Every way
to use the major models.

Google: Gemini 3.8 Flash

multimodal

Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic task...

Anthropic: Claude Fable 5.1

multimodal

Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, a...

Ox Alpha is a reasoning model designed for coding, sustained agentic work, and production workloads. It is suited for long-horizon softwa...

Google: Gemini 3.7 Flash

multimodal

Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed f...

SpaceXAI: Grok 4.6

multimodal

Grok 4.6 is SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.

Sakana Namazu is a Japanese-specialized reasoning model from Sakana AI, based on Kimi K2.6 with additional training for Japanese language...

Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B to...

Claude Opus 5

multimodal

Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at ...

Google: Gemini 3.5 Flash-Lite

multimodal

Gemini 3.5 Flash-Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute ...

Google: Gemini 3.6 Flash

multimodal

Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to pro...

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 co...

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 ...

Auto Router (Beta) is a task-aware router from OpenRouter. It classifies each request, then routes it the [most popular model](/rankings#...

OpenAI: GPT-5.6 Luna

multimodal

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 ch...

OpenAI: GPT-5.6 Luna Pro

multimodal

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` ...

OpenAI: GPT-5.6 Sol

multimodal

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 p...

OpenAI: GPT-5.6 Sol Pro

multimodal

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...

OpenAI: GPT-5.6 Terra

multimodal

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. ...

OpenAI: GPT-5.6 Terra Pro

multimodal

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.mod...

Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in ...

xAI: Grok 4.5

multimodal

Grok 4.5 is SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.

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 thei...

Anthropic: Claude Sonnet 5

multimodal

Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It suppo...

Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)

multimodal

Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity dev...

Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-age...

Laguna M.1 is the flagship coding agent model from [Poolside](https://poolside.ai/), optimized for complex software engineering tasks. De...

Laguna XS.2 is the second-generation model in the XS size class from [Poolside](https://poolside.ai/), their efficient coding agent serie...

Google: Nano Banana 2 (Gemini 3.1 Flash Image)

multimodal

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-le...

Google: Nano Banana Pro (Gemini 3 Pro Image)

multimodal

Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana ...

Anthropic: Claude Fable 5

multimodal

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

Fusion turns your prompt into a small multi-model deliberation. A panel of expert models (see below) analyzes your prompt in parallel wit...

Anthropic: Claude Opus 4.8

multimodal

Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with t...

AI21: Jamba Large 1.7

text

Jamba Large 1.7 is the latest model in the Jamba open family, offering improvements in grounding, instruction-following, and overall effi...

Amazon: Nova 2 Lite

multimodal

Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. ...

Amazon: Nova Lite 1.0

multimodal

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 ...

Amazon: Nova Micro 1.0

text

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 c...

Amazon: Nova Premier 1.0

multimodal

Amazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks and for use as the best teacher for dis...

Amazon: Nova Pro 1.0

multimodal

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 ...

Anthropic: Claude 3 Haiku

multimodal

Claude 3 Haiku is Anthropic's fastest and most compact model for near-instant responsiveness. Quick and accurate targeted performance. S...

Anthropic: Claude Opus 4

multimodal

Claude Opus 4 is benchmarked as the world’s best coding model, at time of release, bringing sustained performance on complex, long-runnin...

Anthropic: Claude Opus 4.1

multimodal

Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic task...

Anthropic: Claude Opus 4.5

multimodal

Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon c...

Anthropic: Claude Opus 4.6

multimodal

Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire...

Anthropic: Claude Sonnet 4

multimodal

Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with...

Anthropic: Claude Sonnet 4.5

multimodal

Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers st...

Your prompt will be processed by a meta-model and routed to one of dozens of models (see below), optimizing for the best possible output....

Transform your natural language requests into structured OpenRouter API request objects. Describe what you want to accomplish with AI mod...

Cohere: Command A

text

Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, mult...

Cohere: Command R (08-2024)

text

command-r-08-2024 is an update of the [Command R](/models/cohere/command-r) with improved performance for multilingual retrieval-augmente...

Cohere: Command R+ (08-2024)

text

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 l...

Cohere: Command R7B (12-2024)

text

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, an...

The simplest way to get free inference. openrouter/free is a router that selects free models at random from the models available on OpenR...

Google: Gemini 2.0 Flash

multimodal

Gemini Flash 2.0 offers a significantly faster time to first token (TTFT) compared to [Gemini Flash 1.5](/google/gemini-flash-1.5), while...

Google: Gemini 2.0 Flash Lite

multimodal

Gemini 2.0 Flash Lite offers a significantly faster time to first token (TTFT) compared to [Gemini Flash 1.5](/google/gemini-flash-1.5), ...

Google: Gemini 2.5 Flash

multimodal

Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and sci...

Google: Gemini 2.5 Flash Lite

multimodal

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 ...

Google: Gemini 3.1 Flash Lite

multimodal

Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text,...

Google: Gemini 3.5 Flash

multimodal

Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed....

Google: Gemma 2 27B

27B

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). ...

Google: Gemma 3 12B

12B

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, unders...

Google: Gemma 3n 4B

4B

Gemma 3n E4B-it is optimized for efficient execution on mobile and low-resource devices, such as phones, laptops, and tablets. It support...

Google: Gemma 4 26B A4B

26B

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...

Google: Gemma 4 31B

31B

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K ...

Google: Nano Banana (Gemini 2.5 Flash Image)

multimodal

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...

Inflection 3 Pi powers Inflection's [Pi](https://pi.ai) chatbot, including backstory, emotional intelligence, productivity, and safety. I...

Inflection 3 Productivity is optimized for following instructions. It is better for tasks requiring JSON output or precise adherence to p...

Aion 3.5 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative g...

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, l...

Anthropic: Claude Haiku 5.5

multimodal

Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use....

Anthropic: Claude Opus 5.5

multimodal

Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. I...

Anthropic: Claude Sonnet 5.5

multimodal

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 ...

Cohere: Command A+

multimodal

Command A+ is Cohere's flagship model for enterprise agentic workflows. It accepts text and image inputs with a 192K context window, supp...

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

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

Google: Nano Banana 2.1

multimodal

Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and N...

Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total.

Schematron V2 Small is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes extraction quality for complex sch...

Schematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes throughput for high-volume extract...

Mistral: Mistral Large 4

multimodal

Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads....

Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual fee...

Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual fee...

NVIDIA: Switchyard

text

Switchyard is an open-source model router that switches between multiple models to optimize the cost of requests. By default it will use ...

OpenAI: GPT-6.1 Sol

multimodal

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 agent...

OpenAI: GPT-6.1 Sol Pro

multimodal

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...

OpenAI: GPT-6 Astra

multimodal

GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep rese...

OpenAI: GPT-6 Astra Pro

multimodal

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...

OpenAI: GPT-6 Luna

multimodal

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 laten...

OpenAI: GPT-6 Luna Pro

multimodal

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...

OpenAI: GPT-6 Sol

multimodal

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...

OpenAI: GPT-6 Sol Pro

multimodal

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 `p...

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

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

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

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

Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance acr...

Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance acr...

Perceptron Mk1.5 is Perceptron's embodied reasoning model for physical agents. It accepts text, image, video, and audio input, and answer...

Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports coding, mathematics, tool calling, and...

Qwen: Qwen3.8 Max Prime

multimodal

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 poin...

Qwen: Qwen3.8 Omni Flash

multimodal

Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audi...

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 o...

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-...

Space Bunny Alpha is an anonymous large model with blazing-fast inference, strong coding capabilities and native multimodal input support...

SpaceXAI: Grok 4.7

multimodal

Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at lo...

Jev Router picks the best model and reasoning effort for each request, balancing quality, speed, and cost. It runs on [Jev](https://openr...

Union Alpha is a multimodal model built for research, coding, and agentic workflows, while delivering frontier-level performance across a...

Upstage: Solar Mini 4

text

Solar Mini 4 is Upstage's compact, cost-efficient language model, a 35B-parameter mixture-of-experts with 3B active parameters and a 524K...

Xiaomi: MiMo-V2.6-Flash

multimodal

MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parame...

Xiaomi: MiMo-V2.6-Pro

multimodal

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 ce...

Xiaomi: MiMo-V2.6-Pro-UltraSpeed

multimodal

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...

Z.ai: GLM 5.3 FlashX

multimodal

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 toke...

Z.ai: GLM 5.3 Prime

text

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...

OpenAI: GPT-3.5 Turbo

text

GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and tradition...

OpenAI: GPT-3.5 Turbo (older v0613)

text

GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and tradition...

OpenAI: GPT-3.5 Turbo 16k

text

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 reque...

OpenAI: GPT-3.5 Turbo Instruct

text

This model is a variant of GPT-3.5 Turbo tuned for instructional prompts and omitting chat-related optimizations. Training data: up to Se...

OpenAI: GPT-4

text

OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy tha...

OpenAI: GPT-4 (older v0314)

text

GPT-4-0314 is the first version of GPT-4 released, with a context length of 8,192 tokens, and was supported until June 14. Training data:...

OpenAI: GPT-4 Turbo (older v1106)

text

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

OpenAI: GPT-4.1

multimodal

GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-contex...

OpenAI: GPT-4.1 Mini

multimodal

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 ...

OpenAI: GPT-4.1 Nano

multimodal

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 performa...

OpenAI: GPT-4o (2024-05-13)

multimodal

GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligen...

OpenAI: GPT-4o (2024-08-06)

multimodal

The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respo...

OpenAI: GPT-4o (2024-11-20)

multimodal

The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improv...

OpenAI: GPT-4o-mini (2024-07-18)

multimodal

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. ...

OpenAI: GPT-5 Chat

multimodal

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

OpenAI: GPT-5 Codex

multimodal

GPT-5-Codex is a specialized version of GPT-5 optimized for software engineering and coding workflows. It is designed for both interactiv...

OpenAI: GPT-5 Image

multimodal

[GPT-5](https://openrouter.ai/openai/gpt-5) Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities. It o...

OpenAI: GPT-5 Image Mini

multimodal

GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by [GPT-5 Mini](https://openrouter.ai/openai/gpt-5-mini), with...

OpenAI: GPT-5 Mini

multimodal

GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following a...

OpenAI: GPT-5 Nano

multimodal

GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low late...

OpenAI: GPT-5 Pro

multimodal

GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized f...

OpenAI: GPT-5.1

multimodal

GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adheren...

OpenAI: GPT-5.1 Chat

multimodal

GPT-5.1 Chat (AKA Instant is the fast, lightweight member of the 5.1 family, optimized for low-latency chat while retaining strong genera...

OpenAI: GPT-5.1-Codex

multimodal

GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both intera...

OpenAI: GPT-5.1-Codex-Max

multimodal

GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is base...

OpenAI: GPT-5.1-Codex-Mini

multimodal

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

OpenAI: GPT-5.2

multimodal

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...

OpenAI: GPT-5.2 Chat

multimodal

GPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retaining strong gener...

OpenAI: GPT-5.2 Pro

multimodal

GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. I...

OpenAI: GPT-5.2-Codex

multimodal

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 in...

OpenAI: GPT-5.3 Chat

multimodal

GPT-5.3 Chat is an update to ChatGPT's most-used model that makes everyday conversations smoother, more useful, and more directly helpful...

OpenAI: GPT-5.3-Codex

multimodal

GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex wi...

OpenAI: GPT-5.4

multimodal

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 ...

OpenAI: GPT-5.4 Image 2

multimodal

[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 capabiliti...

OpenAI: GPT-5.4 Mini

multimodal

GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It suppor...

OpenAI: GPT-5.4 Nano

multimodal

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...

OpenAI: GPT-5.4 Pro

multimodal

GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex,...

OpenAI: GPT-5.5

multimodal

GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher relia...

OpenAI: GPT-5.5 Pro

multimodal

GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a ...

OpenAI: gpt-oss-safeguard-20b

20B

gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts ...

OpenAI: o1

multimodal

The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is t...

OpenAI: o1-pro

multimodal

The o1 series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o1-pro mod...

OpenAI: o3

multimodal

o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It ...

OpenAI: o3 Deep Research

multimodal

o3-deep-research is OpenAI's advanced model for deep research, designed to tackle complex, multi-step research tasks. Note: This model a...

OpenAI: o3 Mini

text

OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and...

OpenAI: o3 Mini High

text

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 langua...

OpenAI: o3 Pro

multimodal

The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro mode...

OpenAI: o4 Mini

multimodal

OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multim...

OpenAI: o4 Mini Deep Research

multimodal

o4-mini-deep-research is OpenAI's faster, more affordable deep research model—ideal for tackling complex, multi-step research tasks. Not...

OpenAI: o4 Mini High

multimodal

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 reason...

Owl Alpha is a high-performance foundation model designed for agentic workloads. Natively supports tool use, and long-context tasks, with...

The Pareto Router maintains a tiered shortlist of strong coding models, ranked by [Artificial Analysis](https://artificialanalysis.ai/) c...

Perplexity: Sonar

multimodal

Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed ...

Perplexity: Sonar Deep Research

text

Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It aut...

Perplexity: Sonar Pro

multimodal

Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing...

Perplexity: Sonar Pro Search

multimodal

Exclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system. It is d...

Perplexity: Sonar Reasoning Pro

multimodal

Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing...

xAI: Grok 4.20

multimodal

Grok 4.20 is a reasoning model from xAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest halluci...

xAI: Grok 4.20 Multi-Agent

multimodal

Grok 4.20 Multi-Agent is a variant of xAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in paral...

xAI: Grok 4.3

multimodal

Grok 4.3 is a reasoning model from xAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instructi...

xAI: Grok Build 0.1

multimodal

Grok Build 0.1 is xAI’s fast coding model trained specifically for agentic software engineering workflows. It supports text and image inp...

Claude Opus 4.7

text

Frontier reasoning and long-form coding from Anthropic.

Claude Sonnet 4.6

text

Best price-performance from Anthropic. Default for production agents.

Claude Haiku 4.5

text

Fast, cheap Claude variant for high-throughput inference.

GPT-5

text

OpenAI's frontier multimodal reasoning model.

Gemini 2.5 Pro

multimodal

Google's frontier reasoning model with native 1M-token context.

Grok 3

multimodal

xAI's frontier model with built-in DeepSearch + real-time X integration.

Claude 3.5 Haiku

text

Fast/cheap Claude 3.5 variant — production fallback for Haiku 4.5.

GPT-4o Mini

multimodal

Cheap multimodal default — replaced GPT-3.5 Turbo for low-cost workloads.

Claude 3.5 Sonnet

text

Anthropic's 3.5 generation — still in active production.

Gemini 1.5 Flash

multimodal

Cheap fast Gemini — production default before 2.0/2.5 Flash.

GPT-4o

multimodal

OpenAI's multimodal model — text, vision, audio in one.

GPT-4 Turbo

text

OpenAI's pre-GPT-5 flagship — still extensively deployed.

Gemini 1.5 Pro

multimodal

Google's pre-2.5 frontier — 2M context launched here.

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

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

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

Claude Opus 5 (Fast)

multimodal

Fast-mode variant of [Opus 5](/anthropic/claude-opus-5) - identical capabilities with higher output speed at 2x pricing relative to regul...

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

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

Anthropic: Claude Opus 4.8 (Fast)

multimodal

Fast-mode variant of [Opus 4.8](/anthropic/claude-opus-4.8) - identical capabilities with higher output speed at 2x pricing relative to r...

Anthropic Claude Haiku Latest

multimodal

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

Anthropic Claude Sonnet Latest

multimodal

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

Anthropic: Claude Opus 4.6 (Fast)

multimodal

Fast-mode variant of [Opus 4.6](/anthropic/claude-opus-4.6) - identical capabilities with higher output speed at premium 6x pricing. Lea...

Anthropic: Claude Opus 4.7 (Fast)

multimodal

Fast-mode variant of [Opus 4.7](/anthropic/claude-opus-4.7) - identical capabilities with higher output speed at premium 6x pricing. Lea...

Anthropic: Claude Opus Latest

multimodal

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

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

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

Google: Gemini 2.5 Flash Lite Preview 09-2025

multimodal

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 ...

Google: Gemini 2.5 Pro Preview 05-06

multimodal

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It emplo...

Google: Gemini 2.5 Pro Preview 06-05

multimodal

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It emplo...

Google: Gemini 3 Flash Preview

multimodal

Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance....

Google: Gemini 3.1 Flash Lite Preview

multimodal

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...

Google: Gemini 3.1 Pro Preview

multimodal

Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic relia...

Google: Gemini 3.1 Pro Preview Custom Tools

multimodal

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 gener...

Google: Lyria 3 Clip Preview

multimodal

30 second duration clips are priced at $0.04 per clip. Lyria 3 is Google's family of music generation models, available through the Gemin...

Google: Lyria 3 Pro Preview

multimodal

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. ...

Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)

multimodal

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, deliverin...

Google: Nano Banana Pro (Gemini 3 Pro Image Preview)

multimodal

Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana ...

OpenAI GPT Latest

multimodal

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

OpenAI GPT Mini Latest

multimodal

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

OpenAI: GPT Chat Latest

multimodal

GPT Chat Latest points to OpenAI's stable API alias `chat-latest` that always resolves to the latest Instant chat model used in ChatGPT. ...

OpenAI: GPT-4 Turbo Preview

text

The preview GPT-4 model with improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more. Traini...

OpenAI: GPT-4o Search Preview

text

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

text

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