六五折
MiniMax1.0M tokens
No description provided for this model
chatFree trial $3.5714/day
Starting price
$0.1950/1M tokens
Context window
1.0M tokens
Latency
—
Throughput
—
Status
No traffic
Routin
Loading...
Loading...
Browse all models configured in Routin and filter them by capabilities, context length and pricing.
No description provided for this model
No description provided for this model
Grok 4.6 is SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.
No description provided for this model
全新的多模态视觉理解模型 DeepSeek-V4-Flash-Vision-Exp 上线 DeepSeek API 平台，这是一个实验性质的模型
deepseek-v4-pro
Tencent252K tokensHy3 正式版面向真实业务场景打磨，采用 295B 总参数、21B 激活 MoE 架构，原生支持 256K 上下文，并提供no_think（极速响应）、think_low（快速思考）与 think_high（深度推理） 多档思考模式，兼顾极速响应、复杂推理与调用成本。相比 Preview 版本，Hy3 基于腾讯元宝、WorkBuddy、ima 、Marvis等真实业务反馈，重点提升了 Coding Agent、长文理解、多轮上下文承接、搜索问答与复杂任务执行能力，在减少幻觉、提升任务完成度和工程可用性方面表现更稳。更加适合前端任务、跨文件代码开发、长文档分析、办公自动化和多步骤 Agent 工作流等实用场景。
No description provided for this model
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 code generation, and finance and analysis tasks in particular. It also tends to be more concise than Fable 5 in its plans and summaries. We recommend testing it as a direct upgrade wherever you use Fable 5 today, and alongside Opus 5 on reasoning-heavy tasks.
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 across reasoning, coding, and computer-use tasks, Haiku 4.5 brings frontier-level capability to real-time and high-volume applications. It introduces extended thinking to the Haiku line; enabling controllable reasoning depth, summarized or interleaved thought output, and tool-assisted workflows with full support for coding, bash, web search, and computer-use tools. Scoring >73% on SWE-bench Verified, Haiku 4.5 ranks among the world’s best coding models while maintaining exceptional responsiveness for sub-agents, parallelized execution, and scaled deployment.
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 across reasoning, coding, and computer-use tasks, Haiku 4.5 brings frontier-level capability to real-time and high-volume applications. It introduces extended thinking to the Haiku line; enabling controllable reasoning depth, summarized or interleaved thought output, and tool-assisted workflows with full support for coding, bash, web search, and computer-use tools. Scoring >73% on SWE-bench Verified, Haiku 4.5 ranks among the world’s best coding models while maintaining exceptional responsiveness for sub-agents, parallelized execution, and scaled deployment.
Claude Opus 4 is benchmarked as the world’s best coding model, at time of release, bringing sustained performance on complex, long-running tasks and agent workflows. It sets new benchmarks in software engineering, achieving leading results on SWE-bench (72.5%) and Terminal-bench (43.2%). Opus 4 supports extended, agentic workflows, handling thousands of task steps continuously for hours without degradation.
Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains in multi-file code refactoring, debugging precision, and detail-oriented reasoning. The model supports extended thinking up to 64K tokens and is optimized for tasks involving research, data analysis, and tool-assisted reasoning.
Claude Opus 4.1 (dated) - Specific version
Claude Opus 4.5 - Most intelligent model for complex tasks
Claude Opus 4.6 supports a 200K context window (with 1M token context window available in beta), 128K max output tokens, extended thinking, and all existing Claude API features.
Claude Opus 4.7 is our most capable generally available model to date. It is highly autonomous and performs exceptionally well on long-horizon agentic work, knowledge work, vision tasks, and memory tasks. This page summarizes everything new at launch.
No description provided for this model
Claude Opus 5 is a step-change improvement over Claude Opus 4.8, with the largest gains in deep reasoning, agentic and long-horizon tasks, and test-time compute scaling. This page summarizes everything new in Claude Opus 5, including thinking on by default, mid-conversation tool changes, and a breaking change to when thinking can be disabled.
Claude Sonnet 4 - Default model for most users
Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Achieving state-of-the-art performance on SWE-bench (72.7%), Sonnet 4 balances capability and computational efficiency, making it suitable for a broad range of applications from routine coding tasks to complex software development projects. Key enhancements include improved autonomous codebase navigation, reduced error rates in agent-driven workflows, and increased reliability in following intricate instructions. Sonnet 4 is optimized for practical everyday use, providing advanced reasoning capabilities while maintaining efficiency and responsiveness in diverse internal and external scenarios. Read more at the blog post here
Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with improvements across system design, code security, and specification adherence. The model is designed for extended autonomous operation, maintaining task continuity across sessions and providing fact-based progress tracking. Sonnet 4.5 also introduces stronger agentic capabilities, including improved tool orchestration, speculative parallel execution, and more efficient context and memory management. With enhanced context tracking and awareness of token usage across tool calls, it is particularly well-suited for multi-context and long-running workflows. Use cases span software engineering, cybersecurity, financial analysis, research agents, and other domains requiring sustained reasoning and tool use.
Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with improvements across system design, code security, and specification adherence. The model is designed for extended autonomous operation, maintaining task continuity across sessions and providing fact-based progress tracking. Sonnet 4.5 also introduces stronger agentic capabilities, including improved tool orchestration, speculative parallel execution, and more efficient context and memory management. With enhanced context tracking and awareness of token usage across tool calls, it is particularly well-suited for multi-context and long-running workflows. Use cases span software engineering, cybersecurity, financial analysis, research agents, and other domains requiring sustained reasoning and tool use.
Adaptive thinking () is the recommended thinking mode for Opus 4.6 and Sonnet 4.6. Claude dynamically decides when and how much to think. At the default effort level (), Claude will almost always think. At lower effort levels, it may skip thinking for simpler problems.thinking: {type: "adaptive"}high thinking: {type: "enabled"} and are deprecated on Opus 4.6 and Sonnet 4.6. They remain functional but will be removed in a future model release. Use adaptive thinking and the effort parameter to control thinking depth instead. Adaptive thinking also automatically enables interleaved thinking.budget_tokens
No description provided for this model
No description provided for this model
No description provided for this model
No description provided for this model
VolcEngine256K tokensSeed 2.0 的编程加强版，更适合 Agentic Coding
VolcEngine256K tokens兼顾生成质量与响应速度，适合作为通用生产级模型
VolcEngine256K tokens面向低时延、高并发与成本敏感场景，强调快速响应与灵活推理部署，支持四档位思考与多模态理解能力。
VolcEngine256K tokens旗舰级全能通用模型，面向 Agent 时代的复杂推理与长链路任务执行场景。强调多模态理解、长上下文推理、结构化生成与工具增强执行。复杂指令与多约束执行能力突出，可稳定应对多步复杂规划、复杂图文推理、视频内容理解与高难度分析等场景。
ByteDance256K tokens迈向生产级智能的新一代大模型，全面升级 Coding、Agent 与多模态能力，以更强的自主规划、长链路执行和动态修复能力，胜任企业真实复杂任务。
ByteDance256K tokens效果与成本均衡，全面升级编程、智能体与多模态能力。
ByteDance256K tokens周级迭代，持续进化 Coding 与 Agent 能力。
VolcEngine4K tokensSeedream 3.0 是一款支持原生高分辨率的中英双语图像生成基础模型，综合能力媲美GPT-4o，处于世界第一梯队。支持原生 2K 分辨率输出；响应速度更快；小字生成更准确，文本排版效果增强；指令遵循能力强，美感&结构提升，保真度和细节表现较好。
VolcEngine4K tokensSeedream 4.5 是字节跳动最新推出的图像多模态模型，整合了文生图、图生图、组图输出等能力，融合常识和推理能力。相比前代4.0模型生成效果大幅提升，具备更好的编辑一致性和多图融合效果，能更精准的控制画面细节，小字、小人脸生成更自然，图片排版、色彩更和谐，美感提升
ByteDance4K tokensSeedream4.5 supports native text, single image, and multi-image input, enabling the creation of diverse image fusion, image editing, and group image generation. It allows for more freedom and control in image creation.
VolcEngine-1 tokens支持文本 、单图和多图输入，支持生成组图
ByteDance4K tokensNo description provided for this model
Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinking" capabilities, enabling it to provide responses with greater accuracy and nuanced context handling. Additionally, Gemini 2.5 Flash is configurable through the "max tokens for reasoning" parameter,
Gemini 2.5 Flash Image, a.k.a. "Nano Banana," is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image generation, edits, and multi-turn conversations.
Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance across common benchmarks compared to earlier Flash models. By default, "thinking" (i.e. multi-pass reasoning) is disabled to prioritize speed
Gemini 2.5 Flash is a high-performance generative AI model developed by Google DeepMind, belonging to the "Flash" variant of the Gemini 2.5 series. Designed as a "workhorse" model, it focuses on fast and excellent performance for everyday tasks, providing timely and low-latency responses. Thanks to Google's wake-up support for the "Think" (think) function in Flash models, it allows developers to dynamically control the model's inference process to balance speed, cost, and accuracy.
Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.
Gemini-3-Flash-Preview is a language model released by Google, typically part of its Gemini series. This model is optimized over the base version of Gemini-3, focusing on faster response times and more efficient computational power, while maintaining strong language comprehension and generation capabilities.
Google Gemini 3 Pro - Latest generation (preview)
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 high-fidelity visual synthesis. The model generates context-rich graphics, from infographics and diagrams to cinematic composites, and can incorporate real-time information via Search grounding. It offers industry-leading text rendering in images (including long passages and multilingual layouts), consistent multi-image blending, and accurate identity preservation across up to five subjects. Nano Banana Pro adds fine-grained creative controls such as localized edits, lighting and focus adjustments, camera transformations, and support for 2K/4K outputs and flexible aspect ratios. It is designed for professional-grade design, product visualization, storyboarding, and complex multi-element compositions while remaining efficient for general image creation workflows.
Gemini 3 Pro is Google’s flagship frontier model for high-precision multimodal reasoning, combining strong performance across text, image, video, audio, and code with a 1M-token context window. Reasoning Details must be preserved when using multi-turn tool calling, It delivers state-of-the-art benchmark results in general reasoning, STEM problem solving, factual QA, and multimodal understanding, including leading scores on LMArena, GPQA Diamond, MathArena Apex, MMMU-Pro, and Video-MMMU. Interactions emphasize depth and interpretability: the model is designed to infer intent with minimal prompting and produce direct, insight-focused responses. Built for advanced development and agentic workflows, Gemini 3 Pro provides robust tool-calling, long-horizon planning stability, and strong zero-shot generation for complex UI, visualization, and coding tasks. It excels at agentic coding (SWE-Bench Verified, Terminal-Bench 2.0), multimodal analysis, and structured long-form tasks such as research synthesis, planning, and interactive learning experiences. Suitable applications include autonomous agents, coding assistants, multimodal analytics, scientific reasoning, and high-context information processing.
No description provided for this model
No description provided for this model
Gemini 3.1 Flash Image Preview, a.k.a. "Nano Banana 2," is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced contextual understanding with fast, cost-efficient inference, making complex image generation and iterative edits significantly more accessible
Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality and approaches Gemini 2.5 Flash performance across key capabilities. Improvements span audio input/ASR, RAG snippet ranking, translation, data extraction, and code completion. Supports full thinking levels (minimal, low, medium, high) for fine-grained cost/performance trade-offs. Priced at half the cost of Gemini 3 Flash.
Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation of the Gemini 3 series, it combines high-precision reasoning across text, image, video, audio, and code with a 1M-token context window. Reasoning Details must be preserved when using multi-turn tool calling, see our docs here: https://openrouter.ai/docs/use-cases/reasoning-tokens#preserving-reasoning. The 3.1 update introduces measurable gains in SWE benchmarks and real-world coding environments, along with stronger autonomous task execution in structured domains such as finance and spreadsheet-based workflows. Designed for advanced development and agentic systems, Gemini 3.1 Pro Preview improves long-horizon stability and tool orchestration while increasing token efficiency. It introduces a new medium thinking level to better balance cost, speed, and performance. The model excels in agentic coding, structured planning, multimodal analysis, and workflow automation, making it well-suited for autonomous agents, financial modeling, spreadsheet automation, and high-context enterprise tasks.
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 loops, supporting text, image, video, audio, and PDF inputs. Defaults to medium thinking effort for faster and more cost-efficient responses, with full support for thinking levels (minimal, low, medium, high) for fine-grained cost/performance trade-offs.
Best for token efficiency in coding, knowledge work, and multimodal tasks
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 problem solving.
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.
GLM-5.3-Flash 是 GLM-5 系列首个原生多模态模型，以极致低成本架构实现超越 GLM-5.2 的更强智能
GPT-4.1 是一款针对高级指令遵循、实际软件工程以及长语境推理进行优化的大型语言模型。它支持 100 万个标记的上下文窗口，并在编码（54.6% 的 SWE-bench 验证分数）、指令遵循（87.4% 的 IFEval）以及多模态理解基准测试中优于 GPT-4o 和 GPT-4.5。它针对精确的代码差异、代理可靠性以及大型文档环境中的高召回率进行了优化，因此非常适合用于代理、集成开发环境工具和企业知识检索。
GPT-4.1 是一款针对高级指令遵循、实际软件工程以及长语境推理进行优化的大型语言模型。它支持 100 万个标记的上下文窗口，并在编码（54.6% 的 SWE-bench 验证分数）、指令遵循（87.4% 的 IFEval）以及多模态理解基准测试中优于 GPT-4o 和 GPT-4.5。它针对精确的代码差异、代理可靠性以及大型文档环境中的高召回率进行了优化，因此非常适合用于代理、集成开发环境工具和企业知识检索。
GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard instruction evals, 35.8% on MultiChallenge, and 84.1% on IFEval. Mini also shows strong coding ability (e.g., 31.6% on Aider’s polyglot diff benchmark) and vision understanding, making it suitable for interactive applications with tight performance constraints.
GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard instruction evals, 35.8% on MultiChallenge, and 84.1% on IFEval. Mini also shows strong coding ability (e.g., 31.6% on Aider’s polyglot diff benchmark) and vision understanding, making it suitable for interactive applications with tight performance constraints.
For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million token context window, and scores 80.1% on MMLU, 50.3% on GPQA, and 9.8% on Aider polyglot coding – even higher than GPT‑4o mini. It’s ideal for tasks like classification or autocompletion.
For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million token context window, and scores 80.1% on MMLU, 50.3% on GPQA, and 9.8% on Aider polyglot coding – even higher than GPT‑4o mini. It’s ideal for tasks like classification or autocompletion.
GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of GPT-4 Turbo while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities. For benchmarking against other models, it was briefly called "im-also-a-good-gpt2-chatbot" #multimodal
The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance & readability. It’s also better at working with uploaded files, providing deeper insights & more thorough responses.
GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable than other recent frontier models, and more than 60% cheaper than GPT-3.5 Turbo. It maintains SOTA intelligence, while being significantly more cost-effective. GPT-4o mini achieves an 82% score on MMLU and presently ranks higher than GPT-4 on chat preferences common leaderboards. Check out the launch announcement to learn more. #multimodal
GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable than other recent frontier models, and more than 60% cheaper than GPT-3.5 Turbo. It maintains SOTA intelligence, while being significantly more cost-effective.
OpenAI GPT-4o Mini TTS - Text to speech
GPT-5 是 OpenAI 最先进的模型，其在推理能力、代码质量以及用户体验方面都有显著提升。该模型针对需要分步推理、遵循指令以及在高风险应用场景中保持高准确性的复杂任务进行了优化。它支持测试时的路由功能和高级的提示理解，包括用户指定的意图，例如“好好思考一下这个”。改进之处包括减少了幻觉、谄媚行为，并在编码、写作和健康相关任务中表现得更为出色。
No description provided for this model
GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost. GPT-5 Mini is the successor to OpenAI's o4-mini model.
GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost. GPT-5 Mini is the successor to OpenAI's o4-mini model.
GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger counterparts, it retains key instruction-following and safety features. It is the successor to GPT-4.1-nano and offers a lightweight option for cost-sensitive or real-time applications.
GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger counterparts, it retains key instruction-following and safety features. It is the successor to GPT-4.1-nano and offers a lightweight option for cost-sensitive or real-time applications.
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 to allocate computation dynamically, responding quickly to simple queries while spending more depth on complex tasks. The model produces clearer, more grounded explanations with reduced jargon, making it easier to follow even on technical or multi-step problems. Built for broad task coverage, GPT-5.1 delivers consistent gains across math, coding, and structured analysis workloads, with more coherent long-form answers and improved tool-use reliability. It also features refined conversational alignment, enabling warmer, more intuitive responses without compromising precision. GPT-5.1 serves as the primary full-capability successor to GPT-5
GPT-5.1 Chat 模型（又名“即时版”，是 5.1 系列中一款快速、轻量且高效的成员，专为低延迟聊天而优化，同时保留了强大的通用智能。它采用自适应推理技术，对较难的问题进行有选择性的“思考”，从而在数学、编程和多步骤任务方面提高准确性，同时不会影响正常的对话速度。该模型默认情况下更亲切、更具对话性，具有更好的指令响应能力和更稳定的简短推理能力。GPT-5.1 会话模型专为高吞吐量、交互性工作负载而设计，在响应速度和一致性方面比深度思考更为重要。）
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. The model supports building projects from scratch, feature development, debugging, large-scale refactoring, and code review. Compared to GPT-5.1, Codex is more steerable, adheres closely to developer instructions, and produces cleaner, higher-quality code outputs. Reasoning effort can be adjusted with the reasoning.effort parameter. Codex integrates into developer environments including the CLI, IDE extensions, GitHub, and cloud tasks. It adapts reasoning effort dynamically—providing fast responses for small tasks while sustaining extended multi-hour runs for large projects. The model is trained to perform structured code reviews, catching critical flaws by reasoning over dependencies and validating behavior against tests. It also supports multimodal inputs such as images or screenshots for UI development and integrates tool use for search, dependency installation, and environment setup. Codex is intended specifically for agentic coding applications.
GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex
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 text and image inputs, enabling high-context reasoning, coding, and multimodal analysis within the same workflow. The model delivers improved performance in coding, document understanding, tool use, and instruction following. It is designed as a strong default for both general-purpose tasks and software engineering, capable of generating production-quality code, synthesizing information across multiple sources, and executing complex multi-step workflows with fewer iterations and greater token efficiency.
No description provided for this model
No description provided for this model
OpenAI gpt-5.5
pro逆向，逆向web pro
No description provided for this model
No description provided for this model
No description provided for this model
No description provided for this model
No description provided for this model
GPT-6 Astra is our most capable model, built for the hardest end-to-end work. Use it for complex reasoning, coding, computer use, research, and document creation. reasoning.effort supports low, medium, high, xhigh, and max.
No description provided for this model
No description provided for this model
No description provided for this model
No description provided for this model
OpenAI 实时语音对话模型，支持音频、文本与图像输入。
OpenAI 实时语音对话模型精简版，音频价格约为旗舰版的三分之一。
A lightweight model that thinks before responding. Fast, smart, and great for logic-based tasks that do not require deep domain knowledge. The raw thinking traces are accessible.
No description provided for this model
No description provided for this model
No description provided for this model
No description provided for this model
xAI's fast coding model trained specifically for agentic coding. Currently in early access.
No description provided for this model
Grok Imagine Image 2.0 is an image generation and editing model from xAI. It is suited for creating images from text prompts and editing images from references, with low and medium quality modes.
No description provided for this model
No description provided for this model
grok-imagine-video-1.5-preview 最新视频模型
Tencent1.0M tokensNo description provided for this model
No description provided for this model
Xiaomi1.0M tokensNo description provided for this model
Xiaomi1.0M tokens文本生成-通用大语言模型
Xiaomi1.0M tokensMiMo-V2.5-Pro 的 UltraSpeed 体验模式——一款万亿参数（1T）旗舰型号，推理速度最高可达 1000 token/s，专为最苛刻的实时场景设计。
Xiaomi256K tokensNo description provided for this model
Xiaomi4K tokensNo description provided for this model
Xiaomi4K tokensNo description provided for this model
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 capability while maintaining exceptional latency, scalability, and cost efficiency. Compared to its predecessor, M2.1 delivers cleaner, more concise outputs and faster perceived response times. It shows leading multilingual coding performance across major systems and application languages, achieving 49.4% on Multi-SWE-Bench and 72.5% on SWE-Bench Multilingual, and serves as a versatile agent “brain” for IDEs, coding tools, and general-purpose assistance. To avoid degrading this model's performance, MiniMax highly recommends preserving reasoning between turns. Learn more about using reasoning_details to pass back reasoning in our docs.
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 capability while maintaining exceptional latency, scalability, and cost efficiency. Compared to its predecessor, M2.1 delivers cleaner, more concise outputs and faster perceived response times. It shows leading multilingual coding performance across major systems and application languages, achieving 49.4% on Multi-SWE-Bench and 72.5% on SWE-Bench Multilingual, and serves as a versatile agent “brain” for IDEs, coding tools, and general-purpose assistance. To avoid degrading this model's performance, MiniMax highly recommends preserving reasoning between turns. Learn more about using reasoning_details to pass back reasoning in our docs.
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 to extend into general office work, reaching fluency in generating and operating Word, Excel, and Powerpoint files, context switching between diverse software environments, and working across different agent and human teams. Scoring 80.2% on SWE-Bench Verified, 51.3% on Multi-SWE-Bench, and 76.3% on BrowseComp, M2.5 is also more token efficient than previous generations, having been trained to optimize its actions and output through planning.
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 to extend into general office work, reaching fluency in generating and operating Word, Excel, and Powerpoint files, context switching between diverse software environments, and working across different agent and human teams. Scoring 80.2% on SWE-Bench Verified, 51.3% on Multi-SWE-Bench, and 76.3% on BrowseComp, M2.5 is also more token efficient than previous generations, having been trained to optimize its actions and output through planning.
No description provided for this model
MiniMax-M2.7-highspeed
Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, audio, and PDF documents, returns text, and offers a 1M-token context window. The model is built to support multi-agent workflows, whether as either a main agent that plans and delegates or as a subagent executing in parallel. It works across multiple coding harnesses and supports structured output, parallel function calling, and configurable reasoning effort. In Meta’s testing, it performs well on multi-file refactors, extended debugging sessions, whole-repository generation, and tasks that stretch well past a single prompt.
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 across extended tasks, work through conflicting inputs, and request clarification or confirmation when needed. Prompts and outputs may be used to improve Meta’s products.
OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. This model supports the reasoning_effort parameter, which can be set to "high", "medium", or "low" to control the thinking time of the model. The default is "medium". OpenRouter also offers the model slug openai/o3-mini-high to default the parameter to "high". The model features three adjustable reasoning effort levels and supports key developer capabilities including function calling, structured outputs, and streaming, though it does not include vision processing capabilities. The model demonstrates significant improvements over its predecessor, with expert testers preferring its responses 56% of the time and noting a 39% reduction in major errors on complex questions. With medium reasoning effort settings, o3-mini matches the performance of the larger o1 model on challenging reasoning evaluations like AIME and GPQA, while maintaining lower latency and cost.
o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following. Use it to think through multi-step problems that involve analysis across text, code, and images.
OpenAI o3-mini-high is the same model as o3-mini with reasoning_effort set to high. o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. The model features three adjustable reasoning effort levels and supports key developer capabilities including function calling, structured outputs, and streaming, though it does not include vision processing capabilities. The model demonstrates significant improvements over its predecessor, with expert testers preferring its responses 56% of the time and noting a 39% reduction in major errors on complex questions. With medium reasoning effort settings, o3-mini matches the performance of the larger o1 model on challenging reasoning evaluations like AIME and GPQA, while maintaining lower latency and cost.
OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning and coding performance across benchmarks like AIME (99.5% with Python) and SWE-bench, outperforming its predecessor o3-mini and even approaching o3 in some domains. Despite its smaller size, o4-mini exhibits high accuracy in STEM tasks, visual problem solving (e.g., MathVista, MMMU), and code editing. It is especially well-suited for high-throughput scenarios where latency or cost is critical. Thanks to its efficient architecture and refined reinforcement learning training, o4-mini can chain tools, generate structured outputs, and solve multi-step tasks with minimal delay—often in under a minute.
OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning and coding performance across benchmarks like AIME (99.5% with Python) and SWE-bench, outperforming its predecessor o3-mini and even approaching o3 in some domains. Despite its smaller size, o4-mini exhibits high accuracy in STEM tasks, visual problem solving (e.g., MathVista, MMMU), and code editing. It is especially well-suited for high-throughput scenarios where latency or cost is critical. Thanks to its efficient architecture and refined reinforcement learning training, o4-mini can chain tools, generate structured outputs, and solve multi-step tasks with minimal delay—often in under a minute.
No description provided for this model
Alibaba1.0M tokensQwen3.8 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.
Alibaba1.0M tokensA 2.4 trillion-parameter MoE flagship, with comprehensive programming and office capabilities significantly enhanced. It can autonomously program for several days to complete a complete project. Capable of handling hundreds of professional tasks such as law, finance, and design, delivering production-level results end-to-end through a single conversation. Native visual understanding runs through the entire process of planning, execution, and verification, supporting deep semantic parsing of ultra-long documents and long videos. Autonomous planning and closed-loop iteration in long-term tasks, continuously evolving.
ByteDance4K tokensNo description provided for this model
ByteDance4K tokensNo description provided for this model
ByteDance4K tokensNo description provided for this model
ByteDance4K tokensNo description provided for this model
ByteDance4K tokensNo description provided for this model
ByteDance4K tokensNo description provided for this model
ByteDance4K tokensNo description provided for this model
Sora 2 is OpenAI's latest video and audio generation model, capable of directly outputting movie-level realistic videos based on text prompts. It features complete audio-visual capabilities such as multi-camera narrative, environmental and physical simulation, and synchronized sound effects. Users can also inject their own appearance and voice into characters through selfies or voice recordings, enabling "everyone to act in movies". In terms of real-world simulation, Sora 2 can precisely reproduce natural phenomena such as water, fabric, and gravity by following the laws of object movement, material properties, light and shadow, and dynamics, making character and camera movements highly credible.
text-embedding-3-large is OpenAI's most capable embedding model for both english and non-english tasks. Embeddings are a numerical representation of text that can be used to measure the relatedness between two pieces of text. Embeddings are useful for search, clustering, recommendations, anomaly detection, and classification tasks.
text-embedding-3-small is OpenAI's improved, more performant version of the ada embedding model. Embeddings are a numerical representation of text that can be used to measure the relatedness between two pieces of text. Embeddings are useful for search, clustering, recommendations, anomaly detection, and classification tasks.
text-embedding-ada-002 is OpenAI's legacy text embedding model.
No description provided for this model