AI Model Intelligence Hub & Specifications

Auto Code is OpenRouter’s router built specifically for coding agents and harnesses. It uses the same routing engine as the [Auto Router](https://openrouter.ai/openrouter/auto), with every request treated as part of an...

Gemini Omni 1.2 Flash is Google's native multimodal video generation and editing model, the successor to Gemini Omni 1.1 Flash. It generates clips up to 15 seconds long with native...

Auto is OpenRouter’s flagship model router, built for general-purpose usage. It adapts to each request, choosing cost-optimal models and adjusting reasoning effort. It balances task difficulty, benchmark results, live prices,...

Gemini Omni 1.1 Flash is Google's native multimodal video generation and editing model, the generally available successor to Gemini Omni Flash Preview. It is suited for text-to-video, image-to-video, first and...

The official release of Hy4 delivers comprehensive and substantial improvements over Hy4 Preview, with particularly strong gains in agentic capabilities and performance across a wide range of long-horizon, real-world productivity...

GLM-5.3-FlashX-Legal (GLM-Legal) is Z.ai's legal-domain variant of GLM-5.3-FlashX, a native multimodal model that accepts text, image, and video input and produces text. It adds legal-domain mid-training and post-training with reinforcement...

GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. It is suited for everyday agentic, coding, and writing work, is particularly strong at understanding screenshots...

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

Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D...

MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity. It is built for complex,...

DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the `deepseek-flash` API model name. V4.1 Flash is a sparse mixture-of-experts model...

Mercury 3 is a diffusion-based language model from Inception, and the lab's most capable model to date. It is suited for agentic workflows and real-time applications where latency compounds, such...

Muse Spark Open is a coding-optimized open-weight model. Trained specifically for agentic coding workflows, it delivers higher first-attempt accuracy, reliable tool calling, and deep codebase understanding across the repos developers...

NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...

LFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liquid AI with 24B total and 2.45B active parameters. It always reasons before answering and is built for agents that call tools. Liquid...

Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across...

Muse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with...

Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and...

Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. It offers a 1M-token context window with up...

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 Nano Banana Pro. It improves product recontextualization,...

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

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

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

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

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

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

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

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

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

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

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

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

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

Switchyard is an open-source model routing system that switches between multiple models to optimize the cost of requests. By default it will use OpenRouter market data to select the most...

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

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

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

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

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

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

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

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

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

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

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

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

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

Ling 3.0 Flash Sante is an advanced artificial intelligence model engineered by Inclusion AI. Tailored for complex multi-step reasoning, programming synthesis, and extended document comprehension, Ling 3.0 Flash Sante represents a key architectural iteration in the Inclusion AI model family. First released in 2026-09-04, it serves enterprise developers, research teams, and autonomous system architects requiring strict instruction compliance. Featuring an input capacity of 262,144 tokens (approximately 350 words), Ling 3.0 Flash Sante processes multi-file code repositories, lengthy technical reports, and complex prompts in a single inference call.

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

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

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

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

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

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

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

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

Mercury 2.5 Preview is an advanced artificial intelligence model engineered by Inception AI. Tailored for complex multi-step reasoning, programming synthesis, and extended document comprehension, Mercury 2.5 Preview represents a key architectural iteration in the Inception AI model family. First released in 2026-08-31, it serves enterprise developers, research teams, and autonomous system architects requiring strict instruction compliance. Featuring an input capacity of 260,000 tokens (approximately 347 words), Mercury 2.5 Preview processes multi-file code repositories, lengthy technical reports, and complex prompts in a single inference call.

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

Ling 3.0 Flash Fin is an advanced artificial intelligence model engineered by Inclusion AI. Tailored for complex multi-step reasoning, programming synthesis, and extended document comprehension, Ling 3.0 Flash Fin represents a key architectural iteration in the Inclusion AI model family. First released in 2026-08-27, it serves enterprise developers, research teams, and autonomous system architects requiring strict instruction compliance. Featuring an input capacity of 262,144 tokens (approximately 350 words), Ling 3.0 Flash Fin processes multi-file code repositories, lengthy technical reports, and complex prompts in a single inference call.

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

Ling 3.0 Tiny is a mixture-of-experts model from InclusionAI, with 1.3B active parameters out of 7.9B total. It is designed for responsive agents, instruction following, and multi-turn conversations, with switchable...

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

Qwen3.8 Max is an advanced artificial intelligence model engineered by Alibaba. Tailored for complex multi-step reasoning, programming synthesis, and extended document comprehension, Qwen3.8 Max represents a key architectural iteration in the Alibaba model family. First released in 2026-08-03, it serves enterprise developers, research teams, and autonomous system architects requiring strict instruction compliance. Featuring an input capacity of 1,000,000 tokens (approximately 1,333 words), Qwen3.8 Max processes multi-file code repositories, lengthy technical reports, and complex prompts in a single inference call.

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

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

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

Claude Opus 5 (Fast) is an advanced artificial intelligence model engineered by Anthropic. Tailored for complex multi-step reasoning, programming synthesis, and extended document comprehension, Claude Opus 5 (Fast) represents a key architectural iteration in the Anthropic model family. First released in 2026-07-24, it serves enterprise developers, research teams, and autonomous system architects requiring strict instruction compliance. Featuring an input capacity of 1,000,000 tokens (approximately 1,333 words), Claude Opus 5 (Fast) processes multi-file code repositories, lengthy technical reports, and complex prompts in a single inference call.

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

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

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

Laguna S 2.1 is an advanced artificial intelligence model engineered by Poolside. Tailored for complex multi-step reasoning, programming synthesis, and extended document comprehension, Laguna S 2.1 represents a key architectural iteration in the Poolside model family. First released in 2026-07-21, it serves enterprise developers, research teams, and autonomous system architects requiring strict instruction compliance. Featuring an input capacity of 1,048,576 tokens (approximately 1,398 words), Laguna S 2.1 processes multi-file code repositories, lengthy technical reports, and complex prompts in a single inference call.

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

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

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

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

KAT-Coder-Pro V2.5 is an advanced artificial intelligence model engineered by Kuaishou. Tailored for complex multi-step reasoning, programming synthesis, and extended document comprehension, KAT-Coder-Pro V2.5 represents a key architectural iteration in the Kuaishou model family. First released in 2026-07-10, it serves enterprise developers, research teams, and autonomous system architects requiring strict instruction compliance. Featuring an input capacity of 262,144 tokens (approximately 350 words), KAT-Coder-Pro V2.5 processes multi-file code repositories, lengthy technical reports, and complex prompts in a single inference call.

KAT-Coder-Air V2.5 is an advanced artificial intelligence model engineered by Kuaishou. Tailored for complex multi-step reasoning, programming synthesis, and extended document comprehension, KAT-Coder-Air V2.5 represents a key architectural iteration in the Kuaishou model family. First released in 2026-07-10, it serves enterprise developers, research teams, and autonomous system architects requiring strict instruction compliance. Featuring an input capacity of 256,000 tokens (approximately 341 words), KAT-Coder-Air V2.5 processes multi-file code repositories, lengthy technical reports, and complex prompts in a single inference call.

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

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

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

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

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

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

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

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

Laguna XS 2.1 is an advanced artificial intelligence model engineered by Poolside. Tailored for complex multi-step reasoning, programming synthesis, and extended document comprehension, Laguna XS 2.1 represents a key architectural iteration in the Poolside model family. First released in 2026-07-02, it serves enterprise developers, research teams, and autonomous system architects requiring strict instruction compliance. Featuring an input capacity of 262,144 tokens (approximately 350 words), Laguna XS 2.1 processes multi-file code repositories, lengthy technical reports, and complex prompts in a single inference call.

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

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

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...

Nex-N2-Mini is an advanced artificial intelligence model engineered by Nex AGI. Tailored for complex multi-step reasoning, programming synthesis, and extended document comprehension, Nex-N2-Mini represents a key architectural iteration in the Nex AGI model family. First released in 2026-06-24, it serves enterprise developers, research teams, and autonomous system architects requiring strict instruction compliance. Featuring an input capacity of 262,144 tokens (approximately 350 words), Nex-N2-Mini processes multi-file code repositories, lengthy technical reports, and complex prompts in a single inference call.

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...

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...

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,...

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...

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...

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...

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

Nex-N2-Pro is an advanced artificial intelligence model engineered by Nex AGI. Tailored for complex multi-step reasoning, programming synthesis, and extended document comprehension, Nex-N2-Pro represents a key architectural iteration in the Nex AGI model family. First released in 2026-06-08, it serves enterprise developers, research teams, and autonomous system architects requiring strict instruction compliance. Featuring an input capacity of 262,144 tokens (approximately 350 words), Nex-N2-Pro processes multi-file code repositories, lengthy technical reports, and complex prompts in a single inference call.

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...

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...

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...

Claude Opus 4.8 (Fast) is an advanced artificial intelligence model engineered by Anthropic. Tailored for complex multi-step reasoning, programming synthesis, and extended document comprehension, Claude Opus 4.8 (Fast) represents a key architectural iteration in the Anthropic model family. First released in 2026-05-27, it serves enterprise developers, research teams, and autonomous system architects requiring strict instruction compliance. Featuring an input capacity of 1,000,000 tokens (approximately 1,333 words), Claude Opus 4.8 (Fast) processes multi-file code repositories, lengthy technical reports, and complex prompts in a single inference call.

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...

Llama 4 Maverick is an advanced artificial intelligence model engineered by Meta. Tailored for complex multi-step reasoning, programming synthesis, and extended document comprehension, Llama 4 Maverick represents a key architectural iteration in the Meta model family. First released in 2026-05-25, it serves enterprise developers, research teams, and autonomous system architects requiring strict instruction compliance. Featuring an input capacity of 1,048,576 tokens (approximately 1,398 words), Llama 4 Maverick processes multi-file code repositories, lengthy technical reports, and complex prompts in a single inference call.

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,...

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

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...

Claude Opus 4.7 (Fast) is an advanced artificial intelligence model engineered by Anthropic. Tailored for complex multi-step reasoning, programming synthesis, and extended document comprehension, Claude Opus 4.7 (Fast) represents a key architectural iteration in the Anthropic model family. First released in 2026-05-12, it serves enterprise developers, research teams, and autonomous system architects requiring strict instruction compliance. Featuring an input capacity of 1,000,000 tokens (approximately 1,333 words), Claude Opus 4.7 (Fast) processes multi-file code repositories, lengthy technical reports, and complex prompts in a single inference call.

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...

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...

Grok 4.20 is an advanced artificial intelligence model engineered by xAI. Tailored for complex multi-step reasoning, programming synthesis, and extended document comprehension, Grok 4.20 represents a key architectural iteration in the xAI model family. First released in 2026-05-05, it serves enterprise developers, research teams, and autonomous system architects requiring strict instruction compliance. Featuring an input capacity of 2,000,000 tokens (approximately 2,667 words), Grok 4.20 processes multi-file code repositories, lengthy technical reports, and complex prompts in a single inference call.

Granite 4.1 8B is an advanced artificial intelligence model engineered by IBM. Tailored for complex multi-step reasoning, programming synthesis, and extended document comprehension, Granite 4.1 8B represents a key architectural iteration in the IBM model family. First released in 2026-04-30, it serves enterprise developers, research teams, and autonomous system architects requiring strict instruction compliance. Featuring an input capacity of 131,072 tokens (approximately 175 words), Granite 4.1 8B processes multi-file code repositories, lengthy technical reports, and complex prompts in a single inference call.

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...

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

Laguna M.1 is an advanced artificial intelligence model engineered by Poolside. Tailored for complex multi-step reasoning, programming synthesis, and extended document comprehension, Laguna M.1 represents a key architectural iteration in the Poolside model family. First released in 2026-04-28, it serves enterprise developers, research teams, and autonomous system architects requiring strict instruction compliance. Featuring an input capacity of 262,144 tokens (approximately 350 words), Laguna M.1 processes multi-file code repositories, lengthy technical reports, and complex prompts in a single inference call.

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

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

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

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

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

Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...

Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a 1M token context window. Tiered pricing kicks in...

Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text output, with a 1M token context window. This...

Anthropic Claude Haiku Latest is an advanced artificial intelligence model engineered by Anthropic. Tailored for complex multi-step reasoning, programming synthesis, and extended document comprehension, Anthropic Claude Haiku Latest represents a key architectural iteration in the Anthropic model family. First released in 2026-04-27, it serves enterprise developers, research teams, and autonomous system architects requiring strict instruction compliance. Featuring an input capacity of 200,000 tokens (approximately 267 words), Anthropic Claude Haiku Latest processes multi-file code repositories, lengthy technical reports, and complex prompts in a single inference call.

Qwen3.6 Max Preview is an advanced artificial intelligence model engineered by Alibaba. Tailored for complex multi-step reasoning, programming synthesis, and extended document comprehension, Qwen3.6 Max Preview represents a key architectural iteration in the Alibaba model family. First released in 2026-04-27, it serves enterprise developers, research teams, and autonomous system architects requiring strict instruction compliance. Featuring an input capacity of 262,144 tokens (approximately 350 words), Qwen3.6 Max Preview processes multi-file code repositories, lengthy technical reports, and complex prompts in a single inference call.

Google Gemini Pro Latest is an advanced artificial intelligence model engineered by Google. Tailored for complex multi-step reasoning, programming synthesis, and extended document comprehension, Google Gemini Pro Latest represents a key architectural iteration in the Google model family. First released in 2026-04-27, it serves enterprise developers, research teams, and autonomous system architects requiring strict instruction compliance. Featuring an input capacity of 1,048,576 tokens (approximately 1,398 words), Google Gemini Pro Latest processes multi-file code repositories, lengthy technical reports, and complex prompts in a single inference call.

Google Gemini Flash Latest is an advanced artificial intelligence model engineered by Google. Tailored for complex multi-step reasoning, programming synthesis, and extended document comprehension, Google Gemini Flash Latest represents a key architectural iteration in the Google model family. First released in 2026-04-27, it serves enterprise developers, research teams, and autonomous system architects requiring strict instruction compliance. Featuring an input capacity of 1,048,576 tokens (approximately 1,398 words), Google Gemini Flash Latest processes multi-file code repositories, lengthy technical reports, and complex prompts in a single inference call.

MoonshotAI Kimi Latest is an advanced artificial intelligence model engineered by Moonshot AI. Tailored for complex multi-step reasoning, programming synthesis, and extended document comprehension, MoonshotAI Kimi Latest represents a key architectural iteration in the Moonshot AI model family. First released in 2026-04-27, it serves enterprise developers, research teams, and autonomous system architects requiring strict instruction compliance. Featuring an input capacity of 1,048,576 tokens (approximately 1,398 words), MoonshotAI Kimi Latest processes multi-file code repositories, lengthy technical reports, and complex prompts in a single inference call.

Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text, image, and video inputs...

Anthropic Claude Sonnet Latest is an advanced artificial intelligence model engineered by Anthropic. Tailored for complex multi-step reasoning, programming synthesis, and extended document comprehension, Anthropic Claude Sonnet Latest represents a key architectural iteration in the Anthropic model family. First released in 2026-04-27, it serves enterprise developers, research teams, and autonomous system architects requiring strict instruction compliance. Featuring an input capacity of 1,000,000 tokens (approximately 1,333 words), Anthropic Claude Sonnet Latest processes multi-file code repositories, lengthy technical reports, and complex prompts in a single inference call.

DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...

DeepSeek V4 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...

GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K output) with support for...

DeepSeek V4 Flash is an advanced artificial intelligence model engineered by DeepSeek. Tailored for complex multi-step reasoning, programming synthesis, and extended document comprehension, DeepSeek V4 Flash represents a key architectural iteration in the DeepSeek model family. First released in 2026-04-24, it serves enterprise developers, research teams, and autonomous system architects requiring strict instruction compliance. Featuring an input capacity of 1,048,576 tokens (approximately 1,398 words), DeepSeek V4 Flash processes multi-file code repositories, lengthy technical reports, and complex prompts in a single inference call.

GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...

DeepSeek V4 Pro is an advanced artificial intelligence model engineered by DeepSeek. Tailored for complex multi-step reasoning, programming synthesis, and extended document comprehension, DeepSeek V4 Pro represents a key architectural iteration in the DeepSeek model family. First released in 2026-04-24, it serves enterprise developers, research teams, and autonomous system architects requiring strict instruction compliance. Featuring an input capacity of 1,048,576 tokens (approximately 1,398 words), DeepSeek V4 Pro processes multi-file code repositories, lengthy technical reports, and complex prompts in a single inference call.

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...

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

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

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

Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...

Gemini 3.1 Flash is an advanced artificial intelligence model engineered by Google. Tailored for complex multi-step reasoning, programming synthesis, and extended document comprehension, Gemini 3.1 Flash represents a key architectural iteration in the Google model family. First released in 2026-04-20, it serves enterprise developers, research teams, and autonomous system architects requiring strict instruction compliance. Featuring an input capacity of 1,000,000 tokens (approximately 1,333 words), Gemini 3.1 Flash processes multi-file code repositories, lengthy technical reports, and complex prompts in a single inference call.

Gemini 3.1 Pro is an advanced artificial intelligence model engineered by Google. Tailored for complex multi-step reasoning, programming synthesis, and extended document comprehension, Gemini 3.1 Pro represents a key architectural iteration in the Google model family. First released in 2026-04-20, it serves enterprise developers, research teams, and autonomous system architects requiring strict instruction compliance. Featuring an input capacity of 2,000,000 tokens (approximately 2,667 words), Gemini 3.1 Pro processes multi-file code repositories, lengthy technical reports, and complex prompts in a single inference call.

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...

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...

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...

Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it delivers...

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...

GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, excels at long-horizon planning, complex coding,...

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

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

KAT-Coder-Pro V2 is an advanced artificial intelligence model engineered by Kuaishou. Tailored for complex multi-step reasoning, programming synthesis, and extended document comprehension, KAT-Coder-Pro V2 represents a key architectural iteration in the Kuaishou model family. First released in 2026-03-27, it serves enterprise developers, research teams, and autonomous system architects requiring strict instruction compliance. Featuring an input capacity of 262,144 tokens (approximately 350 words), KAT-Coder-Pro V2 processes multi-file code repositories, lengthy technical reports, and complex prompts in a single inference call.

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...

GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding,...

GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency...

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...

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...

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...

GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K...

GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for...

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 advanced artificial intelligence model engineered by OpenAI. Tailored for complex multi-step reasoning, programming synthesis, and extended document comprehension, GPT-5.3 Chat represents a key architectural iteration in the OpenAI model family. First released in 2026-03-03, it serves enterprise developers, research teams, and autonomous system architects requiring strict instruction compliance. Featuring an input capacity of 128,000 tokens (approximately 171 words), GPT-5.3 Chat processes multi-file code repositories, lengthy technical reports, and complex prompts in a single inference call.

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,...

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...

The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall...

The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its overall capabilities are comparable to those of...

The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of...

GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2. It achieves state-of-the-art results...

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...

The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers...

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...

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...

Qwen3 Max Thinking is an advanced artificial intelligence model engineered by Alibaba. Tailored for complex multi-step reasoning, programming synthesis, and extended document comprehension, Qwen3 Max Thinking represents a key architectural iteration in the Alibaba model family. First released in 2026-02-09, it serves enterprise developers, research teams, and autonomous system architects requiring strict instruction compliance. Featuring an input capacity of 262,144 tokens (approximately 350 words), Qwen3 Max Thinking processes multi-file code repositories, lengthy technical reports, and complex prompts in a single inference call.

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...

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...

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 an advanced artificial intelligence model engineered by Upstage. Tailored for complex multi-step reasoning, programming synthesis, and extended document comprehension, Solar Pro 3 represents a key architectural iteration in the Upstage model family. First released in 2026-01-27, it serves enterprise developers, research teams, and autonomous system architects requiring strict instruction compliance. Featuring an input capacity of 131,072 tokens (approximately 175 words), Solar Pro 3 processes multi-file code repositories, lengthy technical reports, and complex prompts in a single inference call.

Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed...

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...

As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning,...

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...

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...

Doubao Pro is an advanced artificial intelligence model engineered by ByteDance. Tailored for complex multi-step reasoning, programming synthesis, and extended document comprehension, Doubao Pro represents a key architectural iteration in the ByteDance model family. First released in 2026-01-15, it serves enterprise developers, research teams, and autonomous system architects requiring strict instruction compliance. Featuring an input capacity of 256,000 tokens (approximately 341 words), Doubao Pro processes multi-file code repositories, lengthy technical reports, and complex prompts in a single inference call.

GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....

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.

GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while...

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 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly...

GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning,...

GPT-5.2 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...

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...

GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K tokens, processes complex page layouts...

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...

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...

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...

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

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

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.

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...

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...

GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning...

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

GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....

GPT-5.1 Chat is an advanced artificial intelligence model engineered by OpenAI. Tailored for complex multi-step reasoning, programming synthesis, and extended document comprehension, GPT-5.1 Chat represents a key architectural iteration in the OpenAI model family. First released in 2025-11-13, it serves enterprise developers, research teams, and autonomous system architects requiring strict instruction compliance. Featuring an input capacity of 128,000 tokens (approximately 171 words), GPT-5.1 Chat processes multi-file code repositories, lengthy technical reports, and complex prompts in a single inference call.

Qwen 2.5-Coder 32B is an advanced artificial intelligence model engineered by Alibaba. Tailored for complex multi-step reasoning, programming synthesis, and extended document comprehension, Qwen 2.5-Coder 32B represents a key architectural iteration in the Alibaba model family. First released in 2025-11-12, it serves enterprise developers, research teams, and autonomous system architects requiring strict instruction compliance. Featuring an input capacity of 131,072 tokens (approximately 175 words), Qwen 2.5-Coder 32B processes multi-file code repositories, lengthy technical reports, and complex prompts in a single inference call.

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...

Hunyuan Pro is an advanced artificial intelligence model engineered by Tencent. Tailored for complex multi-step reasoning, programming synthesis, and extended document comprehension, Hunyuan Pro represents a key architectural iteration in the Tencent model family. First released in 2025-11-01, it serves enterprise developers, research teams, and autonomous system architects requiring strict instruction compliance. Featuring an input capacity of 256,000 tokens (approximately 341 words), Hunyuan Pro processes multi-file code repositories, lengthy technical reports, and complex prompts in a single inference call.

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...

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...

Qwen3 VL 32B Instruct is an advanced artificial intelligence model engineered by Alibaba. Tailored for complex multi-step reasoning, programming synthesis, and extended document comprehension, Qwen3 VL 32B Instruct represents a key architectural iteration in the Alibaba model family. First released in 2025-10-23, it serves enterprise developers, research teams, and autonomous system architects requiring strict instruction compliance. Featuring an input capacity of 131,072 tokens (approximately 175 words), Qwen3 VL 32B Instruct processes multi-file code repositories, lengthy technical reports, and complex prompts in a single inference call.

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 Micro is an advanced artificial intelligence model engineered by IBM. Tailored for complex multi-step reasoning, programming synthesis, and extended document comprehension, Granite 4.0 Micro represents a key architectural iteration in the IBM model family. First released in 2025-10-20, it serves enterprise developers, research teams, and autonomous system architects requiring strict instruction compliance. Featuring an input capacity of 131,000 tokens (approximately 175 words), Granite 4.0 Micro processes multi-file code repositories, lengthy technical reports, and complex prompts in a single inference call.

GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by [GPT-5 Mini](https://openrouter.ai/openai/gpt-5-mini), with GPT Image 1 Mini for efficient image generation. This natively multimodal model features superior instruction following, text...

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...

[GPT-5](https://openrouter.ai/openai/gpt-5) Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities. It offers major improvements in reasoning, code quality, and user experience while incorporating GPT Image 1's superior instruction following,...

Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features improved multimodal fusion with Interleaved-MRoPE for long-horizon...

Qwen3 VL 8B Thinking is an advanced artificial intelligence model engineered by Alibaba. Tailored for complex multi-step reasoning, programming synthesis, and extended document comprehension, Qwen3 VL 8B Thinking represents a key architectural iteration in the Alibaba model family. First released in 2025-10-14, it serves enterprise developers, research teams, and autonomous system architects requiring strict instruction compliance. Featuring an input capacity of 131,072 tokens (approximately 175 words), Qwen3 VL 8B Thinking processes multi-file code repositories, lengthy technical reports, and complex prompts in a single inference call.

o4 Mini Deep Research is an advanced artificial intelligence model engineered by OpenAI. Tailored for complex multi-step reasoning, programming synthesis, and extended document comprehension, o4 Mini Deep Research represents a key architectural iteration in the OpenAI model family. First released in 2025-10-10, it serves enterprise developers, research teams, and autonomous system architects requiring strict instruction compliance. Featuring an input capacity of 200,000 tokens (approximately 267 words), o4 Mini Deep Research processes multi-file code repositories, lengthy technical reports, and complex prompts in a single inference call.