nRouter for AI Crawlers

nRouter is a managed LLM gateway: one OpenAI-compatible API key reaches every model in the catalogue, with routing, failover, guardrails, budgets and exact cost tracking handled by the gateway. This page is a plain, text-only index of the site for AI crawlers, agents and low-bandwidth access. It lists the models in the live catalogue by modality, the provider clouds behind them, and the product, use-case and documentation pages, each with a short description and a canonical link.

For a shorter machine-readable overview see /llms.txt. For the full text see /llms-full.txt. For the complete list of URLs see /sitemap.xml. Every model page also has a plain-text twin at /models/{model}/llms.txt.

Site

• Models — Every model served through the gateway, with specs and exact list pricing.
• Leaderboard — Models plotted on a price-versus-performance frontier from live benchmark data.
• Pricing — Pay as you go. Models are served at exact provider list price with a 0% platform fee.
• Documentation — API reference, SDKs, frameworks and guides for building on the gateway.
• Blog — Engineering deep dives, guides and company posts from the nRouter team.
• Help Center — The fastest path to an answer: channels, quick answers and support tiers.
• Support — Open a support ticket for account, billing and API issues.
• Enterprise — Dedicated tenancy, security review support and custom terms for large teams.
• Book a demo — A live walkthrough of the gateway with the team.
• Status — Per-component health for the gateway, dashboard and providers, with incident history.

Chat models

• Claude Fable 5 — Claude Fable 5 is a multimodal foundation model supporting text and image inputs with a 1,000,000-token context window and 128,000 max output tokens. It features a January 2026 knowledge cutoff for agentic workflows.
• Claude Fable 5 — Anthropic language model featuring a 1,000,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Claude Fable 5 1 — Anthropic language model featuring a extended context window. Engineered for dialogue, instruction following, and versatile text generation.
• Claude Haiku 4 5 — Anthropic language model featuring a 200,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Claude Haiku 4 5 20251001 — Claude Haiku 4.5 is a fast, lightweight multimodal model designed for low-latency tasks, high-volume user experiences, and real-time coding assistance.
• Claude Opus 4 5 20251101 — Claude Opus 4.5 is an intelligent reasoning model designed for multi-day software development tasks, autonomous agents, and deep analytical research.
• Claude Opus 4 6 — Claude Opus 4.6 is a multimodal coding and reasoning model with a 1,000,000-token context window and a 128,000 max output token limit. It processes text and image inputs for large codebases and complex agent operations.
• Claude Opus 4 7 — Anthropic language model featuring a 1,000,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Claude Opus 4 7 — Claude Opus 4.7 is a deep reasoning model with an upgraded tokenizer and high-resolution vision, engineered for long-horizon software engineering and interface design.
• Claude Opus 4 8 — Anthropic language model featuring a 1,000,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Claude Opus 4 8 — Claude Opus 4.8 is an enterprise-grade model built for sustained collaboration, dynamic workflow execution, and large-scale architectural problem solving.
• Claude Opus 5 — Claude Opus 5 is a multimodal foundation model supporting text and image inputs with a 1,000,000-token context window and 128,000 max output tokens. It has a May 2026 knowledge cutoff for multi-stage software engineering.
• Claude Opus 5 — Anthropic language model featuring a 1,000,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Claude Opus 5 5 — Anthropic language model featuring a 1,000,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Claude Opus 5 5 — Anthropic language model featuring a 1,000,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Claude Sonnet 4 6 — Claude Sonnet 4.6 provides balanced speed and intelligence with a 1M token context window, designed for enterprise software engineering and agentic planning.
• Claude Sonnet 4 6 — Anthropic language model featuring a 1,000,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Claude Sonnet 5 — Claude Sonnet 5 is a multimodal foundation model offering a 1,000,000-token context window and 128,000 max output tokens. It supports text and image inputs with a January 2026 knowledge cutoff for production workflows.
• Claude Sonnet 5 — Anthropic language model featuring a 1,000,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Claude Sonnet 5 5 — Anthropic language model featuring a 1,000,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Claude Sonnet 5 5 — Anthropic language model featuring a 1,000,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• DeepSeek R1 0528 — deepseek-ai language model featuring a 163,840-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Deepseek R1 0528 Maas — DeepSeek language model featuring a extended context window. Engineered for dialogue, instruction following, and versatile text generation.
• DeepSeek V3 — deepseek-ai language model featuring a 163,840-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• DeepSeek V3.1 — deepseek-ai language model featuring a 163,840-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Deepseek V3.2 — DeepSeek-V3.2 is an open-weights Mixture-of-Experts language model featuring DeepSeek Sparse Attention for efficient long-context reasoning. It offers extended context handling and structured tool calling for complex conversational and agentic workflows.
• DeepSeek V3.2 — deepseek-ai language model featuring a 163,840-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Deepseek V3.2 Maas — DeepSeek language model featuring a extended context window. Engineered for dialogue, instruction following, and versatile text generation.
• Deepseek V4 Flash — DeepSeek-V4-Flash is a high-efficiency Mixture-of-Experts model with 284B total and 13B activated parameters supporting up to a 1M-token context window. Optimized for low latency, it features hybrid sparse attention and dual-mode reasoning capabilities.
• DeepSeek V4 Flash — deepseek-ai language model featuring a 1,048,576-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Deepseek V4 Flash 0731 — DeepSeek-V4-Flash-0731 is the production release of DeepSeek-V4-Flash, incorporating an integrated speculative decoding module. It delivers enhanced agentic performance, tool execution, and code synthesis across a 1M-token context window.
• DeepSeek V4 Flash 0731 — deepseek-ai language model featuring a 1,048,576-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• DeepSeek V4 Flash Vision Exp — deepseek-ai language model featuring a 1,048,576-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Deepseek V4 Pro — DeepSeek-V4-Pro is a text model with a 1,048,576-token context window, 393,216 max output tokens, evaluated at 87.5 on MMLU-Pro, 90.1 on GPQA Diamond, and 80.6 on SWE-bench Verified.
• DeepSeek V4 Pro — deepseek-ai language model featuring a 1,048,576-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Deepseek V4 Pro 0813 — DeepSeek-V4-Pro-0813 is the production release of the DeepSeek-V4-Pro architecture, pairing 1.6T MoE parameters with a DSpark speculative decoding engine for accelerated agentic execution, full-stack software engineering, and deep logical reasoning.
• DeepSeek V4 Pro 0813 — deepseek-ai language model featuring a 1,048,576-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Deepseek V4.1 Flash — DeepSeek language model featuring a 1,000,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• DeepSeek V4.1 Flash — deepseek-ai language model featuring a 1,048,576-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Devstral 2 123b — Mistral AI language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Gemini 1.5 Flash 002 — Google language model featuring a extended context window. Engineered for dialogue, instruction following, and versatile text generation.
• Gemini 1.5 Flash 8b — Google language model featuring a extended context window. Engineered for dialogue, instruction following, and versatile text generation.
• Gemini 1.5 Pro 002 — Google language model featuring a extended context window. Engineered for dialogue, instruction following, and versatile text generation.
• Gemini 2.0 Flash — Google language model featuring a extended context window. Engineered for dialogue, instruction following, and versatile text generation.
• Gemini 2.0 Flash Lite — Google language model featuring a extended context window. Engineered for dialogue, instruction following, and versatile text generation.
• Gemini 2.5 Flash — Google language model featuring a 1,000,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Gemini 2.5 Pro — Google language model featuring a 1,000,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Gemini 3 Flash Preview — Google language model featuring a extended context window. Engineered for dialogue, instruction following, and versatile text generation.
• Gemini 3.1 Flash Lite — Gemini 3.1 Flash-Lite is Google's lightweight multimodal foundation model for high-throughput tasks. It processes up to 1,048,576 input tokens across text, audio, video, image, and PDF, with 65,536 max output tokens for translation, transcription, and classification.
• Gemini 3.1 Flash Lite — Google language model featuring a 1,000,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Gemini 3.1 Pro — Google language model featuring a 1,048,576-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Gemini 3.1 Pro — Google language model featuring a 1,000,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Gemini 3.5 Flash — Google language model featuring a 1,000,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Gemini 3.5 Flash — Google language model featuring a 1,048,576-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Gemini 3.5 Flash Lite — Google language model featuring a 1,048,576-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Gemini 3.5 Live Translate Preview — Google language model featuring a extended context window. Engineered for dialogue, instruction following, and versatile text generation.
• Gemini 3.6 Flash — Google language model featuring a 1,048,576-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Gemini 3.7 Flash — Google language model featuring a 1,000,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Gemini 3.7 Flash — Google language model featuring a 1,048,576-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Gemini 3.8 Flash — Google language model featuring a 1,048,576-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Gemma 3 12b It — Google language model featuring a 131,072-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Gemma 3 12b It — Google language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Gemma 3 27b It — Google language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Gemma 3 27b It — Google language model featuring a 131,072-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Gemma 3 4b It — Google language model featuring a 131,072-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Gemma 3 4b It — Google language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Gemma 4 26B A4B It — Google language model featuring a 262,144-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Gemma 4 31B It — Google language model featuring a 262,144-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Gemma 4 31B It Turbo — Google language model featuring a 262,144-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Gemma 4 31B It Ultra — Google language model featuring a 131,072-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• GLM 4.6 — zai-org language model featuring a 202,752-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Glm 4.7 — Z-AI language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• GLM 4.7 — zai-org language model featuring a 202,752-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Glm 4.7 Flash — Z-AI language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Glm 4.7 Maas — Z-AI language model featuring a extended context window. Engineered for dialogue, instruction following, and versatile text generation.
• Glm 5 — Z-AI language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Glm 5 Maas — Z-AI language model featuring a extended context window. Engineered for dialogue, instruction following, and versatile text generation.
• Glm 5.1 — Z-AI language model featuring a 200,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Glm 5.2 — Z-AI language model featuring a 1,000,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• GLM 5.2 — zai-org language model featuring a 1,048,576-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Glm 5.2 Fast Preview — Z-AI language model featuring a extended context window. Engineered for dialogue, instruction following, and versatile text generation.
• Glm 5.2 Maas — Z-AI language model featuring a extended context window. Engineered for dialogue, instruction following, and versatile text generation.
• GLM 5.3 — zai-org language model featuring a 1,048,576-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• GLM 5.3 Flash — zai-org language model featuring a 1,048,576-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Gpt 3.5 Turbo — OpenAI's legacy compact language model optimized for conversational interactions and general text completion tasks.
• Gpt 3.5 Turbo 0125 — Updated snapshot of GPT-3.5 Turbo with improved instruction following, higher accuracy at responding in requested formats, and bug fixes.
• Gpt 3.5 Turbo 16k — Legacy 16K context variant of GPT-3.5 Turbo offering expanded token capacity for longer text processing tasks.
• Gpt 4 — OpenAI foundation language model for text synthesis and coding tasks with an 8,192-token context window and matching 8,192 max output token limit. It features a December 2023 knowledge cutoff.
• Gpt 4 0613 — Snapshot of GPT-4 introduced in June 2023 with function calling support and improved steering capabilities.
• Gpt 4 Turbo — High-capability multimodal GPT-4 model featuring a 128K token context window and vision processing capabilities.
• Gpt 4 Turbo 2024 04 09 — Generally available GPT-4 Turbo with Vision snapshot supporting structured JSON, parallel tool calling, and multimodal inputs.
• Gpt 4.1 — Multimodal language model featuring a 1,047,576-token context window and a 32,768-token output limit. It supports text and image inputs with a June 2024 knowledge cutoff.
• Gpt 4.1 2025 04 14 — Primary snapshot of GPT-4.1 offering million-token context processing, multimodal inputs, and high-volume reasoning support.
• Gpt 4.1 Mini — Cost-efficient compact variant of GPT-4.1 delivering million-token context capacity with optimized latency and token throughput.
• Gpt 4.1 Mini 2025 04 14 — Snapshot of GPT-4.1 Mini providing 1,047,576 context tokens and high-speed execution for lightweight reasoning and data parsing.
• Gpt 4.1 Nano — Ultra-compact edition of GPT-4.1 built for minimal token cost and low latency operations while maintaining 1M token context support.
• Gpt 4.1 Nano 2025 04 14 — Dated release of GPT-4.1 Nano combining sub-dollar token economics with large-context ingestion and rapid classification capability.
• Gpt 4o — OpenAI omni model supporting text and image inputs with a 128,000-token context window and 16,384 max output tokens. It provides structured outputs and carries an October 2023 knowledge cutoff.
• Gpt 4o 2024 05 13 — Original launch snapshot of GPT-4o offering multimodal text and vision input capabilities with 4,096 max output tokens.
• Gpt 4o 2024 08 06 — Enhanced GPT-4o snapshot introducing Structured Outputs with 100% schema reliability and increased 16,384 token output limits.
• Gpt 4o 2024 11 20 — Refined GPT-4o checkpoint with improved creative writing naturalness, structured responses, and file analysis capabilities.
• Gpt 4o Mini — Fast and lightweight multimodal model designed for high-volume tasks, offering 128K context window at low inference costs.
• Gpt 4o Mini 2024 07 18 — Launch snapshot of GPT-4o Mini optimized for low-latency chat, structured document extraction, and high-frequency API calls.
• Gpt 5 — Multimodal reasoning model supporting text and image inputs with a 400,000-token context window and 128,000 max output tokens. It is designed for multi-step coding and mathematical derivation with a September 2024 knowledge cutoff.
• Gpt 5 2025 08 07 — OpenAI's August 7, 2025 production snapshot of GPT-5, providing deep reasoning capabilities across a 400,000-token context window with configurable reasoning effort for complex coding, math, and agentic workflows.
• Gpt 5 Mini — Cost-sensitive reasoning model delivering strong logical inference with reduced latency for high-volume automated workflows.
• Gpt 5 Mini 2025 08 07 — Initial snapshot of GPT-5 Mini featuring 400K context capacity and up to 128K generation tokens for cost-efficient reasoning.
• Gpt 5 Nano — Compact reasoning model designed for high-throughput, low-cost analytical evaluation and lightweight reasoning tasks.
• Gpt 5 Nano 2025 08 07 — Snapshot of GPT-5 Nano offering 400K context input support and fast inference for cost-sensitive automation pipelines.
• Gpt 5 Search Api — Specialized GPT-5 model variant designed for web search execution via the Chat Completions API, supporting a 200,000-token context window with automated search retrieval before generating completions.
• Gpt 5 Search Api 2025 10 14 — OpenAI advanced reasoning model. Utilizes structured deliberation tokens for multi-step reasoning, mathematical problem solving, and complex logic.
• Gpt 5.1 — OpenAI reasoning model supporting text and image inputs with a 400,000-token context window and 128,000 max output tokens. It supports multi-step logic and software engineering with a September 2024 knowledge cutoff.
• Gpt 5.1 2025 11 13 — Snapshot of GPT-5.1 featuring 400K context input and 128K output limits for reliable production agent deployment.
• Gpt 5.2 — OpenAI reasoning model designed for agentic workflows and multi-turn problem solving across a 400,000-token context window. It supports text and image inputs with 128,000 max output tokens and an August 2025 knowledge cutoff.
• Gpt 5.2 2025 12 11 — Pinned snapshot of GPT-5.2 released on December 11, 2025, offering deterministic reasoning behavior and 400K token context capacity for production systems.
• Gpt 5.2 Pro — OpenAI advanced reasoning model. Utilizes structured deliberation tokens for multi-step reasoning, mathematical problem solving, and complex logic.
• Gpt 5.2 Pro 2025 12 11 — OpenAI advanced reasoning model. Utilizes structured deliberation tokens for multi-step reasoning, mathematical problem solving, and complex logic.
• Gpt 5.3 Codex — OpenAI's specialized reasoning model fine-tuned for agentic software engineering and long-horizon programming tasks in Codex, featuring a 400,000-token context window and up to 128,000 output tokens.
• Gpt 5.4 — High-efficiency OpenAI reasoning model with an expanded 1.05M token context window, suited for extensive codebases, deep reasoning, and computer-use tasks.
• Gpt 5.4 2026 03 05 — Deterministic snapshot of GPT-5.4 from March 5, 2026, featuring a 1,050,000-token context window and 128,000 max output tokens. It processes text and image inputs with an August 2025 knowledge cutoff.
• Gpt 5.4 Mini — Lightweight OpenAI reasoning model engineered for coding, computer control, and fast subagent execution with 400K context tokens.
• Gpt 5.4 Mini 2026 03 17 — Specific snapshot of GPT-5.4 Mini from March 17, 2026, delivering balanced reasoning performance and 400K context capacity at reduced inference latency.
• Gpt 5.4 Nano — Compact and cost-efficient OpenAI reasoning model tailored for high-throughput filtering, summarization, and lightweight classification tasks.
• Gpt 5.4 Nano 2026 03 17 — March 17, 2026 snapshot of GPT-5.4 Nano offering rapid response times and 400K context processing for high-volume, budget-conscious production workloads.
• Gpt 5.4 Pro — OpenAI advanced reasoning model. Utilizes structured deliberation tokens for multi-step reasoning, mathematical problem solving, and complex logic.
• Gpt 5.4 Pro 2026 03 05 — OpenAI advanced reasoning model. Utilizes structured deliberation tokens for multi-step reasoning, mathematical problem solving, and complex logic.
• Gpt 5.5 — OpenAI multimodal model supporting text and image inputs with a 1.05M token context window, 128K max output tokens, and knowledge cutoff of December 2025.
• Gpt 5.5 2026 04 23 — Fixed snapshot of GPT-5.5 dated April 23, 2026, providing stable reasoning outputs and 1.05 million token context limits for production pipelines.
• Gpt 5.6 Luna — OpenAI advanced reasoning model. Utilizes structured deliberation tokens for multi-step reasoning, mathematical problem solving, and complex logic.
• Gpt 5.6 Sol — OpenAI advanced reasoning model. Utilizes structured deliberation tokens for multi-step reasoning, mathematical problem solving, and complex logic.
• Gpt 5.6 Terra — OpenAI advanced reasoning model. Utilizes structured deliberation tokens for multi-step reasoning, mathematical problem solving, and complex logic.
• Gpt 6 Astra — OpenAI advanced reasoning model. Utilizes structured deliberation tokens for multi-step reasoning, mathematical problem solving, and complex logic.
• Gpt 6 Luna — OpenAI advanced reasoning model. Utilizes structured deliberation tokens for multi-step reasoning, mathematical problem solving, and complex logic.
• Gpt 6 Sol — OpenAI advanced reasoning model. Utilizes structured deliberation tokens for multi-step reasoning, mathematical problem solving, and complex logic.
• Gpt 6.1 Sol — OpenAI advanced reasoning model. Utilizes structured deliberation tokens for multi-step reasoning, mathematical problem solving, and complex logic.
• Gpt Oss 120b — OpenAI language model featuring a 131,072-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Gpt Oss 120b 1 — OpenAI language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Gpt Oss 120b Maas — OpenAI language model featuring a extended context window. Engineered for dialogue, instruction following, and versatile text generation.
• Gpt Oss 120b Turbo — OpenAI language model featuring a 131,072-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Gpt Oss 120b Ultra — OpenAI language model featuring a 131,072-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Gpt Oss 20b — OpenAI language model featuring a 131,072-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Gpt Oss 20b 1 — OpenAI language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Gpt Oss Safeguard 120b — OpenAI language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Gpt Oss Safeguard 20b — OpenAI language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Granite 4.2 30b — ibm-granite language model featuring a 131,072-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Granite 4.2 3b — ibm-granite language model featuring a 131,072-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Granite 4.2 8b — ibm-granite language model featuring a 131,072-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Grok 4 1 Fast Non Reasoning — xAI advanced reasoning model. Utilizes structured deliberation tokens for multi-step reasoning, mathematical problem solving, and complex logic.
• Grok 4 1 Fast Reasoning — xAI advanced reasoning model. Utilizes structured deliberation tokens for multi-step reasoning, mathematical problem solving, and complex logic.
• Hermes 3 Llama 3.1 405B — NousResearch language model featuring a 131,072-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Hermes 3 Llama 3.1 70B — NousResearch language model featuring a 131,072-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Hy4 Preview — tencent language model featuring a 1,048,576-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Inkling — thinkingmachines language model featuring a 524,288-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Jev — TypeSafe AI language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Kimi K2 Thinking — Moonshot advanced reasoning model. Utilizes structured deliberation tokens for multi-step reasoning, mathematical problem solving, and complex logic.
• Kimi K2 Thinking Maas — Moonshot language model featuring a extended context window. Engineered for dialogue, instruction following, and versatile text generation.
• Kimi K2.5 — Moonshot language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Kimi K2.6 — moonshotai language model featuring a 262,144-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Kimi K2.7 Code — Moonshot specialized code generation and software development model. Optimized for code synthesis, analysis, and multi-language programming.
• Kimi K3 — moonshotai language model featuring a 1,048,576-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Kimi K3 — Moonshot language model featuring a 1,000,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• L3 8B Lunaris V1 Turbo — Sao10K language model featuring a 8,192-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• L3.1 70B Euryale V2.2 — Sao10K language model featuring a 131,072-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Ling 3.0 Flash — inclusionAI language model featuring a 131,072-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Ling 3.0 Flash VL — inclusionAI language model featuring a 131,072-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Llama 3.3 70B Instruct — Meta language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Llama 3.3 70B Instruct Turbo — meta-llama language model featuring a 131,072-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Llama 4 Maverick 17B 128E Instruct FP8 — Meta language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Llama 4 Scout 17B 16E Instruct — Meta language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Llama 4 Scout 17B 16E Instruct — meta-llama language model featuring a 327,680-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Llama Guard 4 12B — meta-llama language model featuring a 163,840-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Llama3 1 70b Instruct — Meta language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Llama3 1 8b Instruct — Meta language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Llama3 3 70b Instruct — Meta language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Llama4 Maverick 17b Instruct — Meta language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Llama4 Scout 17b Instruct — Meta language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Magistral Small 2509 — Mistral AI language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Meta Llama 3.1 70B Instruct Turbo — meta-llama language model featuring a 131,072-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Meta Llama 3.1 8B Instruct Turbo — meta-llama language model featuring a 131,072-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• MiMo V2.6 Flash — XiaomiMiMo language model featuring a 1,048,576-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• MiMo V2.6 Pro — XiaomiMiMo language model featuring a 1,048,576-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Minimax M2 — MiniMax language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Minimax M2 Maas — MiniMax language model featuring a extended context window. Engineered for dialogue, instruction following, and versatile text generation.
• Minimax M2.1 — MiniMax language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Minimax M2.5 — MiniMax language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• MiniMax M3 — MiniMaxAI language model featuring a 524,288-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Ministral 3 14b Instruct — Mistral AI language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Ministral 3 3b Instruct — Mistral AI language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Ministral 3 8b Instruct — Mistral AI language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Mistral Large 3 675b Instruct — Mistral AI language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Mistral Medium 2505 — Mistral AI language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Mistral Nemo Instruct 2407 — Mistral AI language model featuring a 131,072-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Mistral Small 24B Instruct 2501 — Mistral AI language model featuring a 32,768-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Mistral Small 2503 — Mistral AI language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Mistral Small 3.2 24B Instruct 2506 — Mistral AI language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Muse Glimmer 30B — meta-models language model featuring a 131,072-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Muse Spark 1.1 — Meta language model featuring a 1,048,576-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Muse Spark 1.2 — Meta language model featuring a 1,048,576-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Muse Spark 1.2 Contributor — Meta language model featuring a 1,048,576-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Muse Spark 1.3 — Meta language model featuring a 1,048,576-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Muse Spark 1.3 Contributor — Meta language model featuring a 1,048,576-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• MythoMax L2 13b — Gryphe language model featuring a 4,096-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Nemotron Content Safety 3.5 — nvidia language model featuring a 131,072-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Nemotron Nano 12b V2 — Other language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Nemotron Nano 3 30b — Other language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Nemotron Nano 9b V2 — Other language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Nemotron Super 3 120b — Other language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Nova 2 Lite — Amazon language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Nova Lite — Amazon language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Nova Micro — Amazon language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Nova Pro — Amazon language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• NVIDIA Nemotron 3 Super 120B A12B — nvidia language model featuring a 262,144-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• NVIDIA Nemotron 3 Ultra 550B A55B — nvidia language model featuring a 262,144-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• NVIDIA Nemotron 3.5 Lightning — nvidia language model featuring a 262,144-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• O1 — Full-scale OpenAI reasoning model trained with reinforcement learning to generate detailed chains of thought for STEM, logic, and coding problems.
• O1 2024 12 17 — December 17, 2024 checkpoint of OpenAI o1 with a 200K token context window and 100K output ceiling, ranking 146th on LM Arena text benchmark.
• O1 Pro 2025 03 19 — Compute-intensive version of o1 dated March 19, 2025, using additional reasoning compute for high-difficulty analytical and mathematical queries.
• O3 — OpenAI reasoning model trained to think through multi-step problems in STEM, mathematics, and coding, featuring a 200,000-token context window, 100,000 max output tokens, and text and image input support.
• O3 2025 04 16 — April 16, 2025 checkpoint of OpenAI o3, setting high benchmarks on mathematics, code generation, and visual reasoning across a 200,000-token context window with up to 100,000 generation tokens.
• O3 Mini — Cost-effective OpenAI reasoning model optimized for programming, mathematics, and structured logic queries with customizable thinking intensity.
• O3 Mini 2025 01 31 — January 31, 2025 snapshot of o3-mini delivering fast reasoning capabilities, function calling, and 200K token context limits for production services.
• O4 Mini — Lightweight reasoning model from OpenAI supporting text and image inputs with a 200,000-token context window and 100,000 max output tokens. It is tuned for STEM problem solving with a June 2024 knowledge cutoff.
• O4 Mini 2025 04 16 — April 16, 2025 snapshot of o4-mini featuring multimodal perception and 100K token output generation, ranked 160 on the LM Arena text leaderboard.
• Palmyra Vision 7b — Google language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Phi 4 — Phi-4 is Microsoft's 14-billion parameter language model engineered for complex reasoning, mathematical problem solving, and code generation, trained on synthetic reasoning datasets and curated web texts.
• Phi 4 — microsoft language model featuring a 16,384-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Phi 4 Mini Instruct — Phi-4-mini-instruct is Microsoft's 3.8-billion parameter lightweight instruction-tuned model featuring a 128K context window, engineered for high-throughput edge and latency-sensitive server workloads.
• Phi 4 Mini Reasoning — Phi-4-mini-reasoning is Microsoft's compact reasoning model delivering chain-of-thought problem solving in mathematics and logic within a 128K token context window.
• Phi 4 Multimodal Instruct — Phi-4-multimodal-instruct is Microsoft's 5.6-billion parameter multimodal model accepting text, vision, and audio inputs with a 128K context window for cross-modality comprehension.
• Phi 4 Reasoning — Phi-4-reasoning is Microsoft's 14-billion parameter reasoning model specialized in step-by-step logical deduction, STEM proofs, and rigorous code verification.
• Pixtral Large 2502 — Mistral AI language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Qvq Max — Qwen advanced reasoning model. Utilizes structured deliberation tokens for multi-step reasoning, mathematical problem solving, and complex logic.
• Qwen Coder Plus — Qwen-Coder-Plus is Alibaba Cloud's commercial code generation model engineered for repository-level software development, code refactoring, and multi-file code synthesis across 92 programming languages.
• Qwen Flash — Qwen Flash is Alibaba lightweight and cost-effective foundation model offering 1M-token context support with structured output and context caching for high-speed, high-volume production serving.
• Qwen Flash Character — Qwen Flash Character is Alibaba Cloud's lightweight role-playing dialogue model tuned for conversational agents, NPC game characters, and persona simulation with an 8K context window.
• Qwen Max — Qwen Max is an Alibaba Cloud proprietary dense text model supporting a 32,768-token context window for enterprise reasoning workloads.
• Qwen Mt Flash — Qwen MT Flash is a lightweight machine translation model designed for low-latency, high-concurrency cross-lingual translation tasks supporting 92 languages with a 16K context window.
• Qwen Mt Lite — Qwen MT Lite is a lightweight machine translation model from Alibaba Cloud optimized for high-throughput multilingual translation across 92 languages within a 16K context window.
• Qwen Mt Plus — Qwen-MT-Plus is Alibaba's enhanced machine translation model supporting 92 languages and dialects, providing terminology customization and domain adaptation for cross-lingual enterprise documentation.
• Qwen Mt Turbo — Qwen MT Turbo is a specialized translation model supporting 92 languages based on the Qwen3 architecture.
• Qwen Omni Turbo — Qwen language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Qwen Plus — Qwen Plus provides a balance of speed and reasoning quality for general conversational and instruction tasks.
• Qwen Plus 2025 01 25 — Qwen-Plus-2025-01-25 is a dated snapshot of Alibaba Cloud Qwen-Plus model, providing balanced speed and reasoning across a 1M-token context window with support for function calling and structured outputs.
• Qwen Plus 2025 04 28 — Qwen Plus 2025-04-28 is a snapshot release of Alibaba's balanced language model offering a 1M-token context window with native function calling and structured outputs. It delivers high throughput for general conversational assistance and long-form document synthesis.
• Qwen Plus 2025 07 14 — Qwen-Plus-2025-07-14 is the July 14, 2025 dated snapshot of Alibaba's Qwen Plus foundation model, providing fixed weights and a 1M-token context window for reliable enterprise pipelines and document analysis.
• Qwen Plus 2025 09 11 — Qwen Plus 2025-09-11 is a snapshot release of Alibaba balanced Qwen Plus foundation model, providing a 1M-token context window with optimized instruction following and enterprise reasoning.
• Qwen Plus 2025 12 01 — Qwen Plus 2025-12-01 is a dated production snapshot of Alibaba Cloud's balanced foundation model, offering stable execution for general instruction following, summarization, and reasoning across a 1M-token context window.
• Qwen Plus Character — Qwen Plus Character is a specialized conversational model fine-tuned for character roleplay and persona-driven interactive dialogue with a 32K context window.
• Qwen Plus Latest — Qwen Plus Latest is the rolling production pointer to Alibaba latest Qwen Plus foundation model checkpoint.
• Qwen Turbo — Qwen Turbo is a cost-effective language model engineered for low-latency dialogue and high-throughput serving.
• Qwen Vl Max — Qwen VL Max is an Alibaba Cloud multimodal vision-language model for image reasoning, text reading, and document parsing with a 32,768-token context window.
• Qwen Vl Ocr 2025 11 20 — Qwen-VL-OCR-2025-11-20 is a specialized visual text extraction model from Alibaba Cloud for document parsing, table structure extraction, and mathematical formula recognition from images.
• Qwen Vl Plus — Qwen VL Plus is a high-speed multimodal vision-language model tailored for optical character recognition and visual question answering.
• Qwen2.5 72B Instruct — Qwen language model featuring a 32,768-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Qwen3 14b — Qwen3 14B is a 14.8-billion parameter dense foundation model with a 131,072-token context window and 32,768 max output tokens for logical reasoning.
• Qwen3 14B — Qwen language model featuring a 40,960-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Qwen3 235b A22b — Qwen3 235B-A22B is an Alibaba open-weight mixture-of-experts model with 235 billion total parameters, activating 22 billion parameters per token across a 131,072-token context window and 32,768 max output tokens.
• Qwen3 235b A22b 2507 — Qwen language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Qwen3 235b A22b Instruct 2507 — Qwen3 235B-A22B Instruct 2507 is an aligned mixture-of-experts model with a 131,072-token context window and 32,768 max output tokens for instruction following and reasoning.
• Qwen3 235B A22B Instruct 2507 — Qwen language model featuring a 262,144-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Qwen3 235b A22b Instruct 2507 Maas — Qwen language model featuring a extended context window. Engineered for dialogue, instruction following, and versatile text generation.
• Qwen3 235b A22b Thinking 2507 — Qwen advanced reasoning model. Utilizes structured deliberation tokens for multi-step reasoning, mathematical problem solving, and complex logic.
• Qwen3 30b A3b — Qwen3 30B-A3B is an efficient mixture-of-experts model activating 3 billion parameters per token.
• Qwen3 30B A3B — Qwen language model featuring a 40,960-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Qwen3 30b A3b Instruct 2507 — Qwen3 30B-A3B Instruct 2507 is an instruction-tuned MoE model offering high conversational quality at low serving cost.
• Qwen3 30b A3b Thinking 2507 — Qwen advanced reasoning model. Utilizes structured deliberation tokens for multi-step reasoning, mathematical problem solving, and complex logic.
• Qwen3 32b — Qwen3 32B is a dense language model designed for complex coding, math, and structured tool use.
• Qwen3 32B — Qwen language model featuring a 40,960-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Qwen3 8b — Qwen3 8B is a compact open-weight dense foundation model featuring native dual-mode reasoning and 128K context.
• Qwen3 Coder 30b A3b — Qwen language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Qwen3 Coder 480b A35b — Qwen language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Qwen3 Coder 480b A35b Instruct — Open-weight 480-billion parameter mixture-of-experts model with 35 billion active parameters tuned for programming, repository-scale reasoning, and tool execution.
• Qwen3 Coder 480b A35b Instruct Maas — Qwen language model featuring a extended context window. Engineered for dialogue, instruction following, and versatile text generation.
• Qwen3 Coder 480B A35B Instruct Turbo — Qwen language model featuring a 262,144-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Qwen3 Coder Flash — Qwen3-Coder-Flash is a lightweight, low-latency code intelligence model featuring a 1M-token context window designed for rapid code autocompletion, real-time code reviews, and high-throughput software agent workflows.
• Qwen3 Coder Next — Sparse mixture-of-experts coding model activating 3 billion parameters out of 80 billion, optimized for developer IDE scaffolds and agentic software workflows.
• Qwen3 Coder Plus — Hosted commercial programming model from Alibaba Cloud designed for agentic tool use, complex code generation, and multi-file software engineering.
• Qwen3 Coder Plus 2025 07 22 — Snapshot version of Qwen3-Coder-Plus released on July 22, 2025, offering fixed-behavior execution for production software generation pipelines.
• Qwen3 Coder Plus 2025 09 23 — September 23, 2025 snapshot of Qwen3-Coder-Plus featuring pinned weights for agentic development, bug localization, and automated refactoring.
• Qwen3 Livetranslate Flash Realtime — Qwen language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Qwen3 Livetranslate Flash Realtime 2025 09 22 — Qwen language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Qwen3 Max — Qwen3-Max is Alibaba Cloud dense foundation language model designed for complex multi-step reasoning, offering a 256K-token context window with support for both thinking and non-thinking execution modes.
• Qwen3 Max — Qwen language model featuring a 256,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Qwen3 Max 2025 09 23 — Qwen3 Max 2025-09-23 is Alibaba's dense reasoning checkpoint supporting a 262,144-token context window and dual thinking modes. It is tuned for enterprise text reasoning, multi-step problem solving, and tool integration.
• Qwen3 Max 2026 01 23 — Qwen3-Max-2026-01-23 is the January 23, 2026 production release snapshot of Alibaba's Qwen3-Max model, providing a 262,144-token context window with dual non-thinking and thinking modes for text reasoning.
• Qwen3 Max Preview — Qwen3 Max Preview is a reasoning foundation model from Alibaba's Qwen3 family, featuring a 262,144-token context window with selectable thinking and non-thinking modes for text problem solving.
• Qwen3 Max Thinking — Qwen language model featuring a 256,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Qwen3 Next 80b A3b — Qwen language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Qwen3 Next 80b A3b Instruct — Next-generation 80-billion parameter model with hybrid attention and 3 billion active parameters, built for high-throughput instruction following and long-horizon reasoning.
• Qwen3 Next 80B A3B Instruct — Qwen language model featuring a 262,144-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Qwen3 Next 80b A3b Instruct Maas — Qwen language model featuring a extended context window. Engineered for dialogue, instruction following, and versatile text generation.
• Qwen3 Next 80b A3b Thinking — Qwen advanced reasoning model. Utilizes structured deliberation tokens for multi-step reasoning, mathematical problem solving, and complex logic.
• Qwen3 Next 80b A3b Thinking Maas — Qwen language model featuring a extended context window. Engineered for dialogue, instruction following, and versatile text generation.
• Qwen3 Omni 30b A3b Captioner — Qwen language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Qwen3 Omni Flash — Qwen3-Omni-Flash is an omni-modal foundation model supporting real-time processing of text, image, audio, and video inputs with hybrid thinking modes and natural speech output across 11 languages.
• Qwen3 Omni Flash 2025 09 15 — Qwen3 Omni Flash 2025-09-15 is an omni multimodal foundation model checkpoint supporting text, audio, image, and video inputs with dual thinking and non-thinking execution modes.
• Qwen3 Omni Flash 2025 12 01 — Qwen3-Omni-Flash-2025-12-01 is a hybrid thinking omni-modal foundation model from Alibaba Cloud handling text, speech, audio, image, and video streams for real-time conversational intelligence.
• Qwen3 Omni Flash Realtime — Qwen language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Qwen3 Omni Flash Realtime 2025 09 15 — Qwen language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Qwen3 Omni Flash Realtime 2025 12 01 — Qwen language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Qwen3 S2s Flash Realtime — Qwen language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Qwen3 Vl 235b A22b — Qwen language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Qwen3 Vl 235b A22b Instruct — Multimodal vision-language model with 235 billion total parameters and 22 billion active parameters, offering visual reasoning, document parsing, and video dynamics understanding.
• Qwen3 VL 235B A22B Instruct — Qwen language model featuring a 262,144-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Qwen3 Vl 235b A22b Thinking — Qwen advanced reasoning model. Utilizes structured deliberation tokens for multi-step reasoning, mathematical problem solving, and complex logic.
• Qwen3 VL 30B A3B Instruct — Qwen language model featuring a 262,144-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Qwen3 Vl Flash — Qwen3-VL-Flash is a high-speed vision-language model with a 256K context window optimized for rapid visual recognition, document OCR parsing, and video analysis for feeds up to one hour in length.
• Qwen3 Vl Flash 2026 01 22 — Qwen3-VL-Flash-2026-01-22 is a fast multimodal snapshot model optimized for high-throughput visual processing, supporting videos up to 1 hour and thinking modes across a 256K context window.
• Qwen3 Vl Plus — Qwen3-VL-Plus is Alibaba's multimodal vision-language model supporting high-resolution image analysis and video comprehension up to 1 hour in length. It features a 256K-token context window with native function calling across visual and textual reasoning tasks.
• Qwen3 Vl Plus 2025 09 23 — Qwen3-VL-Plus-2025-09-23 is the September 23, 2025 snapshot of Qwen3-VL-Plus, a multimodal vision-language model with a 256K context window optimized for fine-grained image parsing and video understanding up to 1 hour.
• Qwen3 Vl Plus 2025 12 19 — Qwen3 VL Plus 2025-12-19 is a multimodal snapshot model supporting text, image, and hour-long video comprehension across a 256K context window with dual thinking and non-thinking execution.
• Qwen3.5 122b A10b — Sparse mixture-of-experts architecture activating 10 billion parameters of 122 billion total, combining gated delta networks with long-context comprehension.
• Qwen3.5 27b — Dense 27-billion parameter language model offering efficient inference and native long-context processing for general text and reasoning tasks.
• Qwen3.5 27B — Qwen language model featuring a 262,144-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Qwen3.5 35b A3b — Sparse mixture-of-experts model activating 3 billion parameters from a 35-billion parameter base, designed for low-latency text generation and agent interactions.
• Qwen3.5 35B A3B — Qwen language model featuring a 262,144-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Qwen3.5 397b A17b — High-capacity mixture-of-experts foundation model with 397 billion total parameters and 17 billion active parameters, providing broad domain knowledge, math reasoning, and coding expertise.
• Qwen3.5 397B A17B — Qwen language model featuring a 262,144-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Qwen3.5 9B — Qwen language model featuring a 262,144-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Qwen3.5 Flash — Qwen3.5-Flash is a high-speed, cost-efficient language model from Alibaba Cloud supporting a 1M-token context window, native thinking modes, structured outputs, and function calling for high-throughput applications.
• Qwen3.5 Flash 2026 02 23 — Qwen3.5 Flash 2026-02-23 is a lightweight foundation language model checkpoint from Alibaba engineered for fast inference and complex reasoning with a 1M-token context window.
• Qwen3.5 Livetranslate Flash Realtime — Qwen language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Qwen3.5 Livetranslate Flash Realtime 2026 05 19 — Qwen language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Qwen3.5 Omni Flash — Qwen3.5-Omni-Flash is a lightweight next-generation omni-modal model supporting text, audio, and visual inputs across 113 input languages with low-latency streaming text and speech outputs.
• Qwen3.5 Omni Flash 2026 03 15 — Qwen3.5-Omni-Flash-2026-03-15 is a dated snapshot of Alibaba's omni-modal model supporting low-latency streaming interactions across text, audio, image, and video inputs with native speech output.
• Qwen3.5 Omni Flash Realtime — Qwen language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Qwen3.5 Omni Flash Realtime 2026 03 15 — Qwen language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Qwen3.5 Omni Plus — Qwen3.5-Omni-Plus is an omni-modal foundation model from Alibaba Cloud supporting native speech, audio, image, and video inputs alongside text, engineered for real-time interactive multi-sensory tasks.
• Qwen3.5 Omni Plus 2026 03 15 — Qwen3.5-Omni-Plus 2026-03-15 is an omni-modal foundation model capable of processing text, audio, images, and video within a 64K-token context window. Designed for low-latency interactive processing, it supports function calling and video analysis for real-time applications.
• Qwen3.5 Omni Plus Realtime — Qwen language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Qwen3.5 Omni Plus Realtime 2026 03 15 — Qwen language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Qwen3.5 Plus — Qwen3.5-Plus is Alibaba Cloud's foundation multimodal model offering a 1M-token context window, 64K maximum output tokens, and native vision-language reasoning for conversational and agentic workflows.
• Qwen3.5 Plus 2026 02 15 — Qwen3.5 Plus 2026-02-15 is a multimodal snapshot model delivering native text, image, and video processing with a 1M-token context window and up to 64K output tokens for agentic workflows.
• Qwen3.5 Plus 2026 04 20 — Qwen3.5-Plus-2026-04-20 is a pinned production snapshot of Alibaba Cloud's general-purpose Qwen3.5-Plus model, supporting thinking mode, structured output generation, and tool use across a 1M-token context window.
• Qwen3.6 27b — Qwen3.6-27B is a 27-billion parameter dense multimodal language model from Alibaba featuring a vision encoder, native 262K context window, and enhanced repository-level agentic coding capabilities.
• Qwen3.6 27B — Qwen language model featuring a 262,144-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Qwen3.6 35b A3b — Qwen3.6-35B-A3B is an open-weight mixture-of-experts multimodal model from Alibaba activating 3 billion of its 35 billion parameters, designed for efficient agentic coding with a 262K native context.
• Qwen3.6 35B A3B — Qwen language model featuring a 262,144-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Qwen3.6 Flash — Qwen3.6 Flash is a high-throughput language model from Alibaba featuring native tool calling, hybrid thinking modes, and a 1M-token context window for low-latency agentic workflows.
• Qwen3.6 Flash 2026 04 16 — Qwen3.6-Flash-2026-04-16 is a high-efficiency multimodal model featuring a 1M context window and 64K max output tokens, engineered for fast processing across text, image, and video modalities.
• Qwen3.6 Max Preview — Qwen3.6-Max-Preview is a preview release of Alibaba's reasoning architecture with a 262,144-token context window, featuring thinking mode capabilities for multi-step math, code synthesis, and analytical planning.
• Qwen3.6 Plus — Qwen3.6-Plus is a high-capacity multimodal model from Alibaba featuring 1M context, 64K max output, and native understanding across text, images, and video, ranked #79 on LMSYS Arena.
• Qwen3.6 Plus 2026 04 02 — Qwen3.6-Plus 2026-04-02 is a snapshot of Alibaba's multimodal foundation model featuring a 1M-token context window and 64K max output tokens. It integrates native thinking modes with multimodal inputs across text, images, and video for complex agentic workflows.
• Qwen3.7 Flash — Qwen3.7-Flash is Alibaba's high-speed multimodal model providing a 1M-token context window, 64K output token limit, thinking modes, and fast processing across text, high-resolution images, and long-form video.
• Qwen3.7 Flash 2026 07 15 — Qwen3.7 Flash 2026-07-15 is a high-throughput multimodal snapshot model designed for fast text, image, and video understanding with a 1M-token context window and 64K maximum output tokens.
• Qwen3.7 Max — Qwen3.7-Max is an Alibaba Cloud dense reasoning model featuring dual thinking and non-thinking operational modes, a 1,000,000-token context window, and agentic tool use for enterprise workflows.
• Qwen3.7 Max — Qwen language model featuring a 256,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Qwen3.7 Max 2026 05 20 — Qwen3.7 Max 2026-05-20 is an Alibaba dense reasoning model checkpoint delivering logical deduction, structured outputs, and agentic tool execution across a 1,000,000-token context window.
• Qwen3.7 Max 2026 06 08 — Qwen3.7-Max-2026-06-08 is an Alibaba Cloud foundation model supporting hybrid thinking mode and a 1,048,576-token context window for text reasoning and enterprise problem solving.
• Qwen3.7 Plus — Qwen3.7-Plus is a balanced multimodal foundation model supporting thinking and standard modes across a 1M-token context window, with 64K output token capacity for document synthesis and agentic tool use.
• Qwen3.7 Plus 2026 05 26 — Qwen3.7-Plus-2026-05-26 is a production snapshot of Alibaba's multimodal model with a 1M-token context window and 64K max output, capable of processing text, high-resolution images, and long-form video.
• Qwen3.8 27b — Qwen3.8-27B is Alibaba's 27-billion parameter dense foundation model featuring native vision-language understanding, flexible thinking modes, and autonomous multi-step agent execution.
• Qwen3.8 27B — Qwen language model featuring a 262,144-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Qwen3.8 Flash — Qwen3.8-Flash is Alibaba's high-efficiency production model offering 1M context length, sparse attention architecture, and fast reasoning across text and vision modalities.
• Qwen3.8 Flash — Qwen language model featuring a 1,000,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Qwen3.8 Max — Qwen language model featuring a 256,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Qwen3.8 Max — Qwen3.8-Max is an Alibaba foundation model offering a 1,000,000-token context window, hybrid thinking modes, and multimodal reasoning across text, image, and video inputs. It provides tool calling and long-context comprehension for complex tasks.
• Qwen3.8 Max 0902 — Qwen language model featuring a 1,000,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Qwen3.8 Omni Flash — Qwen language model featuring a 1,000,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Qwq Plus — QwQ-Plus is an Alibaba Cloud reasoning model built on Qwen with Questions, featuring a 131,072-token context window and test-time compute. It scores 90.6 on MATH-500, 65.2 on GPQA, and 50.0 on AIME for mathematics and science proofs.
• R1 — DeepSeek advanced reasoning model. Utilizes structured deliberation tokens for multi-step reasoning, mathematical problem solving, and complex logic.
• Seed 1.8 — ByteDance language model featuring a 256,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Seed 2.0 Code — ByteDance language model featuring a 256,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Seed 2.0 Mini — ByteDance language model featuring a 256,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Seed 2.0 Pro — ByteDance language model featuring a 256,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• V3 — DeepSeek language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• V3.2 — DeepSeek language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Voxtral Mini 3b 2507 — Mistral AI language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
• Voxtral Small 24b 2507 — Mistral AI language model featuring a 128,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.

Image models

• Chatgpt Image Latest — OpenAI high-fidelity visual generation model. Synthesizes detailed images from natural language prompts.
• Gpt Image 1 — Multimodal OpenAI image synthesis model accepting text and visual prompts to generate and edit images with inpainting support.
• Gpt Image 1 Mini — Cost-efficient OpenAI image generation model designed for high-throughput visual asset creation and rapid prototyping.
• Gpt Image 1.5 — Enhanced multimodal generation model by OpenAI offering refined prompt adherence, image editing, and text-image generation outputs.
• Gpt Image 2 — OpenAI high-fidelity visual generation model. Synthesizes detailed images from natural language prompts.
• Gpt Image 2 2026 04 21 — OpenAI high-fidelity visual generation model. Synthesizes detailed images from natural language prompts.
• Muse Image 1.0 — Meta high-fidelity visual generation model. Synthesizes detailed images from natural language prompts.

Video models

• Sora 2 — Next-generation video synthesis foundation model from OpenAI producing high-definition video clips with synchronized audio from text and images.
• Sora 2 Pro — Professional-tier OpenAI video generation model delivering high-resolution video clips with synchronized audio and fine-grained camera control.

Audio models

• Gpt 4o Mini Transcribe — Speech-to-text transcription model powered by GPT-4o Mini for fast and accurate audio transcription with language hints.
• Gpt 4o Mini Transcribe 2025 03 20 — Snapshot of OpenAI lightweight speech-to-text transcription model powered by GPT-4o Mini. Provides fast and cost-effective speech transcription.
• Gpt 4o Mini Transcribe 2025 12 15 — Updated snapshot of OpenAI lightweight speech-to-text transcription model powered by GPT-4o Mini.
• Gpt 4o Mini Tts — OpenAI text-to-speech voice generation model. Converts input text into natural, expressive spoken audio across multiple voice styles.
• Gpt 4o Mini Tts 2025 03 20 — OpenAI text-to-speech voice generation model. Converts input text into natural, expressive spoken audio across multiple voice styles.
• Gpt 4o Mini Tts 2025 12 15 — OpenAI text-to-speech voice generation model. Converts input text into natural, expressive spoken audio across multiple voice styles.
• Gpt 4o Transcribe — OpenAI speech-to-text transcription model powered by GPT-4o. Delivers high-accuracy automated audio transcription across dozens of languages.
• Gpt 4o Transcribe Diarize — OpenAI speech-to-text transcription and speaker diarization model powered by GPT-4o. Delivers automated multi-speaker audio transcription with precise timestamping and speaker attribution.
• Gpt Audio — OpenAI text-to-speech voice generation model. Converts input text into natural, expressive spoken audio across multiple voice styles.
• Gpt Audio 1.5 — OpenAI text-to-speech voice generation model. Converts input text into natural, expressive spoken audio across multiple voice styles.
• Gpt Audio 2025 08 28 — OpenAI text-to-speech voice generation model. Converts input text into natural, expressive spoken audio across multiple voice styles.
• Gpt Audio Mini — OpenAI text-to-speech voice generation model. Converts input text into natural, expressive spoken audio across multiple voice styles.
• Gpt Audio Mini 2025 10 06 — OpenAI text-to-speech voice generation model. Converts input text into natural, expressive spoken audio across multiple voice styles.
• Gpt Audio Mini 2025 12 15 — OpenAI text-to-speech voice generation model. Converts input text into natural, expressive spoken audio across multiple voice styles.
• Gpt Live Transcribe — OpenAI real-time speech transcription model engineered for low-latency streaming audio transcription.
• Gpt Transcribe — OpenAI dedicated speech transcription model for general audio-to-text processing.
• Tts 1 — Low-latency text-to-speech model from OpenAI optimized for real-time voice generation and interactive conversational applications.
• Tts 1 1106 — OpenAI text-to-speech voice generation model. Converts input text into natural, expressive spoken audio across multiple voice styles.
• Tts 1 Hd — High-definition text-to-speech model from OpenAI prioritizing audio clarity, natural prosody, and fidelity for broadcast and narration use cases.
• Tts 1 Hd 1106 — OpenAI text-to-speech voice generation model. Converts input text into natural, expressive spoken audio across multiple voice styles.
• Whisper 1 — Robust automatic speech recognition model from OpenAI supporting multilingual speech transcription, translation, and language identification.

Embedding models

• All MiniLM L6 V2 — sentence-transformers dense vector embedding model. Transforms natural language text into rich semantic embeddings for search and retrieval.
• All Mpnet Base V2 — sentence-transformers dense vector embedding model. Transforms natural language text into rich semantic embeddings for search and retrieval.
• Bge Base En V1.5 — BAAI dense vector embedding model. Transforms natural language text into rich semantic embeddings for search and retrieval.
• Bge En Icl — BAAI dense vector embedding model. Transforms natural language text into rich semantic embeddings for search and retrieval.
• Bge Large En V1.5 — BAAI dense vector embedding model. Transforms natural language text into rich semantic embeddings for search and retrieval.
• Bge M3 — BAAI dense vector embedding model. Transforms natural language text into rich semantic embeddings for search and retrieval.
• Bge M3 Multi — BAAI dense vector embedding model. Transforms natural language text into rich semantic embeddings for search and retrieval.
• Bge M3 Multi 8k — BAAI dense vector embedding model. Transforms natural language text into rich semantic embeddings for search and retrieval.
• Clip ViT B 32 — sentence-transformers dense vector embedding model. Transforms natural language text into rich semantic embeddings for search and retrieval.
• Clip ViT B 32 Multilingual V1 — sentence-transformers dense vector embedding model. Transforms natural language text into rich semantic embeddings for search and retrieval.
• E5 Base V2 — intfloat dense vector embedding model. Transforms natural language text into rich semantic embeddings for search and retrieval.
• E5 Large V2 — intfloat dense vector embedding model. Transforms natural language text into rich semantic embeddings for search and retrieval.
• Embeddinggemma 300m — Google dense vector embedding model. Transforms natural language text into rich semantic embeddings for search and retrieval.
• Gte Base — thenlper dense vector embedding model. Transforms natural language text into rich semantic embeddings for search and retrieval.
• Gte Large — thenlper dense vector embedding model. Transforms natural language text into rich semantic embeddings for search and retrieval.
• Llama Nemotron Embed Vl 1b V2 — nvidia dense vector embedding model. Transforms natural language text into rich semantic embeddings for search and retrieval.
• Multi Qa Mpnet Base Dot V1 — sentence-transformers dense vector embedding model. Transforms natural language text into rich semantic embeddings for search and retrieval.
• Multilingual E5 Large — intfloat dense vector embedding model. Transforms natural language text into rich semantic embeddings for search and retrieval.
• Multilingual E5 Large Instruct — intfloat dense vector embedding model. Transforms natural language text into rich semantic embeddings for search and retrieval.
• Paraphrase MiniLM L6 V2 — sentence-transformers dense vector embedding model. Transforms natural language text into rich semantic embeddings for search and retrieval.
• Qwen3 Embedding 0.6B — Qwen dense vector embedding model. Transforms natural language text into rich semantic embeddings for search and retrieval.
• Qwen3 Embedding 4B — Qwen dense vector embedding model. Transforms natural language text into rich semantic embeddings for search and retrieval.
• Qwen3 Embedding 8B — Qwen dense vector embedding model. Transforms natural language text into rich semantic embeddings for search and retrieval.
• Text Embedding 3 Large — OpenAI text embedding model producing 3,072-dimensional vector representations across an 8,192-token context window. It scores 64.6 on MTEB and 54.9 on MIRACL for search, clustering, and retrieval systems.
• Text Embedding 3 Small — Cost-effective text embedding model by OpenAI yielding 1536-dimensional vectors with elastic dimension truncation for efficient vector database retrieval.
• Text Embedding Ada 002 — Legacy OpenAI embedding model generating 1536-dimensional embeddings across an 8192-token context window for similarity matching and classification.
• Text2vec Base Chinese — shibing624 dense vector embedding model. Transforms natural language text into rich semantic embeddings for search and retrieval.

Provider clouds

Models in the catalogue are served through these provider clouds. The gateway holds the provider credentials; callers use one nRouter key.

• AWS Bedrock
• Alibaba US
• Anthropic
• Azure Foundry
• DeepInfra
• Google Vertex AI
• Meta
• OpenAI
• TypeSafe AI

Product pages

• AI Governance — Governance on every request: guardrails, RBAC, audit logs, budgets and SSO.
• OpenAI-Compatible API — The OpenAI SDK contract kept intact — one API for every provider, with routing, guardrails and budgets.
• LLM Cost Optimization — Cut spend with cost-aware routing, caching, exact list pricing and hard budgets.
• Enterprise LLM Gateway — The managed gateway product for production and enterprise workloads.
• Smart Routing — Direct model selection with configured fallback chains, or nrouter/auto choosing a model for each request.
• Cache — Exact-match response caching, on by default for non-streaming requests.
• Guardrails — Inline screening for PII, prompt injection and blocked content before egress.
• Virtual Keys — Scoped API keys with per-key budgets, rate limits and model access.
• Budgets — Spend ceilings per key, team and organization, enforced before the provider call.
• Analytics — Cost, usage and performance reporting with CSV export.
• Prompts — Versioned prompt templates with A/B testing across variants and role-based access.
• Observability — Request logs and per-step traces for every call through the gateway.
• Teams — Organizations, teams and role-based access for shared accounts.
• MCP Gateway — Managed access to MCP servers through the same key and controls.
• Playground — Browser-based interactive API testing with your own virtual key.

Use cases

• RAG pipelines — Embeddings and chat through one key, with per-stage cost attribution.
• AI agents — Tool-calling workloads with budgets, guardrails and failover per step.
• Customer support — High-volume support automation with spend ceilings and audit logs.
• Code generation — Coding models routed by task, with cost tracked per repository or team.
• Document processing — Extraction and classification pipelines across document types.
• Voice — Speech and transcription models behind the same endpoint.

Documentation

• Documentation home — API reference, SDKs in every supported language, framework integrations and step-by-step guides, including routing, caching, headers, limits, error handling and getting support.