Every AI model,
on one page.

Gemini 3.1 Flash Lite Image. (Version: 3.0, Defaults: temperature=1, topP=0.95, topK=64, interfaces=[generateContent,countTokens,batchGenerateContent])

Gemini Omni Flash Preview (Version: 001, Defaults: temperature=1, topP=0.95, topK=64, interfaces=[generateContent,countTokens])

Google Gemma 4 31B on Cerebras - first multimodal model on wafer-scale inference (~1,850 tok/s). Vision (base64 PNG/JPEG, max 5 images / 10MB), function calling, reasoning (off by default, enable via effort). 131K context (65K free tier), 40K max output.

Best combination of speed and intelligence, with the largest gains in coding and agentic tasks

Moonshot Kimi K2.7 Code served via Alibaba Model Studio. Multimodal, always-on thinking, 256K context. (Alibaba pricing not yet published.)

DeepSeek V4 Pro served via Alibaba Model Studio (Alibaba pricing, ~5x DeepSeek-direct). 1M context, thinking.

DeepSeek V3.2 served via Alibaba Model Studio (superseded by V4). Thinking.

Multi-agent conductor system routing 1-3 expert agents for complex, multi-step reasoning - maximum answer quality on hard tasks. 1M context.

Fast orchestration model routing tasks across a swappable pool of frontier LLMs - low latency, high quality. 1M context. Billed at the routed underlying model's standard rate.

Fast, cost-effective multimodal model with 1M context, near-flagship quality, vision/video, and built-in tools.

DeepSeek V4 Flash served via Alibaba Model Studio. 1M context, thinking.

Flagship agent model with native extended thinking and 1M context. Text-only; strong at coding, productivity, and long-horizon autonomous tasks.

Flagship agent model with native extended thinking and 1M context. Text-only; strong at coding, productivity, and long-horizon autonomous tasks.

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...

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

Z.ai 1M-context flagship (744B MoE, 40B activated). Agentic coding with reasoning_effort control (high/max). 1M context, 128K output.

Most capable widely released model for the most demanding reasoning and long-horizon agentic work

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

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...

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 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...

Multimodal agent model with 1M context, native thinking, and vision/video understanding. Lower cost than Max.

High-speed code variant with ~180 tok/s output (up to 260 in short contexts). Native multimodal with always-on thinking. 256K context.

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,...

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...

Gemini 3 Pro Image (Version: 3.0, Defaults: temperature=1, topP=0.95, topK=64, interfaces=[generateContent,countTokens,batchGenerateContent])

Gemini 3.1 Flash Image. (Version: 3.0, Defaults: temperature=1, topP=0.95, topK=64, interfaces=[generateContent,countTokens,batchGenerateContent])

Most capable Opus-tier model for complex reasoning and agentic coding

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

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...

Gemini 3.5 Flash (Version: 3.5-flash-05-2026, Defaults: temperature=1, topP=0.95, topK=64, interfaces=[generateContent,countTokens,createCachedContent,batchGenerateContent])

Preview release of Antigravity Agent (05-2026) (Version: 0.1, Defaults: temperature=undefined, topP=undefined, topK=undefined, interfaces=[generateContent,countTokens])

Agentic coding model with very long context. Tiered pricing by input length (up to 1M).

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...

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

Alibaba model (not yet curated).

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...

Gemini 3.1 Flash Lite (Version: 3.1-flash-lite-05-2026, Defaults: temperature=1, topP=0.95, topK=64, interfaces=[generateContent,countTokens,createCachedContent,batchGenerateContent])

GPT Chat Latest

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...

Official mistral-medium-latest Mistral AI model

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...

Current vision-language model with strong visual reasoning and thinking. Tiered pricing by input length (up to 256K).

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 M.1 is the flagship coding agent model from [Poolside](https://poolside.ai/), optimized for complex software engineering tasks. Designed for agentic coding workflows, it supports tool calling and reasoning, with a 256K...

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....

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...

Official mistral-medium-latest Mistral AI model

Official mistral-medium-latest Mistral AI model

Alibaba model (not yet curated).

Alibaba model (not yet curated).

Alibaba model (not yet curated).

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

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

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

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

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

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...

Most capable model for complex tasks. Uses more compute for smarter, more precise responses on the hardest problems.

New baseline for complex production workflows. Stronger task execution, more precise tool use, more efficient reasoning with fewer tokens. 1M token context.

MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro....

MiMo-V2.5 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...

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...

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

(https://openrouter.ai/openai/gpt-5.4) Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2. It enables rich multimodal workflows, allowing users to seamlessly move between reasoning, coding, and...

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....

Preview release (April 21th, 2026) of Deep Research (Version: deepthink-exp-05-20, Defaults: temperature=1, topP=0.95, topK=64, interfaces=[generateContent,countTokens])

Preview release (April 21st, 2026) of Deep Research Max (Version: deepthink-exp-05-20, Defaults: temperature=1, topP=0.95, topK=64, interfaces=[generateContent,countTokens])

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

Native multimodal flagship (text, image, video inputs) with thinking and non-thinking modes. Stronger long-form coding, improved instruction compliance and self-correction. 256K context.

Previous most capable model for complex reasoning and agentic coding

Gemini 3.1 Flash TTS Preview (Version: 3.1-flash-tts-preview, Defaults: temperature=1, topP=0.95, topK=64, interfaces=[generateContent,countTokens,batchGenerateContent])

Gemini Robotics-ER 1.6 Preview (Version: 1.6-preview, Defaults: temperature=1, topP=0.95, topK=64, interfaces=[generateContent,countTokens,createCachedContent,batchGenerateContent])

Z.ai flagship (744B MoE, 40B activated). Post-training upgrade over GLM-5 with stronger coding and long-horizon task autonomy. 200K context, thinking mode.

Alibaba model (not yet curated).

Gemma 4 31B IT (Version: 001, Defaults: temperature=1, topP=0.95, topK=64, interfaces=[generateContent,countTokens])

Gemma 4 26B A4B IT (Version: 001, Defaults: temperature=1, topP=0.95, topK=64, interfaces=[generateContent,countTokens])

First multimodal GLM-5 model. Vision-based coding agent with image/video/file inputs. 200K context, 128K output, thinking mode.

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...

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

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

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...

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...

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,...

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,...

MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent...

Cheapest GPT-5.4-class model for simple high-volume tasks like classification and data extraction.

Strongest mini model for coding, computer use, and subagents. GPT-5.4-class intelligence at lower cost and latency.

Mistral Small 4.

Mistral Small 4.

A mid & post-trained version of mistral small 4 for Lean

Speed-optimized GLM-5 variant for agent workflows. Enhanced tool invocation and long-chain execution. 200K context, thinking mode.

NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...

Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design...

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...

Most capable model for complex tasks. Uses more compute for smarter, more precise responses on difficult problems.

Most capable and efficient frontier model for professional work. Native computer use, improved reasoning, coding, and agentic workflows with 1M token context.

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...

GPT-5.3 Chat is an update to ChatGPT's most-used model that makes everyday conversations smoother, more useful, and more directly helpful. It delivers more accurate answers with better contextualization and significantly...

GPT-5.3 Instant model, previously powering ChatGPT. Replaced by GPT-5.5 Instant.

Gemini 3.1 Flash Lite Preview (Version: 3.1-flash-lite-preview-03-2026, Defaults: temperature=1, topP=0.95, topK=64, interfaces=[generateContent,countTokens,createCachedContent,batchGenerateContent])

Gemini 3.1 Flash Image Preview. (Version: 3.0, Defaults: temperature=1, topP=0.95, topK=64, interfaces=[generateContent,countTokens,batchGenerateContent])

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/mediu...

Alibaba model (not yet curated).

Alibaba model (not yet curated).

Alibaba model (not yet curated).

The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the...

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...

Best voice model for audio in, audio out with Chat Completions. Accepts audio inputs and outputs.

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....

Gemini 3.1 Pro Preview optimized for custom tool usage (Version: 3.1-pro-preview-01-2026, Defaults: temperature=1, topP=0.95, topK=64, interfaces=[generateContent,countTokens,createCachedContent,batchGenerateContent])

Gemini 3.1 Pro Preview (Version: 3.1-pro-preview-01-2026, Defaults: temperature=1, topP=0.95, topK=64, interfaces=[generateContent,countTokens,createCachedContent,batchGenerateContent])

Best combination of speed and intelligence for everyday tasks

Alibaba model (not yet curated).

The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of...

MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...

Z.ai flagship foundation model (744B MoE, 40B activated). Designed for Agentic Engineering with SOTA coding and agent capabilities. 200K context, thinking mode.

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...

Most capable agentic coding model. Combines frontier coding performance of GPT-5.2-Codex with reasoning and professional knowledge of GPT-5.2. ~25% faster.

Previous most intelligent model for complex agents and coding, with adaptive thinking

Alibaba model (not yet curated).

Specialized OCR model for text extraction from images and documents.

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

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....

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...

Supports vision (images/videos), thinking mode, and Agent tasks. 256K context.

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...

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...

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...

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.

Fast GLM-4.7 variant with priority routing and higher concurrency. Same model as Flash, better infrastructure.

Free GLM-4.7 variant. Same model as FlashX but with limited concurrency (1 concurrent request) and lower priority.

Z.ai GLM 4.7 (355B) on Cerebras (~1,000 tok/s). Strong agentic coding, advanced reasoning (on by default), superior tool use. 131K context, 40K max output.

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...

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 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.

Latest-gen GLM model with 128K context. Thinking mode activated by default.

Gemini 3 Flash Preview (Version: 3-flash-preview-12-2025, Defaults: temperature=1, topP=0.95, topK=64, interfaces=[generateContent,countTokens,createCachedContent,batchGenerateContent])

Cost-efficient audio model. Accepts audio inputs and outputs via Chat Completions REST API.

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...

GPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on...

Smartest and most trustworthy option for difficult questions. Uses more compute for harder thinking on complex domains like programming.

GPT-5.2 Instant model, previously powering ChatGPT. Replaced by GPT-5.5 Instant.

GPT-5.2 optimized for long-horizon, agentic coding tasks in Codex or similar environments. Supports low, medium, high, and xhigh reasoning effort settings.

Most capable model for professional work and long-running agents. Improvements in general intelligence, long-context, agentic tool-calling, and vision.

Preview release (December 12th, 2025) of Deep Research Pro (Version: deepthink-exp-05-20, Defaults: temperature=1, topP=0.95, topK=64, interfaces=[generateContent,countTokens])

Mobile phone automation agent. Understands phone screens via multimodal perception and executes automated operations.

Official devstral-2512 Mistral AI model

Official devstral-2512 Mistral AI model

Official mistral-medium-latest Mistral AI model

Official devstral-2512 Mistral AI model

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...

Fast vision GLM-4.6 with priority routing and higher concurrency. Image/video/file inputs, 32K output.

Free vision GLM-4.6. Same model as FlashX but with limited concurrency (1 concurrent request). Image/video/file inputs, 32K output.

Vision-enabled GLM-4.6 model. Supports image/video/file inputs, 32K output, hybrid thinking.

Transform your natural language requests into structured OpenRouter API request objects. Describe what you want to accomplish with AI models, and Body Builder will construct the appropriate API calls. Example:...

Official mistral-large-2512 Mistral AI model

Official mistral-large-2512 Mistral AI model

Ministral 3 (a.k.a. Tinystral) 8B Instruct.

Ministral 3 (a.k.a. Tinystral) 3B Instruct.

Ministral 3 (a.k.a. Tinystral) 14B Instruct.

Ministral 3 (a.k.a. Tinystral) 8B Instruct.

Ministral 3 (a.k.a. Tinystral) 3B Instruct.

Ministral 3 (a.k.a. Tinystral) 14B Instruct.

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...

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...

Previous most intelligent model with advanced reasoning for complex agentic workflows

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...

Gemini 3 Pro Image Preview (Version: 3.0, Defaults: temperature=1, topP=0.95, topK=64, interfaces=[generateContent,countTokens,batchGenerateContent])

Gemini 3 Pro Image Preview (Version: 3.0, Defaults: temperature=1, topP=0.95, topK=64, interfaces=[generateContent,countTokens,batchGenerateContent])

Our most intelligent coding model optimized for long-horizon, agentic coding tasks.

Smaller, faster version of GPT-5.1 Codex for efficient coding tasks.

A version of GPT-5.1 optimized for agentic coding tasks in Codex or similar environments.

The best model for coding and agentic tasks with configurable reasoning effort.

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...

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...

GPT-5.1 Instant with adaptive reasoning. More conversational with improved instruction following.

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...

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.

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...

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...

OpenAI safety classification model (20B MoE). Purpose-built for content moderation with Harmony response format. 131K context, 65K max output. ~1000 t/s on Groq.

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...

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...

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,...

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...

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...

Fastest model with exceptional speed and performance

Qwen3-VL-8B-Thinking is the reasoning-optimized variant of the Qwen3-VL-8B multimodal model, designed for advanced visual and textual reasoning across complex scenes, documents, and temporal sequences. It integrates enhanced multimodal alignment and...

Qwen3-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...

Updated web search model in Chat Completions API. 60% cheaper with domain filtering support.

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...

Gemini 2.5 Computer Use Preview 10-2025 (Version: Gemini 2.5 Computer Use Preview 10-2025, Defaults: temperature=1, topP=0.95, topK=64, interfaces=[generateContent,countTokens])

Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM, math, and complex tasks. It excels...

Qwen3-VL-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...

Version of GPT-5 that uses more compute to produce smarter and more precise responses. Designed for tough problems.

Gemini 2.5 Flash Preview Image (Version: 2.0, Defaults: temperature=1, topP=0.95, topK=64, interfaces=[generateContent,countTokens,batchGenerateContent])

GLM-4.6 model with 128K context/output. Hybrid thinking: auto-determines whether to engage deep reasoning.

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...

Previous best combination of speed and intelligence for complex agents and coding

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

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...

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...

Alibaba model (not yet curated).

Alibaba model (not yet curated).

Alibaba model (not yet curated).

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...

Alibaba model (not yet curated).

Mistral Small 4.

Our frontier-class reasoning model release candidate September 2025.

Our efficient reasoning model released September 2025.

Our frontier-class reasoning model release candidate September 2025.

A version of GPT-5 optimized for agentic coding in Codex.

Alibaba model (not yet curated).

Alibaba model (not yet curated).

Balanced quality, speed, and cost with hybrid thinking. 1M context.

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...

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...

Lighter Groq agentic AI with web search, code execution. Pricing based on underlying model usage.

Groq agentic AI with web search, code execution, browser automation. Uses GPT-OSS 120B, Llama 4 Scout, Llama 3.3 70B. Pricing based on underlying model usage.

Alibaba model (not yet curated).

First generally available audio model. Accepts audio inputs and outputs, and can be used in the Chat Completions REST API.

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...

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...

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...

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...

Update on Mistral Medium 3 with improved capabilities.

Vision-enabled GLM-4.5 model. 96K context, 16K output, interleaved thinking.

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...

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

Fastest, most cost-efficient version of GPT-5 for summarization and classification tasks.

A faster, more cost-efficient version of GPT-5 for well-defined tasks.

GPT-5 model used in ChatGPT.

The best model for coding and agentic tasks across domains.

OpenAI flagship open-weight MoE (120B total, 5.1B active) on Cerebras (~3,000 tok/s). Reasoning (default medium effort) and function calling. 131K context, 40K max output.

Previous Opus model. Deprecated June 5, 2026, retiring August 5, 2026.

OpenAI efficient open-weight MoE (20B total, 3.6B active). Tool use, browser search, code execution. 131K context, 65K max output. ~1000 t/s on Groq.

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...

Our cutting-edge language model for coding released August 2025.

Our cutting-edge language model for coding released August 2025.

Alibaba model (not yet curated).

Extended GLM-4.5 model. Interleaved thinking.

Free GLM-4.5 variant with limited concurrency. Prior-gen, superseded by GLM-4.7 Flash.

Extended lightweight GLM-4.5 variant. Interleaved thinking.

Lightweight GLM-4.5 variant. Interleaved thinking.

Prior-gen GLM-4.5 model with 96K context/output. Interleaved thinking.

Alibaba model (not yet curated).

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...

Stable version of Gemini 2.5 Flash-Lite, released in July of 2025 (Version: 001, Defaults: temperature=1, topP=0.95, topK=64, interfaces=[generateContent,countTokens,createCachedContent,batchGenerateContent])

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...

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,...

A small audio understanding model released in July 2025

A mini audio understanding model released in July 2025

A small audio understanding model released in July 2025

A mini audio understanding model released in July 2025

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...

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...

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...

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...

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>...

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>...

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...

Faster, more affordable deep research model for complex, multi-step research tasks.

Our most powerful deep research model for complex, multi-step research tasks.

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...

Our latest enterprise-grade small model with the latest version released June 2025.

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...

Stable release (June 17th, 2025) of Gemini 2.5 Pro (Version: 2.5, Defaults: temperature=1, topP=0.95, topK=64, interfaces=[generateContent,countTokens,createCachedContent,batchGenerateContent])

Stable version of Gemini 2.5 Flash, our mid-size multimodal model that supports up to 1 million tokens, released in June of 2025. (Version: 001, Defaults: temperature=1, topP=0.95, topK=64, interfaces=[generateContent,countTokens,createCachedContent,batchGenerateContent])

Version of o3 with more compute for better responses. Provides consistently better answers for complex tasks.

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...

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 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...

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...

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...

Gemini 2.5 Pro Preview TTS (Version: gemini-2.5-pro-preview-tts-2025-05-19, Defaults: temperature=1, topP=0.95, topK=64, interfaces=[countTokens,generateContent,batchGenerateContent])

Gemini 2.5 Flash Preview TTS (Version: gemini-2.5-flash-exp-tts-2025-05-19, Defaults: temperature=1, topP=0.95, topK=64, interfaces=[countTokens,generateContent])

Official mistral-medium-latest Mistral AI model

Our frontier-class multimodal model released May 2025.

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...

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...

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...

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...

Alibaba model (not yet curated).

Alibaba model (not yet curated).

Alibaba model (not yet curated).

Alibaba model (not yet curated).

Alibaba model (not yet curated).