33K ctx

    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 each other’s responses. It is a fine-tuned base model...

  • Apodex 1.1 Mini (free)

    Apodex ·apodex/apodex-1.1-mini:free

    Free

    262K ctx

    Apodex 1.1 Mini is a reasoning-first model from Apodex, built for complex, long-horizon research and forecasting tasks. It works directly with files, data, code, and tools to produce verifiable results,...

  • Auto Router

    Openrouter ·openrouter/auto

    2M ctx

    The Auto Router automatically selects the best model for your prompt, powered by the wisdom of the market. It routes you based on what the OpenRouter community collectively spends on...

  • Auto Router (Beta)

    Openrouter ·openrouter/auto-beta

    2M ctx

    The experimental version of our Auto Router where we test new improvements. Use it to get the latest and greatest version of our general purpose auto router, but expect beta...

  • Body Builder (beta)

    Openrouter ·openrouter/bodybuilder

    128K ctx

    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 appropriate API calls. Example:...

  • Claude Fable 5

    Anthropic ·anthropic/claude-fable-5

    $10.00/M in · $50.00/M out

    1M ctx

    Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...

  • Claude Fable 5 (batch)

    Anthropic ·anthropic/claude-fable-5:batch

    $5.00/M in · $25.00/M out

    1M ctx

    Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...

  • Claude Fable 5.1

    Anthropic ·anthropic/claude-fable-5.1

    $10.00/M in · $50.00/M out

    1M ctx

    Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual...

  • Claude Fable 5.1 (batch)

    Anthropic ·anthropic/claude-fable-5.1:batch

    $5.00/M in · $25.00/M out

    1M ctx

    Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual...

  • Claude Fable Latest

    Anthropic ·~anthropic/claude-fable-latest

    $10.00/M in · $50.00/M out

    1M ctx

    This model always redirects to the latest model in the Claude Fable family.

  • Claude Haiku 4.5

    Anthropic ·anthropic/claude-haiku-4.5

    $1.00/M in · $5.00/M out

    200K ctx

    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 Claude Sonnet 4’s performance...

  • Claude Haiku 4.5 (batch)

    Anthropic ·anthropic/claude-haiku-4.5:batch

    $0.500/M in · $2.50/M out

    200K ctx

    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 Claude Sonnet 4’s performance...

  • Claude Haiku Latest

    Anthropic ·~anthropic/claude-haiku-latest

    $1.00/M in · $5.00/M out

    200K ctx

    This model always redirects to the latest model in the Claude Haiku family.

  • Claude Opus 4.1

    Anthropic ·anthropic/claude-opus-4.1

    $15.00/M in · $75.00/M out

    200K ctx

    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 and shows notable gains...

  • Claude Opus 4.1 (batch)

    Anthropic ·anthropic/claude-opus-4.1:batch

    $7.50/M in · $37.50/M out

    200K ctx

    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 and shows notable gains...

  • Claude Opus 4.5

    Anthropic ·anthropic/claude-opus-4.5

    $5.00/M in · $25.00/M out

    200K ctx

    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 capabilities, competitive performance across real-world coding and...

  • Claude Opus 4.5 (batch)

    Anthropic ·anthropic/claude-opus-4.5:batch

    $2.50/M in · $12.50/M out

    200K ctx

    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 capabilities, competitive performance across real-world coding and...

  • Claude Opus 4.6

    Anthropic ·anthropic/claude-opus-4.6

    $5.00/M in · $25.00/M out

    1M ctx

    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, making it especially effective...

  • Claude Opus 4.6 (batch)

    Anthropic ·anthropic/claude-opus-4.6:batch

    $2.50/M in · $12.50/M out

    1M ctx

    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, making it especially effective...

  • Claude Opus 4.7

    Anthropic ·anthropic/claude-opus-4.7

    $5.00/M in · $25.00/M out

    1M ctx

    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 stronger performance on...

  • Claude Opus 4.7 (batch)

    Anthropic ·anthropic/claude-opus-4.7:batch

    $2.50/M in · $12.50/M out

    1M ctx

    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 stronger performance on...

  • Claude Opus 4.8

    Anthropic ·anthropic/claude-opus-4.8

    $5.00/M in · $25.00/M out

    1M ctx

    Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...

  • Claude Opus 4.8 (batch)

    Anthropic ·anthropic/claude-opus-4.8:batch

    $2.50/M in · $12.50/M out

    1M ctx

    Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...

  • Claude Opus 5

    Anthropic ·anthropic/claude-opus-5

    $5.00/M in · $25.00/M out

    1M ctx

    Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...

  • Claude Opus 5 (batch)

    Anthropic ·anthropic/claude-opus-5:batch

    $2.50/M in · $12.50/M out

    1M ctx

    Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...

  • Claude Opus 5.5

    Anthropic ·anthropic/claude-opus-5.5

    $4.00/M in · $20.00/M out

    1M ctx

    Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code...

  • Claude Opus 5.5 (batch)

    Anthropic ·anthropic/claude-opus-5.5:batch

    $2.00/M in · $10.00/M out

    1M ctx

    Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code...

  • Claude Opus Latest

    Anthropic ·~anthropic/claude-opus-latest

    $4.00/M in · $20.00/M out

    1M ctx

    This model always redirects to the latest model in the Claude Opus family.

  • Claude Sonnet 4

    Anthropic ·anthropic/claude-sonnet-4

    $3.00/M in · $15.00/M out

    200K ctx

    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. Achieving state-of-the-art performance on SWE-bench (72.7%),...

  • Claude Sonnet 4.5

    Anthropic ·anthropic/claude-sonnet-4.5

    $3.00/M in · $15.00/M out

    1M ctx

    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 benchmarks such as SWE-bench Verified, with...

  • Claude Sonnet 4.5 (batch)

    Anthropic ·anthropic/claude-sonnet-4.5:batch

    $1.50/M in · $7.50/M out

    1M ctx

    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 benchmarks such as SWE-bench Verified, with...

  • Claude Sonnet 4.6

    Anthropic ·anthropic/claude-sonnet-4.6

    $3.00/M in · $15.00/M out

    1M ctx

    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 codebase navigation, end-to-end project management with...

  • Claude Sonnet 4.6 (batch)

    Anthropic ·anthropic/claude-sonnet-4.6:batch

    $1.50/M in · $7.50/M out

    1M ctx

    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 codebase navigation, end-to-end project management with...

  • Claude Sonnet 5

    Anthropic ·anthropic/claude-sonnet-5

    $2.00/M in · $10.00/M out

    1M ctx

    Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...

  • Claude Sonnet 5 (batch)

    Anthropic ·anthropic/claude-sonnet-5:batch

    $1.00/M in · $5.00/M out

    1M ctx

    Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...

  • Claude Sonnet 5.5

    Anthropic ·anthropic/claude-sonnet-5.5

    $2.00/M in · $10.00/M out

    1M ctx

    Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing...

  • Claude Sonnet 5.5 (batch)

    Anthropic ·anthropic/claude-sonnet-5.5:batch

    $1.00/M in · $5.00/M out

    1M ctx

    Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing...

  • Claude Sonnet Latest

    Anthropic ·~anthropic/claude-sonnet-latest

    $2.00/M in · $10.00/M out

    1M ctx

    This model always redirects to the latest model in the Claude Sonnet family.

  • Codestral 2508

    Mistral ·mistralai/codestral-2508

    $0.300/M in · $0.900/M out

    256K ctx

    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 correction and test generation. [Blog Post](https://mistral.ai/news/codestral-25-08)

  • Codestral 2508 (batch)

    Mistral ·mistralai/codestral-2508:batch

    $0.150/M in · $0.450/M out

    256K ctx

    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 correction and test generation. [Blog Post](https://mistral.ai/news/codestral-25-08)

  • Command A

    Cohere ·cohere/command-a

    $2.50/M in · $10.00/M out

    256K ctx

    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 other leading proprietary...

  • Command A+

    Cohere ·cohere/command-a-plus

    $0.300/M in · $1.50/M out

    192K ctx

    Command A+ is Cohere's flagship model for enterprise agentic workflows. It accepts text and image inputs with a 192K context window, supports native tool calling with strict tool schemas, structured...

  • Command R (08-2024)

    Cohere ·cohere/command-r-08-2024

    $0.150/M in · $0.600/M out

    128K ctx

    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 broadly, it is better at math, code and reasoning and...

  • Command R+ (08-2024)

    Cohere ·cohere/command-r-plus-08-2024

    $2.50/M in · $10.00/M out

    128K ctx

    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 Command R+ version, while keeping the hardware footprint...

  • Command R7B (12-2024)

    Cohere ·cohere/command-r7b-12-2024

    $0.037/M in · $0.150/M out

    128K ctx

    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...

  • Cydonia 24B V4.1

    TheDrummer ·thedrummer/cydonia-24b-v4.1

    $0.300/M in · $0.500/M out

    131K ctx

    Uncensored and creative writing model based on Mistral Small 3.2 24B with good recall, prompt adherence, and intelligence.

  • DeepSeek Flash Latest

    DeepSeek ·~deepseek/deepseek-flash-latest

    $0.015/M in · $1.20/M out

    1M ctx

    This model always redirects to the latest model in the DeepSeek Flash family.

  • DeepSeek Pro Latest

    DeepSeek ·~deepseek/deepseek-pro-latest

    $0.132/M in · $0.396/M out

    1M ctx

    This model always redirects to the latest model in the DeepSeek Pro family.

  • DeepSeek V3

    DeepSeek ·deepseek/deepseek-chat

    $0.257/M in · $1.03/M out

    164K ctx

    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 tokens, the reported evaluations...

  • DeepSeek V3 0324

    DeepSeek ·deepseek/deepseek-chat-v3-0324

    $0.290/M in · $1.14/M out

    164K ctx

    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/deepseek-chat-v3) model and performs really well...

  • DeepSeek V3.1

    DeepSeek ·deepseek/deepseek-chat-v3.1

    $0.250/M in · $0.950/M out

    164K ctx

    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 base with a two-phase long-context...

  • DeepSeek V3.1 Terminus

    DeepSeek ·deepseek/deepseek-v3.1-terminus

    $0.300/M in · $1.00/M out

    164K ctx

    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, including language consistency and agent capabilities, further optimizing the model's...

  • DeepSeek V3.2

    DeepSeek ·deepseek/deepseek-v3.2

    $0.280/M in · $0.420/M out

    164K ctx

    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 Attention (DSA), a fine-grained sparse attention mechanism...

  • DeepSeek V3.2 Exp

    DeepSeek ·deepseek/deepseek-v3.2-exp

    $0.270/M in · $0.410/M out

    164K ctx

    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 Attention (DSA), a fine-grained sparse attention mechanism...

  • DeepSeek V4 Flash 0423

    DeepSeek ·deepseek/deepseek-v4-flash

    $0.042/M in · $0.084/M out

    1M ctx

    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. It is designed for fast inference and...

  • DeepSeek V4 Flash 0731

    DeepSeek ·deepseek/deepseek-v4-flash-0731

    $0.017/M in · $1.28/M out

    1M ctx

    DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....

  • DeepSeek V4 Flash Latest

    DeepSeek ·~deepseek/deepseek-v4-flash-latest

    $0.0038/M in · $1.60/M out

    1M ctx

    This model always redirects to the latest model in the DeepSeek V4 Flash family.

  • DeepSeek V4 Flash Vision Exp

    DeepSeek ·deepseek/deepseek-v4-flash-vision-exp

    $0.216/M in · $0.647/M out

    1M ctx

    DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of [DeepSeek V4 Flash 0731](https://openrouter.ai/deepseek/deepseek-v4-flash-0731) from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,...

  • DeepSeek V4 Pro 0423

    DeepSeek ·deepseek/deepseek-v4-pro

    $0.209/M in · $0.418/M out

    1M ctx

    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 designed for advanced reasoning, coding,...

  • DeepSeek V4 Pro 0813

    DeepSeek ·deepseek/deepseek-v4-pro-0813

    $1.32/M in · $3.96/M out

    1M ctx

    DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.

  • DeepSeek V4.1 Flash

    DeepSeek ·deepseek/deepseek-v4.1-flash

    $0.015/M in · $1.20/M out

    1M ctx

    DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...

  • DeepSeek V4.1 Flash (batch)

    DeepSeek ·deepseek/deepseek-v4.1-flash:batch

    $0.112/M in · $0.336/M out

    1M ctx

    DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...

  • Devstral 2 2512

    Mistral ·mistralai/devstral-2512

    $0.400/M in · $2.00/M out

    262K ctx

    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. Devstral 2 supports exploring...

  • Dots3-Note Preview (free)

    Dots Studio ·dots-studio/dots-3-note-preview:free

    Free

    512K ctx

    Dots3-Note Preview is an open-weight mixture-of-experts model from Dots Studio, with 16B active parameters out of 280B total. It is the lightest model in the Dots 3 family and is...

  • Ember-1

    Fireworks ·fireworks/ember-1

    $3.00/M in · $15.00/M out

    1M ctx

    Ember-1 is a specialized reasoning model from Fireworks Research, built on [Kimi K3](https://openrouter.ai/moonshotai/kimi-k3). It is designed to make every token go further: it produces shorter reasoning traces, using roughly 40%...

  • ERNIE 4.5 VL 424B A47B

    Baidu ·baidu/ernie-4.5-vl-424b-a47b

    $0.420/M in · $1.25/M out

    123K ctx

    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 jointly on text and image data...

  • Free Models Router

    Openrouter ·openrouter/free

    Free

    200K ctx

    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 models that...

  • Fugu Max

    Sakana ·sakana/fugu-max

    $2.00/M in · $6.00/M out

    1M ctx

    Fugu Max is the cost-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...

  • Fugu Ultra

    Sakana ·sakana/fugu-ultra

    $5.00/M in · $30.00/M out

    1M ctx

    Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...

  • Fugu Ultra v2

    Sakana ·sakana/fugu-ultra-v2

    $5.00/M in · $30.00/M out

    1M ctx

    Fugu Ultra v2 is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to...

  • Fusion

    OpenRouter ·openrouter/fusion

    1M ctx

    Fusion turns your prompt into a small multi-model deliberation. A panel of expert models (see below) analyzes your prompt in parallel with web search and web fetch enabled, then a...

  • Gemini 2.5 Flash

    Google ·google/gemini-2.5-flash

    $0.300/M in · $2.50/M out

    1M ctx

    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 "thinking" capabilities, enabling it to provide responses with greater...

  • Gemini 2.5 Flash (batch)

    Google ·google/gemini-2.5-flash:batch

    $0.150/M in · $1.25/M out

    1M ctx

    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 "thinking" capabilities, enabling it to provide responses with greater...

  • Gemini 2.5 Flash Lite

    Google ·google/gemini-2.5-flash-lite

    $0.100/M in · $0.400/M out

    1M ctx

    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 generation, and better performance...

  • Gemini 2.5 Flash Lite (batch)

    Google ·google/gemini-2.5-flash-lite:batch

    $0.050/M in · $0.200/M out

    1M ctx

    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 generation, and better performance...

  • Gemini 2.5 Pro

    Google ·google/gemini-2.5-pro

    $1.25/M in · $10.00/M out

    1M ctx

    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 reason through responses with enhanced accuracy...

  • Gemini 2.5 Pro (batch)

    Google ·google/gemini-2.5-pro:batch

    $0.625/M in · $5.00/M out

    1M ctx

    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 reason through responses with enhanced accuracy...

  • Gemini 2.5 Pro Preview 06-05

    Google ·google/gemini-2.5-pro-preview

    $1.25/M in · $10.00/M out

    1M ctx

    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 reason through responses with enhanced accuracy...

  • Gemini 3 Flash Preview

    Google ·google/gemini-3-flash-preview

    $0.500/M in · $3.00/M out

    1M ctx

    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 tool...

  • Gemini 3 Flash Preview (batch)

    Google ·google/gemini-3-flash-preview:batch

    $0.250/M in · $1.50/M out

    1M ctx

    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 tool...

  • Gemini 3.1 Flash Lite

    Google ·google/gemini-3.1-flash-lite

    $0.250/M in · $1.50/M out

    1M ctx

    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 is designed for lightweight agentic...

  • Gemini 3.1 Flash Lite (batch)

    Google ·google/gemini-3.1-flash-lite:batch

    $0.125/M in · $0.750/M out

    1M ctx

    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 is designed for lightweight agentic...

  • Gemini 3.1 Flash Lite Preview

    Google ·google/gemini-3.1-flash-lite-preview

    $0.250/M in · $1.50/M out

    1M ctx

    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 2.5 Flash performance across...

  • Gemini 3.1 Pro Preview

    Google ·google/gemini-3.1-pro-preview

    $2.00/M in · $12.00/M out

    1M ctx

    Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...

  • Gemini 3.1 Pro Preview (batch)

    Google ·google/gemini-3.1-pro-preview:batch

    $1.00/M in · $6.00/M out

    1M ctx

    Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...

  • Gemini 3.1 Pro Preview Custom Tools

    Google ·google/gemini-3.1-pro-preview-customtools

    $2.00/M in · $12.00/M out

    1M ctx

    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-party...

  • Gemini 3.5 Flash

    Google ·google/gemini-3.5-flash

    $1.50/M in · $9.00/M out

    1M ctx

    Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...

  • Gemini 3.5 Flash (batch)

    Google ·google/gemini-3.5-flash:batch

    $0.750/M in · $4.50/M out

    1M ctx

    Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...

  • Gemini 3.5 Flash Lite

    Google ·google/gemini-3.5-flash-lite

    $0.300/M in · $2.50/M out

    1M ctx

    Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.

  • Gemini 3.5 Flash Lite (batch)

    Google ·google/gemini-3.5-flash-lite:batch

    $0.150/M in · $1.25/M out

    1M ctx

    Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.

  • Gemini 3.6 Flash

    Google ·google/gemini-3.6-flash

    $0.750/M in · $3.75/M out

    1M ctx

    Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and...

  • Gemini 3.6 Flash (batch)

    Google ·google/gemini-3.6-flash:batch

    $0.375/M in · $1.88/M out

    1M ctx

    Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and...

  • Gemini 3.7 Flash

    Google ·google/gemini-3.7-flash

    $0.750/M in · $3.75/M out

    1M ctx

    Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step...

  • Gemini 3.7 Flash (batch)

    Google ·google/gemini-3.7-flash:batch

    $0.375/M in · $1.88/M out

    1M ctx

    Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step...

  • Gemini 3.8 Flash

    Google ·google/gemini-3.8-flash

    $0.750/M in · $3.75/M out

    1M ctx

    Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.

  • Gemini 3.8 Flash (batch)

    Google ·google/gemini-3.8-flash:batch

    $0.375/M in · $1.88/M out

    1M ctx

    Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.

  • Gemini Flash Latest

    Google ·~google/gemini-flash-latest

    $0.750/M in · $3.75/M out

    1M ctx

    This model always redirects to the latest model in the Gemini Flash family.

  • Gemini Pro Latest

    Google ·~google/gemini-pro-latest

    $2.00/M in · $12.00/M out

    1M ctx

    This model always redirects to the latest model in the Gemini Pro family.

  • Gemma 2 27B

    Google ·google/gemma-2-27b-it

    $0.650/M in · $0.650/M out

    8K ctx

    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 of...

  • Gemma 3 12B

    Google ·google/gemma-3-12b-it

    $0.050/M in · $0.150/M out

    131K ctx

    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 improved math, reasoning, and chat capabilities,...

  • Gemma 3 27B

    Google ·google/gemma-3-27b-it

    $0.080/M in · $0.450/M out

    131K ctx

    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 improved math, reasoning, and chat capabilities,...

  • Gemma 3 4B

    Google ·google/gemma-3-4b-it

    $0.050/M in · $0.100/M out

    131K ctx

    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 improved math, reasoning, and chat capabilities,...

  • Gemma 4 26B A4B

    Google ·google/gemma-4-26b-a4b-it

    $0.090/M in · $0.300/M out

    262K ctx

    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 — delivering near-31B quality at...

  • Gemma 4 26B A4B (free)

    Google ·google/gemma-4-26b-a4b-it:free

    Free

    262K ctx

    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 — delivering near-31B quality at...

  • Gemma 4 31B

    Google ·google/gemma-4-31b-it

    $0.090/M in · $0.340/M out

    262K ctx

    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/reasoning mode, native function...

  • Gemma 4 31B (free)

    Google ·google/gemma-4-31b-it:free

    Free

    262K ctx

    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/reasoning mode, native function...

  • GLM 4.5

    Z.ai ·z-ai/glm-4.5

    $0.600/M in · $2.20/M out

    131K ctx

    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 up to 128k tokens. GLM-4.5 delivers significantly...

  • GLM 4.5 Air

    Z.ai ·z-ai/glm-4.5-air

    $0.130/M in · $0.850/M out

    131K ctx

    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) architecture but with a more compact parameter...

  • GLM 4.5V

    Z.ai ·z-ai/glm-4.5v

    $0.600/M in · $1.80/M out

    66K ctx

    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, it achieves state-of-the-art results in video understanding,...

  • GLM 4.6

    Z.ai ·z-ai/glm-4.6

    $0.430/M in · $1.75/M out

    205K ctx

    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 handle more complex...

  • GLM 4.6V

    Z.ai ·z-ai/glm-4.6v

    $0.300/M in · $0.900/M out

    131K ctx

    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 tokens, processes complex page layouts...

  • GLM 4.7

    Z.ai ·z-ai/glm-4.7

    $0.600/M in · $2.20/M out

    205K ctx

    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 significant improvements in executing complex agent tasks while...

  • GLM 4.7 Flash

    Z.ai ·z-ai/glm-4.7-flash

    $0.061/M in · $0.400/M out

    200K ctx

    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 capabilities, long-horizon task planning,...

  • GLM 5

    Z.ai ·z-ai/glm-5

    $0.600/M in · $1.92/M out

    205K ctx

    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-grade performance on large-scale programming tasks, rivaling leading...

  • GLM 5 Turbo

    Z.ai ·z-ai/glm-5-turbo

    $1.20/M in · $4.00/M out

    203K ctx

    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-world agent workflows...

  • GLM 5.1

    Z.ai ·z-ai/glm-5.1

    $0.965/M in · $3.03/M out

    205K ctx

    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 interactions, GLM-5.1 can work independently and continuously on...

  • GLM 5.2

    Z.ai ·z-ai/glm-5.2

    $0.410/M in · $3.99/M out

    1M ctx

    GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...

  • GLM 5.3

    Z.ai ·z-ai/glm-5.3

    $1.40/M in · $4.40/M out

    1M ctx

    GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...

  • GLM 5.3 (batch)

    Z.ai ·z-ai/glm-5.3:batch

    $0.450/M in · $2.00/M out

    1M ctx

    GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...

  • GLM 5.3 Flash

    Z.ai ·z-ai/glm-5.3-flash

    $0.150/M in · $0.500/M out

    1M ctx

    GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...

  • GLM 5.3 Flash (batch)

    Z.ai ·z-ai/glm-5.3-flash:batch

    $0.060/M in · $0.200/M out

    1M ctx

    GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...

  • GLM 5.3 FlashX

    Z.ai ·z-ai/glm-5.3-flashx

    $0.370/M in · $1.25/M out

    1M ctx

    GLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens/s. Built on the same hybrid sparse and linear attention architecture...

  • GLM 5.3 Prime

    Z.ai ·z-ai/glm-5.3-prime

    $2.80/M in · $8.80/M out

    1M ctx

    GLM-5.3-Prime is the high-speed variant of Z.ai's GLM-5.3, inheriting its full capabilities while delivering 1.5–2× the output throughput through inference acceleration. It supports text input and output with a 1M-token...

  • GLM 5V Turbo

    Z.ai ·z-ai/glm-5v-turbo

    $1.20/M in · $4.00/M out

    203K ctx

    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, excels at long-horizon planning, complex coding,...

  • GLM Flash Latest

    Z.ai ·~z-ai/glm-flash-latest

    $0.026/M in · $0.900/M out

    1M ctx

    This model always redirects to the latest model in the GLM Flash family.

  • GLM Latest

    Z.ai ·~z-ai/glm-latest

    $0.120/M in · $4.00/M out

    1M ctx

    This model always redirects to the latest GLM model from Z.ai.

  • GPT Astra Latest

    OpenAI ·~openai/gpt-astra-latest

    $10.00/M in · $50.00/M out

    1.1M ctx

    This model always redirects to the latest model in the GPT Astra family.

  • GPT Audio

    OpenAI ·openai/gpt-audio

    $2.50/M in · $10.00/M out

    128K ctx

    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 consistency. Audio is priced...

  • GPT Audio Mini

    OpenAI ·openai/gpt-audio-mini

    $0.600/M in · $2.40/M out

    128K ctx

    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 $0.60 per million...

  • GPT Chat Latest

    OpenAI ·openai/gpt-chat-latest

    $5.00/M in · $30.00/M out

    400K ctx

    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 updates...

  • GPT Luna Latest

    OpenAI ·~openai/gpt-luna-latest

    $0.100/M in · $0.500/M out

    1.1M ctx

    This model always redirects to the latest model in the GPT Luna family.

  • GPT Mini Latest

    OpenAI ·~openai/gpt-mini-latest

    $0.750/M in · $4.50/M out

    400K ctx

    This model always redirects to the latest model in the GPT Mini family.

  • GPT Sol Latest

    OpenAI ·~openai/gpt-sol-latest

    $2.00/M in · $10.00/M out

    1.1M ctx

    This model always redirects to the latest model in the GPT Sol family.

  • GPT Terra Latest

    OpenAI ·~openai/gpt-terra-latest

    $2.00/M in · $12.00/M out

    1.1M ctx

    This model always redirects to the latest model in the GPT Terra family.

  • GPT-3.5 Turbo

    OpenAI ·openai/gpt-3.5-turbo

    $0.500/M in · $1.50/M out

    16K ctx

    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. Training data up to Sep 2021.

  • GPT-3.5 Turbo (batch)

    OpenAI ·openai/gpt-3.5-turbo:batch

    $0.250/M in · $0.750/M out

    16K ctx

    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. Training data up to Sep 2021.

  • GPT-3.5 Turbo (older v0613)

    OpenAI ·openai/gpt-3.5-turbo-0613

    $1.00/M in · $2.00/M out

    4K ctx

    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. Training data up to Sep 2021.

  • GPT-3.5 Turbo 16k

    OpenAI ·openai/gpt-3.5-turbo-16k

    $3.00/M in · $4.00/M out

    16K ctx

    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...

  • GPT-3.5 Turbo Instruct

    OpenAI ·openai/gpt-3.5-turbo-instruct

    $1.50/M in · $2.00/M out

    4K ctx

    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.

  • GPT-4

    OpenAI ·openai/gpt-4

    $30.00/M in · $60.00/M out

    8K ctx

    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 general knowledge and advanced reasoning...

  • GPT-4 Turbo

    OpenAI ·openai/gpt-4-turbo

    $10.00/M in · $30.00/M out

    128K ctx

    The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling. Training data: up to December 2023.

  • GPT-4 Turbo (batch)

    OpenAI ·openai/gpt-4-turbo:batch

    $5.00/M in · $15.00/M out

    128K ctx

    The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling. Training data: up to December 2023.

  • GPT-4.1

    OpenAI ·openai/gpt-4.1

    $2.00/M in · $8.00/M out

    1M ctx

    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 context window and outperforms GPT-4o and...

  • GPT-4.1 (batch)

    OpenAI ·openai/gpt-4.1:batch

    $1.00/M in · $4.00/M out

    1M ctx

    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 context window and outperforms GPT-4o and...

  • GPT-4.1 Mini

    OpenAI ·openai/gpt-4.1-mini

    $0.400/M in · $1.60/M out

    1M ctx

    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 45.1% on hard...

  • GPT-4.1 Mini (batch)

    OpenAI ·openai/gpt-4.1-mini:batch

    $0.200/M in · $0.800/M out

    1M ctx

    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 45.1% on hard...

  • GPT-4.1 Nano

    OpenAI ·openai/gpt-4.1-nano

    $0.100/M in · $0.400/M out

    1M ctx

    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...

  • GPT-4.1 Nano (batch)

    OpenAI ·openai/gpt-4.1-nano:batch

    $0.050/M in · $0.200/M out

    1M ctx

    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...

  • GPT-4o

    OpenAI ·openai/gpt-4o

    $2.50/M in · $10.00/M out

    128K ctx

    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/gpt-4-turbo) while being twice as...

  • GPT-4o (2024-05-13)

    OpenAI ·openai/gpt-4o-2024-05-13

    $5.00/M in · $15.00/M out

    128K ctx

    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/gpt-4-turbo) while being twice as...

  • GPT-4o (2024-08-06)

    OpenAI ·openai/gpt-4o-2024-08-06

    $2.50/M in · $10.00/M out

    128K ctx

    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.com/index/introducing-structured-outputs-in-the-api/). GPT-4o ("o" for "omni") is...

  • GPT-4o (2024-11-20)

    OpenAI ·openai/gpt-4o-2024-11-20

    $2.50/M in · $10.00/M out

    128K ctx

    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 at working with uploaded...

  • GPT-4o (batch)

    OpenAI ·openai/gpt-4o:batch

    $1.25/M in · $5.00/M out

    128K ctx

    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/gpt-4-turbo) while being twice as...

  • GPT-4o-mini

    OpenAI ·openai/gpt-4o-mini

    $0.150/M in · $0.600/M out

    128K ctx

    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 many multiples more affordable...

  • GPT-4o-mini (2024-07-18)

    OpenAI ·openai/gpt-4o-mini-2024-07-18

    $0.150/M in · $0.600/M out

    128K ctx

    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 many multiples more affordable...

  • GPT-4o-mini (batch)

    OpenAI ·openai/gpt-4o-mini:batch

    $0.075/M in · $0.300/M out

    128K ctx

    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 many multiples more affordable...

  • GPT-5

    OpenAI ·openai/gpt-5

    $1.25/M in · $10.00/M out

    400K ctx

    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 reasoning, instruction following, and accuracy...

  • GPT-5 (batch)

    OpenAI ·openai/gpt-5:batch

    $0.625/M in · $5.00/M out

    400K ctx

    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 reasoning, instruction following, and accuracy...

  • GPT-5 Image

    OpenAI ·openai/gpt-5-image

    $10.00/M in · $10.00/M out

    400K ctx

    [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 quality, and user experience while incorporating GPT Image 1's superior instruction following,...

  • GPT-5 Image Mini

    OpenAI ·openai/gpt-5-image-mini

    $2.50/M in · $2.00/M out

    400K ctx

    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 generation. This natively multimodal model features superior instruction following, text...

  • GPT-5 Mini

    OpenAI ·openai/gpt-5-mini

    $0.250/M in · $2.00/M out

    400K ctx

    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 with reduced latency and cost....

  • GPT-5 Mini (batch)

    OpenAI ·openai/gpt-5-mini:batch

    $0.125/M in · $1.00/M out

    400K ctx

    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 with reduced latency and cost....

  • GPT-5 Nano

    OpenAI ·openai/gpt-5-nano

    $0.050/M in · $0.400/M out

    400K ctx

    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 reasoning depth compared to its larger...

  • GPT-5 Nano (batch)

    OpenAI ·openai/gpt-5-nano:batch

    $0.025/M in · $0.200/M out

    400K ctx

    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 reasoning depth compared to its larger...

  • GPT-5 Pro

    OpenAI ·openai/gpt-5-pro

    $15.00/M in · $120.00/M out

    400K ctx

    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 reasoning, instruction following, and...

  • GPT-5 Pro (batch)

    OpenAI ·openai/gpt-5-pro:batch

    $7.50/M in · $60.00/M out

    400K ctx

    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 reasoning, instruction following, and...

  • GPT-5.1

    OpenAI ·openai/gpt-5.1

    $1.25/M in · $10.00/M out

    400K ctx

    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 compared to GPT-5. It uses adaptive reasoning...

  • GPT-5.1 (batch)

    OpenAI ·openai/gpt-5.1:batch

    $0.625/M in · $5.00/M out

    400K ctx

    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 compared to GPT-5. It uses adaptive reasoning...

  • GPT-5.1-Codex

    OpenAI ·openai/gpt-5.1-codex

    $1.25/M in · $10.00/M out

    400K ctx

    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, independent execution of complex engineering tasks....

  • GPT-5.1-Codex-Max

    OpenAI ·openai/gpt-5.1-codex-max

    $1.25/M in · $10.00/M out

    400K ctx

    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 reasoning stack and trained on agentic...

  • GPT-5.1-Codex-Mini

    OpenAI ·openai/gpt-5.1-codex-mini

    $0.250/M in · $2.00/M out

    400K ctx

    GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex

  • GPT-5.2

    OpenAI ·openai/gpt-5.2

    $1.75/M in · $14.00/M out

    400K ctx

    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 computation dynamically, responding quickly...

  • GPT-5.2 (batch)

    OpenAI ·openai/gpt-5.2:batch

    $0.875/M in · $7.00/M out

    400K ctx

    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 computation dynamically, responding quickly...

  • GPT-5.2 Chat

    OpenAI ·openai/gpt-5.2-chat

    $1.75/M in · $14.00/M out

    128K ctx

    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 to selectively “think” on...

  • GPT-5.2 Pro

    OpenAI ·openai/gpt-5.2-pro

    $21.00/M in · $168.00/M out

    400K ctx

    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 require step-by-step reasoning,...

  • GPT-5.2 Pro (batch)

    OpenAI ·openai/gpt-5.2-pro:batch

    $10.50/M in · $84.00/M out

    400K ctx

    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 require step-by-step reasoning,...

  • GPT-5.2-Codex

    OpenAI ·openai/gpt-5.2-codex

    $1.75/M in · $14.00/M out

    400K ctx

    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, independent execution of complex engineering tasks....

  • GPT-5.3-Codex

    OpenAI ·openai/gpt-5.3-codex

    $1.75/M in · $14.00/M out

    400K ctx

    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 knowledge capabilities of GPT-5.2. It achieves state-of-the-art results...

  • GPT-5.4

    OpenAI ·openai/gpt-5.4

    $2.50/M in · $15.00/M out

    1.1M ctx

    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...

  • GPT-5.4 (batch)

    OpenAI ·openai/gpt-5.4:batch

    $1.25/M in · $7.50/M out

    1.1M ctx

    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...

  • GPT-5.4 Image 2

    OpenAI ·openai/gpt-5.4-image-2

    $8.00/M in · $15.00/M out

    272K ctx

    [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 multimodal workflows, allowing users to seamlessly move between reasoning, coding, and...

  • GPT-5.4 Mini

    OpenAI ·openai/gpt-5.4-mini

    $0.750/M in · $4.50/M out

    400K ctx

    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 performance across reasoning, coding,...

  • GPT-5.4 Mini (batch)

    OpenAI ·openai/gpt-5.4-mini:batch

    $0.375/M in · $2.25/M out

    400K ctx

    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 performance across reasoning, coding,...

  • GPT-5.4 Nano

    OpenAI ·openai/gpt-5.4-nano

    $0.200/M in · $1.25/M out

    400K ctx

    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 designed for low-latency...

  • GPT-5.4 Nano (batch)

    OpenAI ·openai/gpt-5.4-nano:batch

    $0.100/M in · $0.625/M out

    400K ctx

    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 designed for low-latency...

  • GPT-5.4 Pro

    OpenAI ·openai/gpt-5.4-pro

    $30.00/M in · $180.00/M out

    1.1M ctx

    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 context window (922K input, 128K...

  • GPT-5.4 Pro (batch)

    OpenAI ·openai/gpt-5.4-pro:batch

    $15.00/M in · $90.00/M out

    1.1M ctx

    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 context window (922K input, 128K...

  • GPT-5.5

    OpenAI ·openai/gpt-5.5

    $5.00/M in · $30.00/M out

    1.1M ctx

    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 hard tasks. It features a 1M+ token...

  • GPT-5.5 (batch)

    OpenAI ·openai/gpt-5.5:batch

    $2.50/M in · $15.00/M out

    1.1M ctx

    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 hard tasks. It features a 1M+ token...

  • GPT-5.5 Pro

    OpenAI ·openai/gpt-5.5-pro

    $30.00/M in · $180.00/M out

    1.1M ctx

    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 output) with support for...

  • GPT-5.5 Pro (batch)

    OpenAI ·openai/gpt-5.5-pro:batch

    $15.00/M in · $90.00/M out

    1.1M ctx

    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 output) with support for...

  • GPT-5.6 Luna

    OpenAI ·openai/gpt-5.6-luna

    $0.200/M in · $1.20/M out

    1.1M ctx

    GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...

  • GPT-5.6 Luna (batch)

    OpenAI ·openai/gpt-5.6-luna:batch

    $0.100/M in · $0.600/M out

    1.1M ctx

    GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...

  • GPT-5.6 Luna Pro

    OpenAI ·openai/gpt-5.6-luna-pro

    $0.200/M in · $1.20/M out

    1.1M ctx

    GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...

  • GPT-5.6 Luna Pro (batch)

    OpenAI ·openai/gpt-5.6-luna-pro:batch

    $0.100/M in · $0.600/M out

    1.1M ctx

    GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...

  • GPT-5.6 Sol

    OpenAI ·openai/gpt-5.6-sol

    $2.00/M in · $10.00/M out

    1.1M ctx

    GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks...

  • GPT-5.6 Sol (batch)

    OpenAI ·openai/gpt-5.6-sol:batch

    $1.00/M in · $5.00/M out

    1.1M ctx

    GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks...

  • GPT-5.6 Sol Pro

    OpenAI ·openai/gpt-5.6-sol-pro

    $4.00/M in · $20.00/M out

    1.1M ctx

    GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...

  • GPT-5.6 Sol Pro (batch)

    OpenAI ·openai/gpt-5.6-sol-pro:batch

    $1.00/M in · $5.00/M out

    1.1M ctx

    GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...

  • GPT-5.6 Terra

    OpenAI ·openai/gpt-5.6-terra

    $2.00/M in · $12.00/M out

    1.1M ctx

    GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic...

  • GPT-5.6 Terra (batch)

    OpenAI ·openai/gpt-5.6-terra:batch

    $1.00/M in · $6.00/M out

    1.1M ctx

    GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic...

  • GPT-5.6 Terra Pro

    OpenAI ·openai/gpt-5.6-terra-pro

    $2.00/M in · $12.00/M out

    1.1M ctx

    GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...

  • GPT-5.6 Terra Pro (batch)

    OpenAI ·openai/gpt-5.6-terra-pro:batch

    $1.00/M in · $6.00/M out

    1.1M ctx

    GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...

  • GPT-6 Astra

    OpenAI ·openai/gpt-6-astra

    $10.00/M in · $50.00/M out

    1.1M ctx

    GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon...

  • GPT-6 Astra (batch)

    OpenAI ·openai/gpt-6-astra:batch

    $5.00/M in · $25.00/M out

    1.1M ctx

    GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon...

  • GPT-6 Astra Pro

    OpenAI ·openai/gpt-6-astra-pro

    $10.00/M in · $50.00/M out

    1.1M ctx

    GPT-6 Astra Pro is the same underlying model as [GPT-6 Astra](https://openrouter.ai/openai/gpt-6-astra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...

  • GPT-6 Astra Pro (batch)

    OpenAI ·openai/gpt-6-astra-pro:batch

    $5.00/M in · $25.00/M out

    1.1M ctx

    GPT-6 Astra Pro is the same underlying model as [GPT-6 Astra](https://openrouter.ai/openai/gpt-6-astra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...

  • GPT-6 Luna

    OpenAI ·openai/gpt-6-luna

    $0.100/M in · $0.500/M out

    1.1M ctx

    GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic...

  • GPT-6 Luna (batch)

    OpenAI ·openai/gpt-6-luna:batch

    $0.050/M in · $0.250/M out

    1.1M ctx

    GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic...

  • GPT-6 Luna Pro

    OpenAI ·openai/gpt-6-luna-pro

    $0.100/M in · $0.500/M out

    1.1M ctx

    GPT-6 Luna Pro is the same underlying model as [GPT-6 Luna](https://openrouter.ai/openai/gpt-6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...

  • GPT-6 Luna Pro (batch)

    OpenAI ·openai/gpt-6-luna-pro:batch

    $0.050/M in · $0.250/M out

    1.1M ctx

    GPT-6 Luna Pro is the same underlying model as [GPT-6 Luna](https://openrouter.ai/openai/gpt-6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...

  • GPT-6 Sol

    OpenAI ·openai/gpt-6-sol

    $2.00/M in · $10.00/M out

    1.1M ctx

    GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional...

  • GPT-6 Sol (batch)

    OpenAI ·openai/gpt-6-sol:batch

    $1.00/M in · $5.00/M out

    1.1M ctx

    GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional...

  • GPT-6 Sol Pro

    OpenAI ·openai/gpt-6-sol-pro

    $2.00/M in · $10.00/M out

    1.1M ctx

    GPT-6 Sol Pro is the same underlying model as [GPT-6 Sol](https://openrouter.ai/openai/gpt-6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...

  • GPT-6 Sol Pro (batch)

    OpenAI ·openai/gpt-6-sol-pro:batch

    $1.00/M in · $5.00/M out

    1.1M ctx

    GPT-6 Sol Pro is the same underlying model as [GPT-6 Sol](https://openrouter.ai/openai/gpt-6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...

  • GPT-6.1 Sol

    OpenAI ·openai/gpt-6.1-sol

    $2.00/M in · $10.00/M out

    1.1M ctx

    GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional...

  • GPT-6.1 Sol Pro

    OpenAI ·openai/gpt-6.1-sol-pro

    $2.00/M in · $10.00/M out

    1.1M ctx

    GPT-6.1 Sol Pro is the same underlying model as [GPT-6.1 Sol](https://openrouter.ai/openai/gpt-6.1-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...

  • gpt-oss-120b

    OpenAI ·openai/gpt-oss-120b

    $0.037/M in · $0.170/M out

    131K ctx

    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. It activates 5.1B parameters per forward pass and is optimized...

  • gpt-oss-120b (batch)

    OpenAI ·openai/gpt-oss-120b:batch

    $0.030/M in · $0.136/M out

    131K ctx

    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. It activates 5.1B parameters per forward pass and is optimized...

  • gpt-oss-20b

    OpenAI ·openai/gpt-oss-20b

    $0.018/M in · $0.090/M out

    131K ctx

    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 forward pass, optimized for...

  • gpt-oss-20b (batch)

    OpenAI ·openai/gpt-oss-20b:batch

    $0.024/M in · $0.112/M out

    131K ctx

    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 forward pass, optimized for...

  • gpt-oss-safeguard-20b

    OpenAI ·openai/gpt-oss-safeguard-20b

    $0.075/M in · $0.300/M out

    131K ctx

    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 tasks like content classification, LLM filtering, and trust...

  • Granite 4.0 Micro

    IBM ·ibm-granite/granite-4.0-h-micro

    $0.017/M in · $0.112/M out

    131K ctx

    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...

  • Granite 4.2 8B

    IBM ·ibm-granite/granite-4.2-8b

    $0.060/M in · $0.250/M out

    131K ctx

    Granite 4.2 8B is a dense reasoning model from IBM. It is suited for mathematics, code generation, multilingual dialogue, and agentic workflows that need multi-step reasoning. It supports full, low-effort,...

  • Grok 4.20

    SpaceXAI ·x-ai/grok-4.20

    $1.25/M in · $2.50/M out

    2M ctx

    Grok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering...

  • Grok 4.20 Multi-Agent

    SpaceXAI ·x-ai/grok-4.20-multi-agent

    $1.25/M in · $2.50/M out

    2M ctx

    Grok 4.20 Multi-Agent is a variant of SpaceXAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information...

  • Grok 4.3

    SpaceXAI ·x-ai/grok-4.3

    $1.25/M in · $2.50/M out

    1M ctx

    Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...

  • Grok 4.3 (batch)

    SpaceXAI ·x-ai/grok-4.3:batch

    $1.00/M in · $2.00/M out

    1M ctx

    Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...

  • Grok 4.5

    SpaceXAI ·x-ai/grok-4.5

    $2.00/M in · $6.00/M out

    500K ctx

    Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.

  • Grok 4.6

    SpaceXAI ·x-ai/grok-4.6

    $2.00/M in · $6.00/M out

    500K ctx

    Grok 4.6 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM. It is succeeded by [Grok 4.7](/x-ai/grok-4.7).

  • Grok 4.7

    SpaceXAI ·x-ai/grok-4.7

    $2.00/M in · $6.00/M out

    500K ctx

    Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks, verifying its own work, and...

  • Grok Build 0.1

    SpaceXAI ·x-ai/grok-build-0.1

    $1.00/M in · $2.00/M out

    256K ctx

    Grok Build 0.1 is SpaceXAI’s fast coding model trained specifically for agentic software engineering workflows. It supports text and image inputs with text output, and is optimized for interactive coding...

  • Grok Latest

    xAI ·~x-ai/grok-latest

    $2.00/M in · $6.00/M out

    500K ctx

    This model always redirects to the latest Grok model from xAI.

  • Hermes 3 405B Instruct

    Nous ·nousresearch/hermes-3-llama-3.1-405b

    $1.00/M in · $1.00/M out

    131K ctx

    Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...

  • Hermes 3 70B Instruct

    Nous ·nousresearch/hermes-3-llama-3.1-70b

    $0.700/M in · $0.700/M out

    131K ctx

    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 better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...

  • Hermes 4 405B

    Nous ·nousresearch/hermes-4-405b

    $1.00/M in · $3.00/M out

    131K ctx

    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 deliberate internally with...

  • Hunyuan A13B Instruct

    Tencent ·tencent/hunyuan-a13b-instruct

    $0.140/M in · $0.570/M out

    131K ctx

    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-Thought. It offers competitive benchmark...

  • Hy-MT2-1.8B

    Tencent ·tencent/hy-mt2-1.8b

    $0.044/M in · $0.177/M out

    8K ctx

    Hy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided...

  • Hy-MT2-30B-A3B

    Tencent ·tencent/hy-mt2-30b-a3b

    $0.074/M in · $0.295/M out

    8K ctx

    Hy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and...

  • Hy-MT2-7B

    Tencent ·tencent/hy-mt2-7b

    $0.074/M in · $0.295/M out

    8K ctx

    Hy-MT2-7B is a 7B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided translation.

  • Hy3

    Tencent ·tencent/hy3

    $0.132/M in · $0.528/M out

    262K ctx

    Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...

  • Hy3 preview

    Tencent ·tencent/hy3-preview

    $0.180/M in · $0.600/M out

    262K ctx

    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, low, and high modes, allowing it to...

  • Hy4 preview

    Tencent ·tencent/hy4-preview

    $0.834/M in · $2.50/M out

    1M ctx

    Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that...

  • Inkling

    Thinking Machines ·thinkingmachines/inkling

    $0.950/M in · $4.05/M out

    524K ctx

    Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...

  • Inkling (free)

    Thinking Machines ·thinkingmachines/inkling:free

    Free

    1M ctx

    Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...

  • Inkling Small

    Thinking Machines ·thinkingmachines/inkling-small

    $0.450/M in · $1.20/M out

    524K ctx

    Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...

  • Inkling Small (free)

    Thinking Machines ·thinkingmachines/inkling-small:free

    Free

    1M ctx

    Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...

  • Jev Router

    TypeSafe ·typesafe/jev-router

    1M ctx

    Jev Router picks the best model and reasoning effort for each request, balancing quality, speed, and cost. It runs on [Jev](https://openrouter.ai/~typesafe/jev-latest), TypeSafe's first System One model, and adapts as your...

  • KAT-Coder-Pro V2.5

    Kwaipilot ·kwaipilot/kat-coder-pro-v2.5

    $0.740/M in · $2.96/M out

    262K ctx

    KAT-Coder-Pro V2.5 is a flagship-level Agentic Coding model that can directly hand over an entire issue or an entire business workflow to it, allowing it to autonomously locate and make...

  • Kimi K2 0711

    MoonshotAI ·moonshotai/kimi-k2

    $0.570/M in · $2.30/M out

    131K ctx

    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. It is optimized for...

  • Kimi K2 0905

    MoonshotAI ·moonshotai/kimi-k2-0905

    $0.600/M in · $2.50/M out

    262K ctx

    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 trillion total parameters with 32...

  • Kimi K2 Thinking

    MoonshotAI ·moonshotai/kimi-k2-thinking

    $0.600/M in · $2.50/M out

    262K ctx

    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-of-Experts (MoE) architecture introduced in...

  • Kimi K2.5

    MoonshotAI ·moonshotai/kimi-k2.5

    $0.450/M in · $2.25/M out

    262K ctx

    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 pretraining over approximately 15T mixed...

  • Kimi K2.6

    MoonshotAI ·moonshotai/kimi-k2.6

    $0.434/M in · $1.83/M out

    262K ctx

    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-to-end coding tasks across Python, Rust, and Go, and...

  • Kimi K2.7 Code

    MoonshotAI ·moonshotai/kimi-k2.7-code

    $0.671/M in · $3.35/M out

    262K ctx

    MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...

  • Kimi K3

    MoonshotAI ·moonshotai/kimi-k3

    $2.70/M in · $13.50/M out

    1M ctx

    Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...

  • Kimi K3 (batch)

    MoonshotAI ·moonshotai/kimi-k3:batch

    $2.28/M in · $11.40/M out

    1M ctx

    Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...

  • Kimi Latest

    MoonshotAI ·~moonshotai/kimi-latest

    $1.39/M in · $13.00/M out

    1M ctx

    This model always redirects to the latest model in the Kimi family.

  • Laguna S 2.1

    Poolside ·poolside/laguna-s-2.1

    $0.090/M in · $0.180/M out

    1M ctx

    Laguna S 2.1 is the latest coding agent model from [Poolside](<https://poolside.ai/>). Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and...

  • Laguna S 2.1 (free)

    Poolside ·poolside/laguna-s-2.1:free

    Free

    262K ctx

    Laguna S 2.1 is the latest coding agent model from [Poolside](<https://poolside.ai/>). Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and...

  • Laguna XS 2.1

    Poolside ·poolside/laguna-xs-2.1

    $0.060/M in · $0.120/M out

    262K ctx

    Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026). It combines...

  • Laguna XS 2.1 (free)

    Poolside ·poolside/laguna-xs-2.1:free

    Free

    262K ctx

    Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026). It combines...

  • LFM2.5-2.6B (free)

    LiquidAI ·liquid/lfm-2.5-2.6b:free

    Free

    66K ctx

    LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or...

  • Ling 3.0 Flash

    inclusionAI ·inclusionai/ling-3.0-flash

    $0.021/M in · $0.063/M out

    262K ctx

    *Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*. The model is designed with *token efficiency and production-scale agentic inference* as key priorities, enabling developers...

  • Ling 3.0 Flash Fin

    inclusionAI ·inclusionai/ling-3.0-flash-fin

    $0.060/M in · $0.180/M out

    262K ctx

    Ling 3.0 Flash Fin is a finance-focused mixture-of-experts model from InclusionAI, built on Ling 3.0 Flash with 5.1B active parameters out of 124B total. It is designed for real-world investment...

  • Ling 3.0 Flash Sante (free)

    inclusionAI ·inclusionai/ling-3.0-flash-sante:free

    Free

    262K ctx

    Ling 3.0 Flash Sante is a health and medicine-focused mixture-of-experts model from InclusionAI, built on Ling 3.0 Flash with 5.1B active parameters out of 124B total. It is designed for...

  • Ling 3.0 Flash VL

    inclusionAI ·inclusionai/ling-3.0-flash-vl

    $0.021/M in · $0.062/M out

    262K ctx

    Ling 3.0 Flash VL builds on Ling 3.0 Flash (124B total / 5.5B active MoE from InclusionAI), further strengthening its language capabilities while adding native visual perception and advanced visual...

  • Llama 3 8B Lunaris

    Sao10K ·sao10k/l3-lunaris-8b

    $0.040/M in · $0.050/M out

    8K ctx

    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 general knowledge....

  • Llama 3.1 70B Instruct

    Meta ·meta-llama/llama-3.1-70b-instruct

    $0.400/M in · $0.400/M out

    131K ctx

    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 demonstrated strong...

  • Llama 3.1 8B Instruct

    Meta ·meta-llama/llama-3.1-8b-instruct

    $0.050/M in · $0.080/M out

    131K ctx

    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 compared to...

  • Llama 3.1 Euryale 70B v2.2

    Sao10K ·sao10k/l3.1-euryale-70b

    $0.850/M in · $0.850/M out

    131K ctx

    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).

  • Llama 3.2 1B Instruct

    Meta ·meta-llama/llama-3.2-1b-instruct

    $0.027/M in · $0.201/M out

    60K ctx

    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 smaller size allows it to operate...

  • Llama 3.2 3B Instruct

    Meta ·meta-llama/llama-3.2-3b-instruct

    $0.050/M in · $0.330/M out

    131K ctx

    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 summarization. Designed with the latest transformer architecture, it...

  • Llama 3.3 70B Instruct

    Meta ·meta-llama/llama-3.3-70b-instruct

    $0.100/M in · $0.320/M out

    131K ctx

    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 only model...

  • Llama 3.3 Euryale 70B

    Sao10K ·sao10k/l3.3-euryale-70b

    $0.650/M in · $0.750/M out

    131K ctx

    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).

  • Llama 4 Maverick

    Meta ·meta-llama/llama-4-maverick

    $0.188/M in · $0.652/M out

    1M ctx

    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 parameters per forward...

  • Llama 4 Scout

    Meta ·meta-llama/llama-4-scout

    $0.100/M in · $0.300/M out

    1.3M ctx

    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 multimodal input...

  • Llama Guard 4 12B

    Meta ·meta-llama/llama-guard-4-12b

    $0.180/M in · $0.180/M out

    164K ctx

    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 in both LLM...

  • LongCat 2.0

    Meituan ·meituan/longcat-2.0

    $0.300/M in · $1.20/M out

    1M ctx

    LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total. It is suited for coding, repository-level changes, long-horizon problem solving, and agentic...

  • Lyria 3 Clip Preview

    Google ·google/lyria-3-clip-preview

    Free

    1M ctx

    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...

  • Lyria 3 Pro Preview

    Google ·google/lyria-3-pro-preview

    Free

    1M ctx

    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, 48kHz...

  • Magnum v4 72B

    Anthracite Org ·anthracite-org/magnum-v4-72b

    $2.50/M in · $5.00/M out

    33K ctx

    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://openrouter.ai/anthropic/claude-3-opus). The model is fine-tuned on top of [Qwen2.5 72B](https://openrouter.ai/qwen/qwen-2.5-72b-instruct).

  • Mercury 2

    Inception ·inception/mercury-2

    $0.250/M in · $0.750/M out

    128K ctx

    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 tokens in parallel, achieving...

  • Mercury 2.5

    Inception ·inception/mercury-2.5

    $0.040/M in · $0.150/M out

    260K ctx

    Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, Mercury 2.5 produces and refines multiple tokens in parallel, achieving...

  • MiMo-V2.5

    Xiaomi ·xiaomi/mimo-v2.5

    $0.140/M in · $0.280/M out

    1.1M ctx

    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 perception across image and video understanding...

  • MiMo-V2.5-Pro

    Xiaomi ·xiaomi/mimo-v2.5-pro

    $0.435/M in · $0.870/M out

    1.1M ctx

    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 benchmarks such as ClawEval, GDPVal, and SWE-bench Pro....

  • MiMo-V2.6-Flash

    Xiaomi ·xiaomi/mimo-v2.6-flash

    $0.140/M in · $0.280/M out

    1.1M ctx

    MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employs a hybrid attention mechanism for...

  • MiMo-V2.6-Pro

    Xiaomi ·xiaomi/mimo-v2.6-pro

    $0.435/M in · $0.870/M out

    1.1M ctx

    MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi. Built at a scale of over 1T parameters, it is designed to push the ceiling of capability for the most demanding...

  • MiMo-V2.6-Pro-UltraSpeed

    Xiaomi ·xiaomi/mimo-v2.6-pro-ultraspeed

    $4.35/M in · $8.70/M out

    1M ctx

    MiMo-V2.6-Pro-UltraSpeed is the fast speed edition of Xiaomi's flagship foundation model, MiMo-V2.6-Pro. Built from the same 1T MiMo-V2.6-Pro checkpoint, it matches the original model in quality while delivering roughly 10x...

  • MiniMax M1

    MiniMax ·minimax/minimax-m1

    $0.550/M in · $2.20/M out

    1M ctx

    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 paired with a custom "lightning attention" mechanism, allowing it...

  • MiniMax M2

    MiniMax ·minimax/minimax-m2

    $0.300/M in · $1.20/M out

    205K ctx

    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 delivers near-frontier intelligence across general reasoning,...

  • MiniMax M2-her

    MiniMax ·minimax/minimax-m2-her

    $0.300/M in · $1.20/M out

    66K ctx

    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 tone and personality, it supports rich message...

  • MiniMax M2.1

    MiniMax ·minimax/minimax-m2.1

    $0.300/M in · $1.20/M out

    205K ctx

    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 parameters, it delivers a major jump in real-world...

  • MiniMax M2.5

    MiniMax ·minimax/minimax-m2.5

    $0.270/M in · $1.08/M out

    205K ctx

    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 the coding expertise of M2.1...

  • MiniMax M2.7

    MiniMax ·minimax/minimax-m2.7

    $0.210/M in · $0.840/M out

    205K ctx

    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 evolution, M2.7 integrates advanced agentic capabilities through multi-agent...

  • MiniMax M3

    MiniMax ·minimax/minimax-m3

    4.0 ★ · 1 rating

    $0.300/M in · $1.20/M out

    1M ctx

    MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...

  • MiniMax-01

    MiniMax ·minimax/minimax-01

    $0.200/M in · $1.10/M out

    1M ctx

    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 inference, and can handle a context...

  • Ministral 3 14B 2512

    Mistral ·mistralai/ministral-14b-2512

    $0.200/M in · $0.200/M out

    262K ctx

    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 efficient language...

  • Ministral 3 3B 2512

    Mistral ·mistralai/ministral-3b-2512

    $0.100/M in · $0.100/M out

    131K ctx

    The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.

  • Ministral 3 8B 2512

    Mistral ·mistralai/ministral-8b-2512

    $0.150/M in · $0.150/M out

    262K ctx

    A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.

  • Ministral 3 8B 2512 (batch)

    Mistral ·mistralai/ministral-8b-2512:batch

    $0.075/M in · $0.075/M out

    262K ctx

    A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.

  • Mistral Large

    Mistralai ·mistralai/mistral-large

    $2.00/M in · $6.00/M out

    128K ctx

    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. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/)....

  • Mistral Large 2407

    Mistralai ·mistralai/mistral-large-2407

    $2.00/M in · $6.00/M out

    131K ctx

    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. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/)....

  • Mistral Large 3 2512

    Mistral ·mistralai/mistral-large-2512

    $0.500/M in · $1.50/M out

    262K ctx

    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 Apache 2.0 license.

  • Mistral Large 3 2512 (batch)

    Mistral ·mistralai/mistral-large-2512:batch

    $0.250/M in · $0.750/M out

    262K ctx

    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 Apache 2.0 license.

  • Mistral Medium 3

    Mistral ·mistralai/mistral-medium-3

    $0.400/M in · $2.00/M out

    131K ctx

    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-of-the-art reasoning and multimodal performance with 8× lower cost...

  • Mistral Medium 3.1

    Mistral ·mistralai/mistral-medium-3.1

    $0.400/M in · $2.00/M out

    131K ctx

    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 significantly reduced operational cost. It balances...

  • Mistral Medium 3.1 (batch)

    Mistral ·mistralai/mistral-medium-3.1:batch

    $0.200/M in · $1.00/M out

    131K ctx

    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 significantly reduced operational cost. It balances...

  • Mistral Medium 3.5

    Mistral ·mistralai/mistral-medium-3-5

    $1.50/M in · $7.50/M out

    262K ctx

    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, and complex...

  • Mistral Medium 3.5 (batch)

    Mistral ·mistralai/mistral-medium-3-5:batch

    $0.750/M in · $3.75/M out

    262K ctx

    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, and complex...

  • Mistral Nemo

    Mistral ·mistralai/mistral-nemo

    $0.019/M in · $0.030/M out

    131K ctx

    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, Italian, Portuguese, Chinese, Japanese,...

  • Mistral Small 3

    Mistral ·mistralai/mistral-small-24b-instruct-2501

    $0.050/M in · $0.080/M out

    33K ctx

    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 and instruction-tuned versions designed...

  • Mistral Small 3.1 24B

    Mistral ·mistralai/mistral-small-3.1-24b-instruct

    $0.351/M in · $0.555/M out

    128K ctx

    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 performance in text-based reasoning and...

  • Mistral Small 3.2 24B

    Mistral ·mistralai/mistral-small-3.2-24b-instruct

    $0.094/M in · $0.250/M out

    256K ctx

    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. Compared to the 3.1 release, version 3.2 significantly improves accuracy on...

  • Mistral Small 4

    Mistral ·mistralai/mistral-small-2603

    $0.150/M in · $0.600/M out

    262K ctx

    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 reasoning from...

  • Mistral Small 4 (batch)

    Mistral ·mistralai/mistral-small-2603:batch

    $0.075/M in · $0.300/M out

    262K ctx

    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 reasoning from...

  • Mixtral 8x22B Instruct

    Mistral ·mistralai/mixtral-8x22b-instruct

    $2.00/M in · $6.00/M out

    66K ctx

    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 for its size. Its strengths include: - strong math, coding,...

  • Morph V3 Fast

    Morph ·morph/morph-v3-fast

    $0.800/M in · $1.20/M out

    82K ctx

    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: <instruction>{instruction}</instruction> <code>{initial_code}</code> <update>{edit_snippet}</update>...

  • Morph V3 Large

    Morph ·morph/morph-v3-large

    $0.900/M in · $1.90/M out

    262K ctx

    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 format: <instruction>{instruction}</instruction> <code>{initial_code}</code>...

  • Muse Glimmer 30B

    Meta ·meta/muse-glimmer-30b

    $0.350/M in · $1.50/M out

    131K ctx

    Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon...

  • Muse Spark 1.1

    Meta ·meta/muse-spark-1.1

    $1.25/M in · $4.25/M out

    1M ctx

    Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, and PDF documents and returns text, with a 1M-token context window....

  • Muse Spark 1.2

    Meta ·meta/muse-spark-1.2

    $1.25/M in · $4.25/M out

    1M ctx

    Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, and PDF documents, returns text, and offers a 1M-token context window....

  • Muse Spark 1.2 Contributor

    Meta ·meta/muse-spark-1.2-contributor

    $0.100/M in · $0.200/M out

    1M ctx

    Muse Spark 1.2 contributor tier is a reasoning model from Meta designed for developers who want to start building at an even lower cost. It’s meaningfully cheaper than Muse Spark...

  • Muse Spark 1.3

    Meta ·meta/muse-spark-1.3

    $1.25/M in · $4.25/M out

    1M ctx

    Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It is designed to keep track of information across extended tasks, work through...

  • Muse Spark 1.3 Contributor

    Meta ·meta/muse-spark-1.3-contributor

    $0.100/M in · $0.200/M out

    1M ctx

    Muse Spark 1.3 Contributor is the cost-efficient contributor tier of Meta’s multimodal reasoning model for experimentation, learning, and early-stage agentic, multi-agent, and coding workflows. It is designed to track information...

  • MythoMax 13B

    Gryphe ·gryphe/mythomax-l2-13b

    $0.080/M in · $0.110/M out

    8K ctx

    One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay. #merge

  • Nano Banana (Gemini 2.5 Flash Image)

    Google ·google/gemini-2.5-flash-image

    $0.300/M in · $2.50/M out

    33K ctx

    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 generation,...

  • Nano Banana 2 (Gemini 3.1 Flash Image Preview)

    Google ·google/gemini-3.1-flash-image-preview

    $0.500/M in · $3.00/M out

    66K ctx

    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. It combines...

  • Nano Banana 2 (Gemini 3.1 Flash Image)

    Google ·google/gemini-3.1-flash-image

    $0.500/M in · $3.00/M out

    131K ctx

    Gemini 3.1 Flash Image, 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. It combines advanced...

  • Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)

    Google ·google/gemini-3.1-flash-lite-image

    $0.250/M in · $1.50/M out

    66K ctx

    Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual exploration. It delivers text-to-image generation...

  • Nano Banana Pro (Gemini 3 Pro Image Preview)

    Google ·google/gemini-3-pro-image-preview

    $2.00/M in · $12.00/M out

    66K ctx

    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 reasoning, real-world grounding, and...

  • Nano Banana Pro (Gemini 3 Pro Image)

    Google ·google/gemini-3-pro-image

    $2.00/M in · $12.00/M out

    131K ctx

    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 reasoning, real-world grounding, and...

  • Nemotron 3 Nano 30B A3B

    NVIDIA ·nvidia/nemotron-3-nano-30b-a3b

    $0.050/M in · $0.200/M out

    262K ctx

    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...

  • Nemotron 3 Nano Omni (free)

    NVIDIA ·nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free

    Free

    256K ctx

    NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and...

  • Nemotron 3 Super

    NVIDIA ·nvidia/nemotron-3-super-120b-a12b

    $0.080/M in · $0.450/M out

    262K ctx

    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. Built on a hybrid Mamba-Transformer...

  • Nemotron 3 Super (free)

    NVIDIA ·nvidia/nemotron-3-super-120b-a12b:free

    Free

    262K ctx

    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. Built on a hybrid Mamba-Transformer...

  • Nemotron 3 Ultra

    NVIDIA ·nvidia/nemotron-3-ultra-550b-a55b

    $0.500/M in · $2.20/M out

    262K ctx

    NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...

  • Nemotron 3 Ultra (free)

    NVIDIA ·nvidia/nemotron-3-ultra-550b-a55b:free

    5.0 ★ · 1 rating

    Free

    1M ctx

    NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...

  • Nemotron 3.5 Content Safety

    NVIDIA ·nvidia/nemotron-3.5-content-safety

    $0.200/M in · $0.200/M out

    131K ctx

    NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...

  • Nemotron 3.5 Content Safety (free)

    NVIDIA ·nvidia/nemotron-3.5-content-safety:free

    Free

    128K ctx

    NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...

  • Nemotron 3.5 Lightning

    NVIDIA ·nvidia/nemotron-3.5-lightning

    $0.060/M in · $0.160/M out

    262K ctx

    NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...

  • Nemotron 3.5 Lightning (free)

    NVIDIA ·nvidia/nemotron-3.5-lightning:free

    Free

    1M ctx

    NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...

  • Nex-N2.5-Mini

    Nex AGI ·nex-agi/nex-n2.5-mini

    $0.025/M in · $0.100/M out

    262K ctx

    Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file...

  • Nex-N2.5-Pro

    Nex AGI ·nex-agi/nex-n2.5-pro

    $0.075/M in · $0.250/M out

    262K ctx

    Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file...

  • North Mini Code (free)

    Cohere ·cohere/north-mini-code:free

    Free

    256K ctx

    North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized...

  • Nova 2 Lite

    Amazon ·amazon/nova-2-lite-v1

    $0.300/M in · $2.50/M out

    1M ctx

    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 capabilities in processing...

  • Nova Lite 1.0

    Amazon ·amazon/nova-lite-v1

    $0.060/M in · $0.240/M out

    300K ctx

    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...

  • Nova Micro 1.0

    Amazon ·amazon/nova-micro-v1

    $0.035/M in · $0.140/M out

    128K ctx

    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...

  • Nova Premier 1.0

    Amazon ·amazon/nova-premier-v1

    $2.50/M in · $12.50/M out

    1M ctx

    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.

  • Nova Pro 1.0

    Amazon ·amazon/nova-pro-v1

    $0.800/M in · $3.20/M out

    300K ctx

    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...

  • o1

    OpenAI ·openai/o1

    $15.00/M in · $60.00/M out

    200K ctx

    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 learning to reason...

  • o1-pro

    OpenAI ·openai/o1-pro

    $150.00/M in · $600.00/M out

    200K ctx

    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 provide...

  • o3

    OpenAI ·openai/o3

    $2.00/M in · $8.00/M out

    200K ctx

    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 instruction-following....

  • o3 (batch)

    OpenAI ·openai/o3:batch

    $1.00/M in · $4.00/M out

    200K ctx

    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 instruction-following....

  • o3 Mini

    OpenAI ·openai/o3-mini

    $1.10/M in · $4.40/M out

    200K ctx

    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_effort` parameter, which can be set to...

  • o3 Mini (batch)

    OpenAI ·openai/o3-mini:batch

    $0.550/M in · $2.20/M out

    200K ctx

    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_effort` parameter, which can be set to...

  • o3 Mini High

    OpenAI ·openai/o3-mini-high

    $1.10/M in · $4.40/M out

    200K ctx

    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, particularly excelling in science, mathematics, and...

  • o3 Pro

    OpenAI ·openai/o3-pro

    $20.00/M in · $80.00/M out

    200K ctx

    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 provide consistently...

  • o4 Mini

    OpenAI ·openai/o4-mini

    $1.10/M in · $4.40/M out

    200K ctx

    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 tool use and demonstrates competitive reasoning...

  • o4 Mini (batch)

    OpenAI ·openai/o4-mini:batch

    $0.550/M in · $2.20/M out

    200K ctx

    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 tool use and demonstrates competitive reasoning...

  • o4 Mini High

    OpenAI ·openai/o4-mini-high

    $1.10/M in · $4.40/M out

    200K ctx

    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 fast, cost-efficient performance while retaining...

  • Palmyra X5

    Writer ·writer/palmyra-x5

    $0.600/M in · $6.00/M out

    1M ctx

    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 windows up to 1 million...

  • Pareto

    Unbiased ·unbiased/pareto

    $2.50/M in · $7.50/M out

    262K ctx

    Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.

  • Pareto 26.10 Preview

    Unbiased ·unbiased/pareto-26.10-preview

    $0.800/M in · $3.20/M out

    1M ctx

    Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks. This is a preview of the...

  • Pareto Code Router

    Openrouter ·openrouter/pareto-code

    2M ctx

    The Pareto Router maintains a tiered shortlist of strong coding models, ranked by [Artificial Analysis](https://artificialanalysis.ai/) coding percentiles. Set min_coding_score between 0 and 1 on the [pareto-router plugin](https://openrouter.ai/docs/guides/routing/routers/pareto-router#the-min_coding_score-parameter) to control how...

  • Perceptron Mk1

    Perceptron ·perceptron/perceptron-mk1

    $0.150/M in · $1.50/M out

    33K ctx

    Perceptron Mk1 (Mark One) is Perceptron's highest-quality vision-language model for video and embodied reasoning.** It accepts image and video inputs paired with natural language queries, and produces detailed visual understanding...

  • Perceptron Mk1.5

    Perceptron ·perceptron/perceptron-mk1.5

    $0.150/M in · $1.50/M out

    37K ctx

    Perceptron Mk1.5 is Perceptron's embodied reasoning model for physical agents. It accepts text, image, video, and audio input, and answers with text plus optional structured annotations: points, boxes, polygons, tracks,...

  • Phi 4

    Microsoft ·microsoft/phi-4

    $0.070/M in · $0.140/M out

    16K ctx

    [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 are needed. At 14 billion...

  • Qwen Plus 0728

    Qwen ·qwen/qwen-plus-2025-07-28

    $0.260/M in · $0.780/M out

    1M ctx

    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-Plus

    Qwen ·qwen/qwen-plus

    $0.260/M in · $0.780/M out

    1M ctx

    Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination.

  • Qwen2.5 72B Instruct

    Qwen ·qwen/qwen-2.5-72b-instruct

    $0.360/M in · $0.400/M out

    33K ctx

    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 capabilities in coding and...

  • Qwen2.5 7B Instruct

    Qwen ·qwen/qwen-2.5-7b-instruct

    $0.100/M in · $0.200/M out

    33K ctx

    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 capabilities in coding and...

  • Qwen2.5 Coder 32B Instruct

    Qwen ·qwen/qwen-2.5-coder-32b-instruct

    $0.660/M in · $1.00/M out

    33K ctx

    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: - Significantly improvements in **code generation**, **code reasoning**...

  • Qwen2.5 VL 72B Instruct

    Qwen ·qwen/qwen2.5-vl-72b-instruct

    $0.800/M in · $1.00/M out

    128K ctx

    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 within images.

  • Qwen3 14B

    Qwen ·qwen/qwen3-14b

    $0.120/M in · $0.240/M out

    131K ctx

    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 a "thinking" mode for...

  • Qwen3 235B A22B

    Qwen ·qwen/qwen3-235b-a22b

    $0.455/M in · $1.82/M out

    131K ctx

    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" mode for complex reasoning, math, and...

  • Qwen3 235B A22B Instruct 2507

    Qwen ·qwen/qwen3-235b-a22b-2507

    $0.087/M in · $0.350/M out

    262K ctx

    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 pass. It is optimized for general-purpose text generation, including instruction following,...

  • Qwen3 235B A22B Thinking 2507

    Qwen ·qwen/qwen3-235b-a22b-thinking-2507

    $0.230/M in · $2.30/M out

    131K ctx

    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 parameters per forward pass and natively supports up to 262,144...

  • Qwen3 30B A3B

    Qwen ·qwen/qwen3-30b-a3b

    $0.120/M in · $0.500/M out

    131K ctx

    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, and advanced agent tasks. Its unique...

  • Qwen3 30B A3B Instruct 2507

    Qwen ·qwen/qwen3-30b-a3b-instruct-2507

    $0.100/M in · $0.300/M out

    262K ctx

    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 designed for high-quality instruction following, multilingual understanding, and...

  • Qwen3 30B A3B Thinking 2507

    Qwen ·qwen/qwen3-30b-a3b-thinking-2507

    $0.200/M in · $2.40/M out

    82K ctx

    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 specifically for “thinking mode,” where internal reasoning traces are separated...

  • Qwen3 32B

    Qwen ·qwen/qwen3-32b

    $0.080/M in · $0.280/M out

    131K ctx

    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 between a "thinking" mode for...

  • Qwen3 8B

    Qwen ·qwen/qwen3-8b

    $0.117/M in · $0.455/M out

    131K ctx

    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 between "thinking" mode for math,...

  • Qwen3 Coder 30B A3B Instruct

    Qwen ·qwen/qwen3-coder-30b-a3b-instruct

    $0.070/M in · $0.280/M out

    262K ctx

    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-scale understanding, and agentic tool use. Built on the...

  • Qwen3 Coder 480B A35B

    Qwen ·qwen/qwen3-coder

    $0.300/M in · $1.00/M out

    262K ctx

    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, tool use, and long-context reasoning over...

  • Qwen3 Coder Flash

    Qwen ·qwen/qwen3-coder-flash

    $0.195/M in · $0.975/M out

    1M ctx

    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 tool calling...

  • Qwen3 Coder Next

    Qwen ·qwen/qwen3-coder-next

    $0.120/M in · $0.800/M out

    262K ctx

    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 3B activated per...

  • Qwen3 Coder Plus

    Qwen ·qwen/qwen3-coder-plus

    $0.650/M in · $3.25/M out

    1M ctx

    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 calling and...

  • Qwen3 Max

    Qwen ·qwen/qwen3-max

    $0.780/M in · $3.90/M out

    262K ctx

    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 compared to the January 2025 version. It...

  • Qwen3 Max Thinking

    Qwen ·qwen/qwen3-max-thinking

    $0.780/M in · $3.90/M out

    262K ctx

    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 model capacity and reinforcement learning compute, it...

  • Qwen3 Next 80B A3B Instruct

    Qwen ·qwen/qwen3-next-80b-a3b-instruct

    $0.100/M in · $1.10/M out

    262K ctx

    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 across reasoning, code generation, knowledge QA, and multilingual...

  • Qwen3 Next 80B A3B Thinking

    Qwen ·qwen/qwen3-next-80b-a3b-thinking

    $0.150/M in · $1.20/M out

    262K ctx

    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; math proofs, code synthesis/debugging, logic, and agentic...

  • Qwen3 VL 235B A22B Instruct

    Qwen ·qwen/qwen3-vl-235b-a22b-instruct

    $0.210/M in · $1.90/M out

    262K ctx

    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 general vision-language use (VQA, document parsing, chart/table...

  • Qwen3 VL 235B A22B Thinking

    Qwen ·qwen/qwen3-vl-235b-a22b-thinking

    $0.400/M in · $4.00/M out

    131K ctx

    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 multimodal reasoning in STEM and math....

  • Qwen3 VL 30B A3B Instruct

    Qwen ·qwen/qwen3-vl-30b-a3b-instruct

    $0.150/M in · $0.600/M out

    262K ctx

    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-following for general multimodal tasks. It excels in perception...

  • Qwen3 VL 30B A3B Thinking

    Qwen ·qwen/qwen3-vl-30b-a3b-thinking

    $0.200/M in · $2.40/M out

    262K ctx

    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, math, and complex tasks. It excels...

  • Qwen3 VL 32B Instruct

    Qwen ·qwen/qwen3-vl-32b-instruct

    $0.104/M in · $0.416/M out

    131K ctx

    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 parameters, it combines deep visual perception with advanced text...

  • Qwen3 VL 8B Instruct

    Qwen ·qwen/qwen3-vl-8b-instruct

    $0.117/M in · $0.455/M out

    262K ctx

    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 improved multimodal fusion with Interleaved-MRoPE for long-horizon...

  • Qwen3 VL 8B Thinking

    Qwen ·qwen/qwen3-vl-8b-thinking

    $0.180/M in · $2.10/M out

    131K ctx

    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, and temporal sequences. It integrates enhanced multimodal alignment and...

  • Qwen3.5 397B A17B

    Qwen ·qwen/qwen3.5-397b-a17b

    $0.550/M in · $3.50/M out

    262K ctx

    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, achieving higher inference efficiency. It delivers...

  • Qwen3.5 Plus 2026-02-15

    Qwen ·qwen/qwen3.5-plus-02-15

    $0.260/M in · $1.56/M out

    1M ctx

    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, achieving higher inference efficiency. In a variety of...

  • Qwen3.5 Plus 2026-04-20

    Qwen ·qwen/qwen3.5-plus-20260420

    $0.300/M in · $1.80/M out

    1M ctx

    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. This...

  • Qwen3.5-122B-A10B

    Qwen ·qwen/qwen3.5-122b-a10b

    $0.260/M in · $2.08/M out

    262K ctx

    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 higher inference efficiency. In terms of...

  • Qwen3.5-27B

    Qwen ·qwen/qwen3.5-27b

    $0.195/M in · $1.56/M out

    262K ctx

    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 overall capabilities are comparable to those of...

  • Qwen3.5-35B-A3B

    Qwen ·qwen/qwen3.5-35b-a3b

    $0.150/M in · $1.00/M out

    262K ctx

    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, achieving higher inference efficiency. Its overall...

  • Qwen3.5-9B

    Qwen ·qwen/qwen3.5-9b

    $0.100/M in · $0.150/M out

    262K ctx

    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 architecture. It uses a unified vision-language design...

  • Qwen3.5-Flash

    Qwen ·qwen/qwen3.5-flash-02-23

    $0.065/M in · $0.260/M out

    1M ctx

    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 higher inference efficiency. Compared to the...

  • Qwen3.6 27B

    Qwen ·qwen/qwen3.6-27b

    $0.320/M in · $3.20/M out

    262K ctx

    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, and video inputs...

  • Qwen3.6 35B A3B

    Qwen ·qwen/qwen3.6-35b-a3b

    $0.150/M in · $1.00/M out

    262K ctx

    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-experts architecture combining Gated...

  • Qwen3.6 Flash

    Qwen ·qwen/qwen3.6-flash

    $0.188/M in · $1.13/M out

    1M ctx

    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...

  • Qwen3.6 Max Preview

    Qwen ·qwen/qwen3.6-max-preview

    $1.03/M in · $6.16/M out

    262K ctx

    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 optimized for agentic coding, tool use, and...

  • Qwen3.6 Plus

    Qwen ·qwen/qwen3.6-plus

    $0.325/M in · $1.95/M out

    1M ctx

    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 inference. Compared to the 3.5 series, it delivers...

  • Qwen3.7 Flash

    Qwen ·qwen/qwen3.7-flash

    $0.030/M in · $0.130/M out

    1M ctx

    Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world...

  • Qwen3.7 Max

    Qwen ·qwen/qwen3.7-max

    $1.48/M in · $4.42/M out

    1M ctx

    Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks,...

  • Qwen3.7 Plus

    Qwen ·qwen/qwen3.7-plus

    $0.320/M in · $1.28/M out

    1M ctx

    Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its...

  • Qwen3.8 2.4T A95B

    Qwen ·qwen/qwen3.8-2.4t-a95b

    $2.00/M in · $6.00/M out

    1M ctx

    Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is...

  • Qwen3.8 27B

    Qwen ·qwen/qwen3.8-27b

    $0.420/M in · $3.00/M out

    1M ctx

    Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...

  • Qwen3.8 27B (free)

    Qwen ·qwen/qwen3.8-27b:free

    Free

    262K ctx

    Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...

  • Qwen3.8 Flash

    Qwen ·qwen/qwen3.8-flash

    $0.150/M in · $0.470/M out

    1M ctx

    Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart analysis, and long-video analysis.

  • Qwen3.8 Max (0902)

    Qwen ·qwen/qwen3.8-max-0902

    $2.00/M in · $6.00/M out

    1M ctx

    Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. It is a 2.4-trillion-parameter mixture-of-experts model that accepts text, image, and video input and returns text,...

  • Qwen3.8 Max Prime

    Qwen ·qwen/qwen3.8-max-prime

    $4.00/M in · $12.00/M out

    1M ctx

    Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba's Qwen team, served as a separate SKU at a higher price point. It accepts text, image, and video...

  • Qwen3.8 Omni Flash

    Qwen ·qwen/qwen3.8-omni-flash

    $0.150/M in · $0.470/M out

    1M ctx

    Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding. It is suited for audio-video analysis and summarization,...

  • R1

    DeepSeek ·deepseek/deepseek-r1

    $0.700/M in · $2.50/M out

    64K ctx

    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 inference pass....

  • R1 0528

    DeepSeek ·deepseek/deepseek-r1-0528

    $0.500/M in · $2.15/M out

    164K ctx

    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 671B parameters in size, with 37B active...

  • Reka Edge

    Rekaai ·rekaai/reka-edge

    $0.100/M in · $0.100/M out

    16K ctx

    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 deliver industry-leading performance in image understanding,...

  • Reka Flash 3

    Rekaai ·rekaai/reka-flash-3

    $0.100/M in · $0.200/M out

    66K ctx

    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-following, and function calling. Featuring a...

  • Relace Apply 3

    Relace ·relace/relace-apply-3

    $0.850/M in · $1.25/M out

    256K ctx

    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 files at...

  • Relace Search

    Relace ·relace/relace-search

    $1.00/M in · $3.00/M out

    256K ctx

    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 performs agentic...

  • ReMM SLERP 13B

    Undi95 ·undi95/remm-slerp-l2-13b

    $0.350/M in · $0.650/M out

    6K ctx

    A recreation trial of the original MythoMax-L2-B13 but with updated models. #merge

  • Saba

    Mistral ·mistralai/mistral-saba

    $0.200/M in · $0.600/M out

    33K ctx

    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 efficient performance. Trained on curated regional...

  • Sakana Namazu

    Sakana ·sakana/sakana-namazu

    $0.950/M in · $4.00/M out

    262K ctx

    Sakana Namazu is a Japanese-specialized reasoning model from Sakana AI, based on Kimi K2.6 with additional training for Japanese language and business contexts. It is suited for Japanese instruction following,...

  • Schematron V2 Small

    Inference.net ·inference-net/schematron-v2-small

    $0.050/M in · $0.230/M out

    128K ctx

    Schematron V2 Small is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes extraction quality for complex schemas and long pages. Extraction instructions must be supplied through a JSON schema...

  • Schematron V2 Turbo

    Inference.net ·inference-net/schematron-v2-turbo

    $0.030/M in · $0.150/M out

    128K ctx

    Schematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes throughput for high-volume extraction workloads. Extraction instructions must be supplied through a JSON schema in response_format rather...

  • Seed 1.6

    ByteDance Seed ·bytedance-seed/seed-1.6

    $0.250/M in · $2.00/M out

    262K ctx

    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.

  • Seed 1.6 Flash

    ByteDance Seed ·bytedance-seed/seed-1.6-flash

    $0.075/M in · $0.300/M out

    262K ctx

    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 outputs of...

  • Seed 2.1 Turbo

    ByteDance Seed ·bytedance-seed/seed-2-1-turbo

    $0.500/M in · $2.50/M out

    262K ctx

    Seed 2.1 Turbo is a multimodal model from ByteDance Seed for coding and long-horizon agent workflows. It is suited for end-to-end software delivery, multi-step task execution, and understanding visual and...

  • Seed-2.0-Code

    ByteDance Seed ·bytedance-seed/seed-2.0-code

    $0.500/M in · $3.00/M out

    262K ctx

    Seed 2.0 Code is a model from ByteDance Seed optimized for agentic coding. It is suited for frontend development, multilingual programming tasks, and coding-agent workflows in tools such as Claude...

  • Seed-2.0-Lite

    ByteDance Seed ·bytedance-seed/seed-2.0-lite

    $0.250/M in · $2.00/M out

    262K ctx

    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 practical default choice for most production workloads across...

  • Seed-2.0-Mini

    ByteDance Seed ·bytedance-seed/seed-2.0-mini

    $0.100/M in · $0.400/M out

    262K ctx

    Seed-2.0-mini targets latency-sensitive, high-concurrency, and cost-sensitive scenarios, emphasizing fast response and flexible inference deployment. It delivers performance comparable to ByteDance-Seed-1.6, supports 256k context, four reasoning effort modes (minimal/low/medium/high), multimodal understanding,...

  • Skyfall 36B V2

    TheDrummer ·thedrummer/skyfall-36b-v2

    $0.550/M in · $0.800/M out

    33K ctx

    Skyfall 36B v2 is an enhanced iteration of Mistral Small 2501, specifically fine-tuned for improved creativity, nuanced writing, role-playing, and coherent storytelling.

  • Solar Mini 4

    Upstage ·upstage/solar-mini4

    $0.050/M in · $0.200/M out

    524K ctx

    Solar Mini 4 is Upstage's compact, cost-efficient language model, a 35B-parameter mixture-of-experts with 3B active parameters and a 524K context window. It is built for agentic use cases where response...

  • Solar Pro 3

    Upstage ·upstage/solar-pro-3

    $0.150/M in · $0.600/M out

    131K ctx

    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 performance while maintaining computational efficiency. Optimized...

  • Solar Pro 4

    Upstage ·upstage/solar-pro4

    $0.090/M in · $0.360/M out

    524K ctx

    Solar Pro 4 is Upstage's cost-efficient large language model, featuring a 524K context window. It is built for long-horizon tasks and agentic workflows, with strong capabilities in office productivity, document-intensive...

  • Sonar

    Perplexity ·perplexity/sonar

    $1.00/M in · $1.00/M out

    127K ctx

    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 lightweight question-and-answer features...

  • Sonar Deep Research

    Perplexity ·perplexity/sonar-deep-research

    $2.00/M in · $8.00/M out

    128K ctx

    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 sources, refining its approach as it gathers...

  • Sonar Pro

    Perplexity ·perplexity/sonar-pro

    $3.00/M in · $15.00/M out

    200K ctx

    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-sonar-pro) For enterprises seeking more advanced capabilities, the Sonar Pro API can handle in-depth, multi-step queries with added extensibility, like...

  • Sonar Pro Search

    Perplexity ·perplexity/sonar-pro-search

    $3.00/M in · $15.00/M out

    200K ctx

    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. Pricing is based...

  • Sonar Reasoning Pro

    Perplexity ·perplexity/sonar-reasoning-pro

    $2.00/M in · $8.00/M out

    128K ctx

    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-sonar-pro) Sonar Reasoning Pro is a premier reasoning model powered by DeepSeek R1 with Chain of Thought (CoT). Designed for...

  • Space Bunny Alpha

    Stealth ·stealth/space-bunny-alpha

    Free

    1M ctx

    Space Bunny Alpha is an anonymous large model with blazing-fast inference, strong coding capabilities and native multimodal input support. It delivers adjustable reasoning effort, and a 1M-token context window. Space...

  • Step 3.5 Flash

    StepFun ·stepfun/step-3.5-flash

    $0.100/M in · $0.300/M out

    262K ctx

    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 parameters per token....

  • Step 3.7 Flash

    StepFun ·stepfun/step-3.7-flash

    $0.200/M in · $1.15/M out

    262K ctx

    Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...

  • Ternary Bonsai 2 27B

    PrismML ·prism-ml/ternary-bonsai-2-27b

    $0.075/M in · $0.500/M out

    262K ctx

    Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports coding, mathematics, tool calling, and image understanding with a 262K-token context window. Ternary compression shrinks...

  • Trinity Large Thinking

    Arcee AI ·arcee-ai/trinity-large-thinking

    $0.250/M in · $0.800/M out

    262K ctx

    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. Launch video: https://youtu.be/Gc82AXLa0Rg?si=4RLn6WBz33qT--B7...

  • UI-TARS 7B

    ByteDance ·bytedance/ui-tars-1.5-7b

    $0.100/M in · $0.200/M out

    128K ctx

    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, it builds upon the UI-TARS framework with reinforcement...

  • Uncensored

    Venice ·cognitivecomputations/dolphin-mistral-24b-venice-edition

    $0.200/M in · $0.900/M out

    128K ctx

    Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an “uncensored” instruct-tuned LLM, preserving...

  • UnslopNemo 12B

    TheDrummer ·thedrummer/unslopnemo-12b

    $0.400/M in · $0.400/M out

    1M ctx

    UnslopNemo v4.1 is the latest addition from the creator of Rocinante, designed for adventure writing and role-play scenarios.

  • Voxtral Small 24B 2507

    Mistral ·mistralai/voxtral-small-24b-2507

    $0.100/M in · $0.300/M out

    33K ctx

    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 transcription, translation and audio understanding. Input audio...

  • Weaver (alpha)

    Mancer ·mancer/weaver

    $0.400/M in · $0.750/M out

    8K ctx

    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.

  • WizardLM-2 8x22B

    Microsoft ·microsoft/wizardlm-2-8x22b

    $0.620/M in · $0.620/M out

    66K ctx

    WizardLM-2 8x22B is Microsoft AI's most advanced Wizard model. It demonstrates highly competitive performance compared to leading proprietary models, and it consistently outperforms all existing state-of-the-art opensource models. It is...