Models

Claude Sonnet 4.6

Max Output

128K

$3.00/M input

$15.00/M output

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 Opus 4.7

Max Output

128K

$5.00/M input

$25.00/M output

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 4.6

Max Output

128K

$5.00/M input

$25.00/M output

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 Haiku 4.5Free

Free input

Free output

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...

OpenAI: GPT-5

$1.25/M input

$10.00/M output

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...

OpenAI: GPT-5 Mini

$0.250/M input

$2.00/M output

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....

OpenAI: GPT-4o-miniFree

Free input

Free output

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...

OpenAI: o1-pro

$150.00/M input

$600.00/M output

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...

Gemini 3.1 Pro Preview

Max Output

66K

$2.00/M input

$12.00/M output

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 2.5 Pro

Max Output

66K

$1.25/M input

$10.00/M output

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 Flash

Max Output

66K

$0.300/M input

$2.50/M output

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...

DeepSeek: DeepSeek V3Free

Free input

Free output

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...

OpenAI: GPT Audio

$2.50/M input

$10.00/M output

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...

OpenAI: GPT Audio Mini

$0.600/M input

$2.40/M output

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...

OpenAI: GPT Chat Latest

$5.00/M input

$30.00/M output

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...

OpenAI: GPT-3.5 Turbo

$0.500/M input

$1.50/M output

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.

OpenAI: GPT-3.5 Turbo (older v0613)

$1.00/M input

$2.00/M output

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.

OpenAI: GPT-3.5 Turbo 16k

$3.00/M input

$4.00/M output

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...

OpenAI: GPT-3.5 Turbo Instruct

$1.50/M input

$2.00/M output

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.

OpenAI: GPT-4

$30.00/M input

$60.00/M output

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...

OpenAI: GPT-4 Turbo

$10.00/M input

$30.00/M output

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.

OpenAI: GPT-4 Turbo Preview

$10.00/M input

$30.00/M output

The preview GPT-4 model with improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more. Training data: up to Dec 2023. **Note:** heavily rate limited by OpenAI while...

OpenAI: GPT-4.1

$2.00/M input

$8.00/M output

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...

OpenAI: GPT-4.1 Mini

$0.400/M input

$1.60/M output

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...

OpenAI: GPT-4.1 Nano

$0.100/M input

$0.400/M output

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...

OpenAI: GPT-4o

$2.50/M input

$10.00/M output

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...

OpenAI: GPT-4o Search Preview

$2.50/M input

$10.00/M output

GPT-4o Search Previewis a specialized model for web search in Chat Completions. It is trained to understand and execute web search queries.

OpenAI: GPT-4o-mini Search Preview

$0.150/M input

$0.600/M output

GPT-4o mini Search Preview is a specialized model for web search in Chat Completions. It is trained to understand and execute web search queries.

OpenAI: GPT-5 Chat

$1.25/M input

$10.00/M output

GPT-5 Chat is designed for advanced, natural, multimodal, and context-aware conversations for enterprise applications.

OpenAI: GPT-5 Codex

$1.25/M input

$10.00/M output

GPT-5-Codex is a specialized version of GPT-5 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....

OpenAI: GPT-5 Nano

$0.050/M input

$0.400/M output

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...

OpenAI: GPT-5 Pro

$15.00/M input

$120.00/M output

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...

OpenAI: GPT-5.1

$1.25/M input

$10.00/M output

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...

OpenAI: GPT-5.1 Chat

$1.25/M input

$10.00/M output

GPT-5.1 Chat (AKA Instant is the fast, lightweight member of the 5.1 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on...

OpenAI: GPT-5.1-Codex

$1.25/M input

$10.00/M output

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....

OpenAI: GPT-5.1-Codex-Max

$1.25/M input

$10.00/M output

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...

OpenAI: GPT-5.1-Codex-Mini

$0.250/M input

$2.00/M output

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

OpenAI: gpt-oss-120b

$0.030/M input

$0.150/M output

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...

OpenAI: gpt-oss-120b (free)

— input

— output

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...

OpenAI: gpt-oss-20b

$0.029/M input

$0.140/M output

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...

OpenAI: gpt-oss-20b (free)

— input

— output

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...

OpenAI: gpt-oss-safeguard-20b

$0.075/M input

$0.300/M output

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...

OpenAI: o1

$15.00/M input

$60.00/M output

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...

OpenAI: o3

$2.00/M input

$8.00/M output

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....

OpenAI: o3 Deep Research

$10.00/M input

$40.00/M output

o3-deep-research is OpenAI's advanced model for deep research, designed to tackle complex, multi-step research tasks. Note: This model always uses the 'web_search' tool which adds additional cost.

OpenAI: o3 Mini

$1.10/M input

$4.40/M output

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...

OpenAI: o3 Mini High

$1.10/M input

$4.40/M output

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...

OpenAI: o3 Pro

$20.00/M input

$80.00/M output

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...

OpenAI: o4 Mini

$1.10/M input

$4.40/M output

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...

OpenAI: o4 Mini Deep Research

$2.00/M input

$8.00/M output

o4-mini-deep-research is OpenAI's faster, more affordable deep research model—ideal for tackling complex, multi-step research tasks. Note: This model always uses the 'web_search' tool which adds additional cost.

OpenAI: o4 Mini High

$1.10/M input

$4.40/M output

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...

Anthropic: Claude 3 Haiku

$0.250/M input

$1.25/M output

Claude 3 Haiku is Anthropic's fastest and most compact model for near-instant responsiveness. Quick and accurate targeted performance. See the launch announcement and benchmark results [here](https://www.anthropic.com/news/claude-3-haiku) #multimodal

Anthropic: Claude Opus 4

$15.00/M input

$75.00/M output

Claude Opus 4 is benchmarked as the world’s best coding model, at time of release, bringing sustained performance on complex, long-running tasks and agent workflows. It sets new benchmarks in...

Anthropic: Claude Opus 4.6 (Fast)

$30.00/M input

$150.00/M output

Fast-mode variant of [Opus 4.6](/anthropic/claude-opus-4.6) - identical capabilities with higher output speed at premium 6x pricing. Learn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode

Anthropic: Claude Opus 4.7 (Fast)

$30.00/M input

$150.00/M output

Fast-mode variant of [Opus 4.7](/anthropic/claude-opus-4.7) - identical capabilities with higher output speed at premium 6x pricing. Learn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode

Anthropic: Claude Opus 4.8 (Fast)

$10.00/M input

$50.00/M output

Fast-mode variant of [Opus 4.8](/anthropic/claude-opus-4.8) - identical capabilities with higher output speed at 2x pricing relative to regular Opus 4.8. Learn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode

Anthropic: Claude Sonnet 4

$3.00/M input

$15.00/M output

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 Fable 5

Max Output

128K

$10.00/M input

$50.00/M output

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 Opus 4.1

$1.50/M input

$7.50/M output

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

$0.500/M input

$2.50/M output

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 4.8

Max Output

128K

$5.00/M input

$25.00/M output

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 Sonnet 4.5

$0.300/M input

$1.50/M output

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...

Gemini 2.5 Flash-LiteFree

Max Output

66K

Free input

Free output

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 3 Flash Preview

Max Output

66K

$0.500/M input

$3.00/M output

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

Max Output

66K

$0.250/M input

$1.50/M output

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

Max Output

66K

$0.250/M input

$1.50/M output

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 Custom Tools

Max Output

66K

$2.00/M input

$12.00/M output

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

Max Output

66K

$1.50/M input

$9.00/M output

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 Flash Latest

Max Output

66K

$1.50/M input

$9.00/M output

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

Gemini Pro Latest

Max Output

66K

$2.00/M input

$12.00/M output

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

Google: Gemini 2.5 Flash Lite Preview 09-2025

$0.100/M input

$0.400/M output

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...

Google: Gemini 2.5 Pro Preview 05-06

$1.25/M input

$10.00/M output

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...

Google: Gemini 2.5 Pro Preview 06-05

$1.25/M input

$10.00/M output

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...

Google: Gemma 2 27B

$0.650/M input

$0.650/M output

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...

Google: Gemma 3 27B

$0.080/M input

$0.160/M output

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,...

google/gemma-3-12b-it

Max Output

16K

$0.050/M input

$0.150/M output

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,...

google/gemma-3-4b-it

Max Output

16K

$0.050/M input

$0.100/M output

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,...

google/gemma-3n-e4b-it

$0.060/M input

$0.120/M output

Gemma 3n E4B-it is optimized for efficient execution on mobile and low-resource devices, such as phones, laptops, and tablets. It supports multimodal inputs—including text, visual data, and audio—enabling diverse tasks...

Lyria 3 Clip Preview

Max Output

66K

— input

— output

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

Max Output

66K

— input

— output

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...

Nano Banana

Max Output

33K

$0.300/M input

$2.50/M output

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

Max Output

33K

$0.500/M input

$3.00/M output

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

Max Output

33K

$0.500/M input

$3.00/M output

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 Pro

Max Output

33K

$2.00/M input

$12.00/M output

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

Max Output

33K

$2.00/M input

$12.00/M output

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...

codestral-2508

$0.300/M input

$0.900/M output

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)

devstral-2512

$0.400/M input

$2.00/M output

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...

ministral-14b-2512

$0.200/M input

$0.200/M output

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-3b-2512

$0.100/M input

$0.100/M output

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

ministral-8b-2512

$0.150/M input

$0.150/M output

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

Mistral Large 2407

$2.00/M input

$6.00/M output

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-2512

$0.500/M input

$1.50/M output

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

$0.400/M input

$2.00/M output

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-3-5

$1.50/M input

$7.50/M output

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-small-2603

$0.150/M input

$0.600/M output

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: Mistral Medium 3.1

$0.400/M input

$2.00/M output

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: Mistral Nemo

$0.020/M input

$0.030/M output

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: Mistral Small 3

$0.050/M input

$0.080/M output

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: Mistral Small 3.1 24B

$0.351/M input

$0.555/M output

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: Mistral Small 3.2 24B

$0.075/M input

$0.200/M output

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: Mixtral 8x22B Instruct

$2.00/M input

$6.00/M output

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,...

Mistral: Saba

$0.200/M input

$0.600/M output

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...

Mistral: Voxtral Small 24B 2507

$0.100/M input

$0.300/M output

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...

mistralai/mistral-large

$2.00/M input

$6.00/M output

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/)....

deepseek-v4-flashFree

Max Output

66K

Free input

Free output

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: DeepSeek V3 0324

$0.200/M input

$0.770/M output

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: DeepSeek V3.1

$0.210/M input

$0.790/M output

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: DeepSeek V3.1 Terminus

$0.270/M input

$0.950/M output

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: DeepSeek V3.2

$0.229/M input

$0.343/M output

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: DeepSeek V3.2 Exp

$0.270/M input

$0.410/M output

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: R1

$0.700/M input

$2.50/M output

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....

DeepSeek: R1 0528

$0.500/M input

$2.15/M output

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...

DeepSeek: R1 Distill Llama 70B

$0.800/M input

$0.800/M output

DeepSeek R1 Distill Llama 70B is a distilled large language model based on [Llama-3.3-70B-Instruct](/meta-llama/llama-3.3-70b-instruct), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). The model combines advanced distillation techniques to achieve high performance across...

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 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-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 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 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 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,...

Cohere: Command A

$2.50/M input

$10.00/M output

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...

Cohere: North Mini Code (free)

— input

— output

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...

command-r-08-2024

Max Output

4K

$0.150/M input

$0.600/M output

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-plus-08-2024

Max Output

4K

$2.50/M input

$10.00/M output

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

Max Output

4K

$0.037/M input

$0.150/M output

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...

grok-4.3

$1.25/M input

$2.50/M output

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

grok-build-0.1

$1.00/M input

$2.00/M output

Grok Build 0.1 is xAI’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...

Meta: Llama 3 8B Instruct

$0.140/M input

$0.140/M output

Meta's latest class of model (Llama 3) launched with a variety of sizes & flavors. This 8B instruct-tuned version was optimized for high quality dialogue usecases. It has demonstrated strong...

Meta: Llama 3.1 70B Instruct

$0.400/M input

$0.400/M output

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...

Meta: Llama 3.1 8B Instruct

$0.020/M input

$0.030/M output

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...

Meta: Llama 3.2 11B Vision Instruct

$0.345/M input

$0.345/M output

Llama 3.2 11B Vision is a multimodal model with 11 billion parameters, designed to handle tasks combining visual and textual data. It excels in tasks such as image captioning and...

Meta: Llama 3.2 1B Instruct

$0.027/M input

$0.201/M output

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...

Meta: Llama 3.2 3B Instruct

$0.051/M input

$0.335/M output

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...

Meta: Llama 3.2 3B Instruct (free)

— input

— output

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...

Meta: Llama 3.3 70B Instruct

$0.100/M input

$0.320/M output

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...

Meta: Llama 3.3 70B Instruct (free)

— input

— output

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...

Meta: Llama 4 Maverick

$0.150/M input

$0.600/M output

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...

Meta: Llama 4 Scout

$0.100/M input

$0.300/M output

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...

Meta: Llama Guard 4 12B

$0.180/M input

$0.180/M output

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...

Open 1M-context chat model served by MoonMath inference.

Qwen: Qwen Plus 0728 (thinking)

$0.260/M input

$0.780/M output

Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination.

Qwen: Qwen-Plus

$0.260/M input

$0.780/M output

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

Qwen: Qwen2.5 7B Instruct

$0.040/M input

$0.100/M output

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...

Qwen: Qwen2.5 VL 72B Instruct

$0.800/M input

$1.00/M output

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.

Qwen: Qwen3 14B

$0.100/M input

$0.240/M output

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...

Qwen: Qwen3 235B A22B

$0.455/M input

$1.82/M output

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...

Qwen: Qwen3 235B A22B Instruct 2507

$0.090/M input

$0.100/M output

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,...

Qwen: Qwen3 235B A22B Thinking 2507

$0.100/M input

$0.100/M output

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...

Qwen: Qwen3 30B A3B

$0.120/M input

$0.500/M output

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...

Qwen: Qwen3 30B A3B Instruct 2507

$0.048/M input

$0.193/M output

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...

Qwen: Qwen3 30B A3B Thinking 2507

$0.080/M input

$0.400/M output

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...

Qwen: Qwen3 32B

$0.080/M input

$0.280/M output

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...

Qwen: Qwen3 8B

$0.050/M input

$0.400/M output

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,...

Qwen: Qwen3 Coder 30B A3B Instruct

$0.070/M input

$0.270/M output

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...

Qwen: Qwen3 Coder 480B A35B

$0.220/M input

$1.80/M output

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...

Qwen: Qwen3 Coder 480B A35B (free)

— input

— output

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...

Qwen: Qwen3 Coder Flash

$0.195/M input

$0.975/M output

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...

Qwen: Qwen3 Coder Next

$0.110/M input

$0.800/M output

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...

Qwen: Qwen3 Coder Plus

$0.650/M input

$3.25/M output

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...

Qwen: Qwen3 Max

$0.780/M input

$3.90/M output

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...

Qwen: Qwen3 Max Thinking

$0.780/M input

$3.90/M output

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...

Qwen: Qwen3 Next 80B A3B Instruct (free)

— input

— output

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...

Qwen: Qwen3 Next 80B A3B Thinking

$0.098/M input

$0.780/M output

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...

Qwen: Qwen3 VL 235B A22B Instruct

$0.200/M input

$0.880/M output

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...

Qwen: Qwen3 VL 235B A22B Thinking

$0.260/M input

$2.60/M output

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....

Qwen: Qwen3 VL 30B A3B Instruct

$0.130/M input

$0.520/M output

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...

Qwen: Qwen3 VL 30B A3B Thinking

$0.130/M input

$1.56/M output

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...

Qwen: Qwen3 VL 32B Instruct

$0.104/M input

$0.416/M output

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...

Qwen: Qwen3 VL 8B Instruct

$0.080/M input

$0.500/M output

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...

Qwen: Qwen3 VL 8B Thinking

$0.117/M input

$1.36/M output

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...

Qwen: Qwen3.7 Max

$1.25/M input

$3.75/M output

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,...

Qwen: Qwen3.7 Plus

$0.320/M input

$1.28/M output

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...

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

Max Output

16K

$0.090/M input

$1.10/M output

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...

Qwen2.5 72B Instruct

$0.360/M input

$0.400/M output

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 Coder 32B Instruct

$0.660/M input

$1.00/M output

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**...

AI21: Jamba Large 1.7

$0.200/M input

$0.800/M output

Jamba Large 1.7 is the latest model in the Jamba open family, offering improvements in grounding, instruction-following, and overall efficiency. Built on a hybrid SSM-Transformer architecture with a 256K context...

Aion-1.0 is a multi-model system designed for high performance across various tasks, including reasoning and coding. It is built on DeepSeek-R1, augmented with additional models and techniques such as Tree...

Aion-1.0-Mini 32B parameter model is a distilled version of the DeepSeek-R1 model, designed for strong performance in reasoning domains such as mathematics, coding, and logic. It is a modified variant...

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-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...

Olmo 3 32B Think is a large-scale, 32-billion-parameter model purpose-built for deep reasoning, complex logic chains and advanced instruction-following scenarios. Its capacity enables strong performance on demanding evaluation tasks and...

Amazon: Nova 2 Lite

$0.300/M input

$2.50/M output

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...

Amazon: Nova Lite 1.0

$0.060/M input

$0.240/M output

Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite...

Amazon: Nova Micro 1.0

$0.035/M input

$0.140/M output

Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost. With a context length...

Amazon: Nova Premier 1.0

$2.50/M input

$12.50/M output

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.

Amazon: Nova Pro 1.0

$0.800/M input

$3.20/M output

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...

Coder‑Large is a 32 B‑parameter offspring of Qwen 2.5‑Instruct that has been further trained on permissively‑licensed GitHub, CodeSearchNet and synthetic bug‑fix corpora. It supports a 32k context window, enabling multi‑file...

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...

Trinity Mini is a 26B-parameter (3B active) sparse mixture-of-experts language model featuring 128 experts with 8 active per token. Engineered for efficient reasoning over long contexts (131k) with robust function...

Virtuoso‑Large is Arcee's top‑tier general‑purpose LLM at 72 B parameters, tuned to tackle cross‑domain reasoning, creative writing and enterprise QA. Unlike many 70 B peers, it retains the 128 k...

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...

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 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-2.0-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 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,...

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...

Cogito v2.1 671B MoE represents one of the strongest open models globally, matching performance of frontier closed and open models. This model is trained using self play with reinforcement learning...

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 4.1 8B is a dense, decoder-only 8-billion-parameter language model from IBM, part of the Granite 4.1 family. It supports a 131K-token context window and is designed for enterprise tasks...

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...

Ling-2.6-1T is an instant (instruct) model from inclusionAI and the company’s trillion-parameter flagship, designed for real-world agents that require fast execution and high efficiency at scale. It uses a “fast...

Ling-2.6-flash is an instant (instruct) model from inclusionAI with 104B total parameters and 7.4B active parameters, designed for real-world agents that require fast responses, strong execution, and high token efficiency....

Ring-2.6-1T is a 1T-parameter-scale thinking model with 63B active parameters, built for real-world agent workflows that require both strong capability and operational efficiency. It is optimized for coding agents, tool...

Inflection 3 Pi powers Inflection's [Pi](https://pi.ai) chatbot, including backstory, emotional intelligence, productivity, and safety. It has access to recent news, and excels in scenarios like customer support and roleplay. Pi...

Inflection 3 Productivity is optimized for following instructions. It is better for tasks requiring JSON output or precise adherence to provided guidelines. It has access to recent news. For emotional...

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...

KAT-Coder-Pro V2 is the latest high-performance model in KwaiKAT’s KAT-Coder series, designed for complex enterprise-grade software engineering and SaaS integration. It builds on the agentic coding strengths of earlier versions,...

LFM2-24B-A2B is the largest model in the LFM2 family of hybrid architectures designed for efficient on-device deployment. Built as a 24B parameter Mixture-of-Experts model with only 2B active parameters per...

LFM2.5-1.2B-Instruct is a compact, high-performance instruction-tuned model built for fast on-device AI. It delivers strong chat quality in a 1.2B parameter footprint, with efficient edge inference and broad runtime support.

LFM2.5-1.2B-Thinking is a lightweight reasoning-focused model optimized for agentic tasks, data extraction, and RAG—while still running comfortably on edge devices. It supports long context (up to 32K tokens) and is...

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).

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.

Microsoft: Phi 4

$0.070/M input

$0.140/M output

[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...

Microsoft: Phi 4 Mini Instruct

$0.080/M input

$0.350/M output

Phi-4-mini-instruct is a lightweight open model built upon synthetic data and filtered publicly available websites - with a focus on high-quality, reasoning dense data. The model belongs to the Phi-4...

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 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 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 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-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 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...

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 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 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...

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'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>...

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

Nex-N2-Pro is an agentic mixture-of-experts model from Nex AGI, with 17B active parameters out of 397B total. Built on the Qwen3.5 architecture, it accepts text and image input and produces...

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 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 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 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...

Hermes 4 70B is a hybrid reasoning model from Nous Research, built on Meta-Llama-3.1-70B. It introduces the same hybrid mode as the larger 405B release, allowing the model to either...

NVIDIA: Nemotron 3 Nano 30B A3B (free)

— input

— output

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...

NVIDIA: Nemotron 3 Nano Omni (free)

— input

— output

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...

NVIDIA: Nemotron 3 Ultra (free)

— input

— output

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...

NVIDIA: Nemotron 3.5 Content Safety (free)

— input

— output

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...

NVIDIA: Nemotron Nano 12B 2 VL (free)

— input

— output

NVIDIA Nemotron Nano 2 VL is a 12-billion-parameter open multimodal reasoning model designed for video understanding and document intelligence. It introduces a hybrid Transformer-Mamba architecture, combining transformer-level accuracy with Mamba’s...

NVIDIA: Nemotron Nano 9B V2 (free)

— input

— output

NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and...

nvidia/llama-3.3-nemotron-super-49b-v1.5

Max Output

16K

$0.400/M input

$0.400/M output

Llama-3.3-Nemotron-Super-49B-v1.5 is a 49B-parameter, English-centric reasoning/chat model derived from Meta’s Llama-3.3-70B-Instruct with a 128K context. It’s post-trained for agentic workflows (RAG, tool calling) via SFT across math, code, science, and...

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

Max Output

228K

$0.050/M input

$0.200/M output

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...

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

Max Output

16K

$0.500/M input

$2.20/M output

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...

Owl Alpha is a high-performance foundation model designed for agentic workloads. Natively supports tool use, and long-context tasks, with strong performance in code generation, automated workflows, and complex instruction execution....

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...

Perplexity: Sonar

$1.00/M input

$1.00/M output

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...

Perplexity: Sonar Deep Research

$2.00/M input

$8.00/M output

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...

Perplexity: Sonar Pro

$3.00/M input

$15.00/M output

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...

Perplexity: Sonar Pro Search

$3.00/M input

$15.00/M output

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...

Perplexity: Sonar Reasoning Pro

$2.00/M input

$8.00/M output

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...

Laguna XS.2 is the second-generation model in the XS size class from [Poolside](https://poolside.ai/), their efficient coding agent series. It combines tool calling and reasoning capabilities with a compact footprint, offering...

Laguna XS.2 is the second-generation model in the XS size class from [Poolside](https://poolside.ai/), their efficient coding agent series. It combines tool calling and reasoning capabilities with a compact footprint, offering...

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 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 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...

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...

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

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...

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....

This is [Sao10K](/sao10k)'s experiment over [Euryale v2.2](/sao10k/l3.1-euryale-70b).

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).

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).

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 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...

Switchpoint AI's router instantly analyzes your request and directs it to the optimal AI from an ever-evolving library. As the world of LLMs advances, our router gets smarter, ensuring you...

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...

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...

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

Rocinante 12B is designed for engaging storytelling and rich prose. Early testers have reported: - Expanded vocabulary with unique and expressive word choices - Enhanced creativity for vivid narratives -...

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

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

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...

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...

WizardLM-2 8x22B

$0.620/M input

$0.620/M output

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...

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...

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 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....

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,...