GPT-4o
旗舰级通用模型，兼顾高级推理与多模态能力
available · 2026-10-15T02:47:32.213716143+00:00InferLink Unified AI API
Access verified multi-provider AI models through one OpenAI-compatible API.
Available models
DeepSeek V3
高性价比模型，强调代码与数学推理能力
available · 2026-10-15T02:47:32.213721448+00:00Flux Pro
高保真图像生成，支持复杂场景和细节
available · 2026-10-15T02:47:32.213726252+00:00Chatgpt-4o-latest
ChatGPT-4o 指向 ChatGPT 中当前使用的 GPT-4o 快照。我们建议对大多数 API 集成使用 GPT-5 或 GPT-4o 等 API 模型，但您也可以随意使用此 ChatGPT-4o 模型来测试我们针对聊天用例的最新改进。
available · 2026-10-15T02:47:32.213730595+00:00Chatterbox-pro
Generate expressive, natural speech with Resemble AI's Chatterbox.
available · 2026-10-15T02:47:32.213734716+00:00Claude-3.5-haiku
Anthropic's fastest, most cost-effective model, with a 200K token context window (claude-3-5-haiku-20241022)
available · 2026-10-15T02:47:32.213739804+00:00Claude-fable-5
Claude Fable 5 text model
available · 2026-10-15T02:47:32.213743279+00:00Claude-fable-5-thinking
Claude Fable 5 Thinking text model
available · 2026-10-15T02:47:32.213746640+00:00Claude-haiku-4-5-20251001
该模型尚未补充完整说明，欢迎联系 InferLink 获取更多资料。
available · 2026-10-15T02:47:32.213750561+00:00Claude-opus-4-5-20251101
该模型尚未补充完整说明，欢迎联系 InferLink 获取更多资料。
available · 2026-10-15T02:47:32.213755079+00:00Claude-opus-4-5-20251101-thinking
Claude Opus 4.5 是 Anthropic 领先的推理模型，专为复杂的软件工程、代理工作流和长期计算机使用而优化。它提供强大的多模态能力，在实际编码和推理基准测试中具有竞争力的性能，并提高了对提示注入的鲁棒性。
available · 2026-10-15T02:47:32.213759439+00:00Claude-opus-4-6
该模型尚未补充完整说明，欢迎联系 InferLink 获取更多资料。
available · 2026-10-15T02:47:32.213762471+00:00Claude-opus-4-6-thinking
该模型尚未补充完整说明，欢迎联系 InferLink 获取更多资料。
available · 2026-10-15T02:47:32.213765207+00:00Claude-opus-4-7
在 Opus 4.6 的编码和代理功能优势基础上，显著提升了复杂多步骤任务的性能，并在扩展工作流中实现了更可靠的代理执行。它尤其适用于任务随时间展开的异步代理管道、大型代码库、多阶段调试以及端到端项目编排。
available · 2026-10-15T02:47:32.213768110+00:00Claude-opus-4-7-thinking
在 Opus 4.6 的编码和代理功能优势基础上，显著提升了复杂多步骤任务的性能，并在扩展工作流中实现了更可靠的代理执行。它尤其适用于任务随时间展开的异步代理管道、大型代码库、多阶段调试以及端到端项目编排。
available · 2026-10-15T02:47:32.213771612+00:00Claude-opus-4-8
Claude Opus 4.8，Deeprouter 聚合的高能力 Anthropic 模型。当前按 Opus 4.7 同档价格临时上线，待页面价格复核后回填。
available · 2026-10-15T02:47:32.213774983+00:00Claude-opus-4-8-thinking
Claude Opus 4.8 Thinking，Deeprouter 聚合的高能力 Anthropic 思考模型。当前按 Opus 4.7 Thinking 同档价格临时上线，待页面价格复核后回填。
available · 2026-10-15T02:47:32.213777882+00:00Claude-sonnet-4-20250514
Claude Sonnet 4显著增强了其前身Sonnet 3.7的能力，在编码和推理任务中都表现出色，且精度和可控性均有所提高。
available · 2026-10-15T02:47:32.213782682+00:00Claude-sonnet-4-20250514-thinking
Claude Sonnet 4显著增强了其前身Sonnet 3.7的能力，在编码和推理任务中都表现出色，且精度和可控性均有所提高。
available · 2026-10-15T02:47:32.213785978+00:00Claude-sonnet-4-5
该模型尚未补充完整说明，欢迎联系 InferLink 获取更多资料。
available · 2026-10-15T02:47:32.213789140+00:00Claude-sonnet-4-5-20250929
该模型尚未补充完整说明，欢迎联系 InferLink 获取更多资料。
available · 2026-10-15T02:47:32.213792317+00:00Claude-sonnet-4-5-20250929-thinking
该模型尚未补充完整说明，欢迎联系 InferLink 获取更多资料。
available · 2026-10-15T02:47:32.213795475+00:00Claude-sonnet-4-5-thinking
该模型尚未补充完整说明，欢迎联系 InferLink 获取更多资料。
available · 2026-10-15T02:47:32.213797928+00:00Claude-sonnet-4-6
该模型尚未补充完整说明，欢迎联系 InferLink 获取更多资料。
available · 2026-10-15T02:47:32.213800466+00:00Claude-sonnet-4-6-thinking
该模型尚未补充完整说明，欢迎联系 InferLink 获取更多资料。
available · 2026-10-15T02:47:32.213802845+00:00Claude-sonnet-5
Claude Sonnet 5 text model
available · 2026-10-15T02:47:32.213805237+00:00Clip
Official CLIP models, generate CLIP (clip-vit-large-patch14) text & image embeddings
available · 2026-10-15T02:47:32.213809893+00:00Cosyvoice-v1
Aliyun CosyVoice native text to speech
available · 2026-10-15T02:47:32.213813847+00:00Cosyvoice-v3-flash
Aliyun CosyVoice native text to speech
available · 2026-10-15T02:47:32.213816829+00:00Create
Image generation model from Reve
available · 2026-10-15T02:47:32.213821666+00:00Cs-claude-opus-4-5
Claude Opus 4.5 是 Anthropic 领先的推理模型，专为复杂的软件工程、代理工作流和长期计算机使用而优化。它提供强大的多模态能力，在实际编码和推理基准测试中具有竞争力的性能，并提高了对提示注入的鲁棒性。
available · 2026-10-15T02:47:32.213824653+00:00Cs-claude-opus-4-5-thinking
Claude Opus 4.5 是 Anthropic 领先的推理模型，专为复杂的软件工程、代理工作流和长期计算机使用而优化。它提供强大的多模态能力，在实际编码和推理基准测试中具有竞争力的性能，并提高了对提示注入的鲁棒性。
available · 2026-10-15T02:47:32.213828146+00:00Cs-claude-opus-4-6
Opus 4.6 是 Anthropic 在编码和长期专业任务方面最强的模型。它专为在完整工作流程中运行的代理而设计，而不是针对单个提示，这使得它在处理大型代码库、复杂重构和多步骤调试（这些任务随时间展开）时特别有效。
available · 2026-10-15T02:47:32.213832097+00:00Cs-claude-opus-4-6-thinking
Opus 4.6 是 Anthropic 在编码和长期专业任务方面最强的模型。它专为在完整工作流程中运行的代理而设计，而不是针对单个提示，这使得它在处理大型代码库、复杂重构和多步骤调试（这些任务随时间展开）时特别有效。
available · 2026-10-15T02:47:32.213837234+00:00Cs-claude-opus-4-7
在 Opus 4.6 的编码和代理功能优势基础上，显著提升了复杂多步骤任务的性能，并在扩展工作流中实现了更可靠的代理执行。它尤其适用于任务随时间展开的异步代理管道、大型代码库、多阶段调试以及端到端项目编排。
available · 2026-10-15T02:47:32.213840339+00:00Cs-claude-opus-4-7-thinking
在 Opus 4.6 的编码和代理功能优势基础上，显著提升了复杂多步骤任务的性能，并在扩展工作流中实现了更可靠的代理执行。它尤其适用于任务随时间展开的异步代理管道、大型代码库、多阶段调试以及端到端项目编排。
available · 2026-10-15T02:47:32.213843273+00:00Cs-claude-sonnet-4-6
Sonnet 4.6 是 Anthropic 迄今为止功能最强大的 Sonnet 系列产品，在编码、代理和专业工作方面均展现出卓越的性能。它擅长迭代开发、复杂代码库导航、端到端项目管理（含内存管理）、文档创建以及在 Web 质量保证和工作流自动化方面的出色计算机应用。
available · 2026-10-15T02:47:32.213846536+00:00Cs-claude-sonnet-4-6-thinking
Sonnet 4.6 是 Anthropic 迄今为止功能最强大的 Sonnet 系列产品，在编码、代理和专业工作方面均展现出卓越的性能。它擅长迭代开发、复杂代码库导航、端到端项目管理（含内存管理）、文档创建以及在 Web 质量保证和工作流自动化方面的出色计算机应用。
available · 2026-10-15T02:47:32.213849452+00:00Cs-gemini-2.5-pro
Gemini 2.5 Pro 是谷歌最先进的 AI 模型，专为高级推理、编码、数学和科学任务设计。它采用“思维”能力，使其能够以更高的准确性和更细致的上下文处理能力进行推理响应。
available · 2026-10-15T02:47:32.213852257+00:00Cs-gemini-3-pro
Gemini 3 Pro 是谷歌的旗舰前沿模型，专为高精度多模态推理而设计，能够在文本、图像、视频、音频和代码等多种模态上表现出强大的性能，并具备 100 万 token 的上下文窗口。
available · 2026-10-15T02:47:32.213855604+00:00Dall-e-2
The original classic DALLᐧE 2
available · 2026-10-15T02:47:32.213859107+00:00Dall-e-3
OpenAI high-quality creative image generation
available · 2026-10-15T02:47:32.213862129+00:00Deepseek-chat
DeepSeek Chat
available · 2026-10-15T02:47:32.213865028+00:00Deepseek-r1
A reasoning model trained with reinforcement learning, on par with OpenAI o1
available · 2026-10-15T02:47:32.213868296+00:00Deepseek-reasoner
DeepSeek Reasoner
available · 2026-10-15T02:47:32.213870817+00:00Deepseek-v3
DeepSeek-V3-0324 is the leading non-reasoning model, a milestone for open source
available · 2026-10-15T02:47:32.213874094+00:00Deepseek-v3.1
DeepSeek-V3.1是一个大型混合推理模型（671B参数，37B活跃），支持通过提示模板实现思维和非思维两种模式。它在DeepSeek-V3基础模型上通过两阶段长上下文训练过程进行扩展，最长可达128K tokens，并使用FP8微缩放以实现高效推理。
available · 2026-10-15T02:47:32.213876928+00:00Deepseek-v3.1
Latest hybrid thinking model from Deepseek
available · 2026-10-15T02:47:32.213879955+00:00Deepseek-v3.2
DeepSeek-V3.2，它引入了 DeepSeek 稀疏注意力（DSA），这是一种细粒度的稀疏注意力机制，旨在提高长上下文场景中的训练和推理效率，同时保持输出质量。用户可以通过启用推理布尔值来控制推理行为。
available · 2026-10-15T02:47:32.213883364+00:00Deepseek-v4-flash
DeepSeek V4 Flash
available · 2026-10-15T02:47:32.213885915+00:00Deepseek-v4-pro
DeepSeek V4 Pro
available · 2026-10-15T02:47:32.213888926+00:00Doubao-seed-1-6-251015
Doubao Seed 1.6
available · 2026-10-15T02:47:32.213891562+00:00Doubao-seed-1-8
该模型尚未补充完整说明，欢迎联系 InferLink 获取更多资料。
available · 2026-10-15T02:47:32.213894494+00:00Doubao-seed-2-0-code
该模型尚未补充完整说明，欢迎联系 InferLink 获取更多资料。
available · 2026-10-15T02:47:32.213898140+00:00Doubao-seed-2-0-code-preview-260215
该模型尚未补充完整说明，欢迎联系 InferLink 获取更多资料。
available · 2026-10-15T02:47:32.213903630+00:00Doubao-seed-2-0-lite
该模型尚未补充完整说明，欢迎联系 InferLink 获取更多资料。
available · 2026-10-15T02:47:32.213908393+00:00Doubao-seed-2-0-mini
该模型尚未补充完整说明，欢迎联系 InferLink 获取更多资料。
available · 2026-10-15T02:47:32.213912515+00:00Doubao-seed-2-0-pro
该模型尚未补充完整说明，欢迎联系 InferLink 获取更多资料。
available · 2026-10-15T02:47:32.213917276+00:00Doubao-seed-character
该模型尚未补充完整说明，欢迎联系 InferLink 获取更多资料。
available · 2026-10-15T02:47:32.213922306+00:00Doubao-seed-translation
该模型尚未补充完整说明，欢迎联系 InferLink 获取更多资料。
available · 2026-10-15T02:47:32.213927283+00:00Doubao-seedance-1-0-pro-250528
ByteDance Seedance 1.0 Pro video generation
available · 2026-10-15T02:47:32.213931640+00:00Doubao-seedance-1-0-pro-fast-251015
ByteDance Seedance 1.0 Pro fast video generation
available · 2026-10-15T02:47:32.213935626+00:00Doubao-seedance-2-0
ByteDance Seedance 2.0 multimodal video generation
available · 2026-10-15T02:47:32.213939505+00:00Doubao-seedance-2-0-fast
ByteDance Seedance 2.0 fast multimodal video generation
available · 2026-10-15T02:47:32.213943347+00:00Doubao-seedance-2-0-mini
ByteDance Seedance 2.0 mini multimodal video generation
available · 2026-10-15T02:47:32.213947140+00:00Doubao-seedream-5-0
该模型尚未补充完整说明，欢迎联系 InferLink 获取更多资料。
available · 2026-10-15T02:47:32.213956375+00:00Dreamina-3.1
4MP text-to-image generation with enhanced cinematic-quality image generation with precise style control, improved text rendering, and commercial design optimization.
available · 2026-10-15T02:47:32.213963053+00:00Fibo
SOTA Open source model trained on licensed data, transforming intent into structured control for precise, high-quality AI image generation in enterprise and agentic workflows.
available · 2026-10-15T02:47:32.213969871+00:00Flux-1.1-pro
Faster, better FLUX Pro. Text-to-image model with excellent image quality, prompt adherence, and output diversity.
available · 2026-10-15T02:47:32.213976060+00:00Flux-1.1-pro-ultra
FLUX1.1 [pro] in ultra and raw modes. Images are up to 4 megapixels. Use raw mode for realism.
available · 2026-10-15T02:47:32.213982978+00:00Flux-2-dev
Quality image generation and editing with support for reference images
available · 2026-10-15T02:47:32.213988541+00:00Flux-2-flex
Max-quality image generation and editing with support for ten reference images
available · 2026-10-15T02:47:32.213994169+00:00Flux-2-klein-4b
Very fast image generation and editing model. 4 steps distilled, sub-second inference for production and near real-time applications.
available · 2026-10-15T02:47:32.214000510+00:00Flux-2-klein-4b-base
Un-distilled version of FLUX.2 [klein]. Optimized for fine-tuning, customization, and post-training workflows
available · 2026-10-15T02:47:32.214006692+00:00Flux-2-klein-9b
4 step distilled version of FLUX.2 [klein]. A foundation model for maximum flexibility and control
available · 2026-10-15T02:47:32.214012349+00:00Flux-2-klein-9b-base
Un-distilled version of FLUX.2 [klein]. A foundation model for maximum flexibility and control
available · 2026-10-15T02:47:32.214018359+00:00Flux-2-max
The highest fidelity image model from Black Forest Labs
available · 2026-10-15T02:47:32.214023582+00:00Flux-dev
A 12 billion parameter rectified flow transformer capable of generating images from text descriptions
available · 2026-10-15T02:47:32.214029388+00:00Flux-fast
This is the fastest Flux endpoint in the world.
available · 2026-10-15T02:47:32.214034480+00:00Flux-kontext-max
A premium text-based image editing model that delivers maximum performance and improved typography generation for transforming images through natural language prompts
available · 2026-10-15T02:47:32.214040183+00:00Flux-kontext-pro
A state-of-the-art text-based image editing model that delivers high-quality outputs with excellent prompt following and consistent results for transforming images through natural language
available · 2026-10-15T02:47:32.214046007+00:00Flux-krea-dev
An opinionated text-to-image model from Black Forest Labs in collaboration with Krea that excels in photorealism. Creates images that avoid the oversaturated "AI look".
available · 2026-10-15T02:47:32.214051808+00:00Flux-schnell
The fastest image generation model tailored for local development and personal use
available · 2026-10-15T02:47:32.214057358+00:00Gemini-2.5-flash
Google’s hybrid “thinking” AI model optimized for speed and cost-efficiency
available · 2026-10-15T02:47:32.214061648+00:00Gemini-2.5-flash-image
Google's latest image generation model in Gemini 2.5
available · 2026-10-15T02:47:32.214066159+00:00Gemini-2.5-flash-image-preview
谷歌绘画 Nano Banana原生多模态模型， 使用简单的文本提示转换任何图像。提供一致的角色编辑和场景保留，超越 Flux Kontext。体验 AI 图像编辑的未来。
available · 2026-10-15T02:47:32.214070562+00:00Gemini-2.5-flash-lite
Gemini 2.5 系列中的一个轻量级推理模型，它经过优化，可实现超低延迟和高成本效益。与早期的 Flash 模型相比，它提供了更高的吞吐量、更快的令牌生成速度以及在常见基准测试中更优的性能。
available · 2026-10-15T02:47:32.214074967+00:00Gemini-2.5-flash-thinking
Gemini 2.5 Flash 是谷歌最先进的主力模型，专为高级推理、编码、数学和科学任务设计。它内置“思考”能力，能够提供更准确的响应和细致的上下文处理。
available · 2026-10-15T02:47:32.214079935+00:00Gemini-3-flash
Google's most intelligent model built for speed with frontier intelligence, superior search, and grounding
available · 2026-10-15T02:47:32.214085029+00:00Gemini-3-flash-preview
Gemini 3 Flash Preview 是一款高速、高价值的思维模型，专为代理工作流程、多轮对话和编码辅助而设计。它提供接近 Pro 级别的推理和工具使用性能，同时延迟远低于大型 Gemini 变体，使其非常适合交互式开发、长时间运行的代理循环和协作编码任务。与 Gemini 2.5 Flash 相比，它在推理、多模态理解和可靠性方面提供了全面的质量改进。
available · 2026-10-15T02:47:32.214089784+00:00Gemini-3-pro
Google's most advanced reasoning Gemini model
available · 2026-10-15T02:47:32.214093791+00:00Gemini-3.1-flash-lite-preview
Google 针对高容量使用场景优化的高效模型。其整体质量优于 Gemini 2.5 Flash Lite，并在关键功能方面接近 Gemini 2.5 Flash 的性能。
available · 2026-10-15T02:47:32.214098379+00:00Gemini-3.1-pro
Google's most intelligent model, with improved reasoning and a new medium thinking level
available · 2026-10-15T02:47:32.214102951+00:00Gemini-3.1-pro-preview
Google Gemini 3.1 Pro Preview, next-gen multimodal reasoning flagship with Thinking mode
available · 2026-10-15T02:47:32.214106984+00:00Gen4-image
Runway's Gen-4 Image model with references. Use up to 3 reference images to create the exact image you need. Capture every angle.
available · 2026-10-15T02:47:32.214113069+00:00Generalv3.5
Spark General V3.5
available · 2026-10-15T02:47:32.214118149+00:00Glm-4.5
Zhipu GLM-4.5 text model
available · 2026-10-15T02:47:32.214126521+00:00Glm-4.5-air
Zhipu GLM-4.5 Air text model
available · 2026-10-15T02:47:32.214131796+00:00Glm-4.6
Zhipu GLM-4.6 text model
available · 2026-10-15T02:47:32.214138694+00:00Glm-4.7
Zhipu GLM-4.7 text model
available · 2026-10-15T02:47:32.214146920+00:00Glm-4.7-flash
Zhipu GLM-4.7 Flash native text model
available · 2026-10-15T02:47:32.214152709+00:00Glm-4.7-flashx
Zhipu GLM-4.7 FlashX text model
available · 2026-10-15T02:47:32.214158134+00:00Glm-5
Zhipu GLM-5 text model
available · 2026-10-15T02:47:32.214165649+00:00Glm-5-turbo
Zhipu GLM-5 Turbo text model
available · 2026-10-15T02:47:32.214170384+00:00Glm-5.1
Zhipu GLM-5.1 text model
available · 2026-10-15T02:47:32.214178443+00:00Glm-5.2
GLM 5.2 coding and agent model
available · 2026-10-15T02:47:32.214185061+00:00Gpt-3.5-turbo
该模型尚未补充完整说明，欢迎联系 InferLink 获取更多资料。
available · 2026-10-15T02:47:32.214189529+00:00Gpt-4-turbo
Optimized GPT-4 version with faster response, larger context window, and better cost-effectiveness.
available · 2026-10-15T02:47:32.214193162+00:00Gpt-4.1
OpenAI's Flagship GPT model for complex tasks.
available · 2026-10-15T02:47:32.214197938+00:00Gpt-4.1-mini
Fast, affordable version of GPT-4.1
available · 2026-10-15T02:47:32.214202357+00:00Gpt-4.1-nano
Fastest, most cost-effective GPT-4.1 model from OpenAI
available · 2026-10-15T02:47:32.214206695+00:00Gpt-4o-image
OpenAI ChatGPT 4o 高级画图功能，支持图片编辑和中文文字画图
available · 2026-10-15T02:47:32.214210625+00:00Gpt-4o-mini
Low latency, low cost version of OpenAI's GPT-4o model
available · 2026-10-15T02:47:32.214215111+00:00Gpt-5
OpenAI's new model excelling at coding, writing, and reasoning.
available · 2026-10-15T02:47:32.214220007+00:00Gpt-5-mini
Faster version of OpenAI's flagship GPT-5 model
available · 2026-10-15T02:47:32.214224190+00:00Gpt-5-structured
GPT-5 with support for structured outputs, web search and custom tools
available · 2026-10-15T02:47:32.214228704+00:00Gpt-5.1
The best model for coding and agentic tasks with configurable reasoning effort.
available · 2026-10-15T02:47:32.214234112+00:00Gpt-5.1-chat
GPT-5.1专为广泛任务覆盖而构建，在数学、编程和结构化分析等任务中均表现优异，生成长篇答案时更具连贯性，工具使用可靠性也显著提升。其对话协调能力经过优化，能在保持精确度的同时呈现更温暖、更直观的回应。
available · 2026-10-15T02:47:32.214237784+00:00Gpt-5.1-high
OpenAI next-generation flagship model with major breakthroughs in reasoning, multimodal understanding, and complex task handling.
available · 2026-10-15T02:47:32.214241445+00:00Gpt-5.2
The best model for coding and agentic tasks across industries
available · 2026-10-15T02:47:32.214246015+00:00Gpt-5.2-codex-high
OpenAI GPT-5.2 Codex high-performance tier, optimized for complex code generation and deep code reasoning
available · 2026-10-15T02:47:32.214249616+00:00Gpt-5.2-codex-low
OpenAI GPT-5.2 Codex low tier, suited for simple code completion and script generation
available · 2026-10-15T02:47:32.214253376+00:00Gpt-5.2-codex-medium
OpenAI GPT-5.2 Codex medium tier, cost-effective for code completion and refactoring
available · 2026-10-15T02:47:32.214257091+00:00Gpt-5.2-codex-xhigh
OpenAI GPT-5.2 Codex extra-high tier for the most complex large codebases and architecture design
available · 2026-10-15T02:47:32.214260559+00:00Gpt-5.2-high
GPT-5.2 是 GPT-5 系列中最新的前沿模型，与 GPT-5.1 相比，它提供了更强的代理能力和长上下文性能。它采用自适应推理来动态分配计算资源，对简单查询做出快速响应，同时在复杂任务上投入更多深度。
available · 2026-10-15T02:47:32.214265160+00:00Gpt-5.2-low
GPT-5.2 是 GPT-5 系列中最新的前沿模型，与 GPT-5.1 相比，它提供了更强的代理能力和长上下文性能。它采用自适应推理来动态分配计算资源，对简单查询做出快速响应，同时在复杂任务上投入更多深度。
available · 2026-10-15T02:47:32.214269276+00:00Gpt-5.2-medium
GPT-5.2 是 GPT-5 系列中最新的前沿模型，与 GPT-5.1 相比，它提供了更强的代理能力和长上下文性能。它采用自适应推理来动态分配计算资源，对简单查询做出快速响应，同时在复杂任务上投入更多深度。
available · 2026-10-15T02:47:32.214273678+00:00Gpt-5.2-pro
GPT-5.2 是 GPT-5 系列中最新的前沿模型，与 GPT-5.1 相比，它提供了更强的代理能力和长上下文性能。它采用自适应推理来动态分配计算资源，对简单查询做出快速响应，同时在复杂任务上投入更多深度。
available · 2026-10-15T02:47:32.214277468+00:00Gpt-5.2-xhigh
GPT-5.2 是 GPT-5 系列中最新的前沿模型，与 GPT-5.1 相比，它提供了更强的代理能力和长上下文性能。它采用自适应推理来动态分配计算资源，对简单查询做出快速响应，同时在复杂任务上投入更多深度。
available · 2026-10-15T02:47:32.214281396+00:00Gpt-5.3-codex
GPT‑5.2-Codex 基于 GPT‑5.2，并针对 Codex 智能体编码进行了深度优化，具体改进包括：通过上下文压缩 (compaction) 提升长程任务执行能力、在大规模代码变更（如重构与迁移）中具备更出色的性能、在 Windows 环境下实现更优表现，以及在网络安全方面显著增强。
available · 2026-10-15T02:47:32.214293607+00:00Gpt-5.3-codex-high
OpenAI GPT-5.3 Codex high tier, next-gen code intelligence with deeper context understanding
available · 2026-10-15T02:47:32.214297742+00:00Gpt-5.3-codex-low
OpenAI GPT-5.3 Codex low tier, low-latency code completion
available · 2026-10-15T02:47:32.214301251+00:00Gpt-5.3-codex-medium
OpenAI GPT-5.3 Codex medium tier, ideal for daily development coding assistance
available · 2026-10-15T02:47:32.214304500+00:00Gpt-5.3-codex-xhigh
OpenAI GPT-5.3 Codex extra-high tier for professional-grade code generation and system architecture reasoning
available · 2026-10-15T02:47:32.214308059+00:00Gpt-5.4
OpenAI's most capable frontier model for complex professional work, coding, and multi-step reasoning.
available · 2026-10-15T02:47:32.214312947+00:00Gpt-5.4-high
GPT-5.4 是 OpenAI 最新的前沿模型，它将 Codex 和 GPT 系列整合到一个统一的系统中。它拥有超过 100 万个 token 的上下文窗口，支持文本和图像输入，从而能够在同一工作流程中实现高上下文推理、编码和多模态分析。该模型在编码、文档理解、工具使用和指令执行方面均表现出色。
available · 2026-10-15T02:47:32.214316949+00:00Gpt-5.4-low
GPT-5.4 是 OpenAI 最新的前沿模型，它将 Codex 和 GPT 系列整合到一个统一的系统中。它拥有超过 100 万个 token 的上下文窗口，支持文本和图像输入，从而能够在同一工作流程中实现高上下文推理、编码和多模态分析。该模型在编码、文档理解、工具使用和指令执行方面均表现出色。
available · 2026-10-15T02:47:32.214320627+00:00Gpt-5.4-medium
OpenAI GPT-5.4 medium tier, balanced performance and cost
available · 2026-10-15T02:47:32.214323773+00:00Gpt-5.4-mini
OpenAI GPT-5.4 Mini lightweight model, fast responses for high-throughput everyday tasks
available · 2026-10-15T02:47:32.214326943+00:00Gpt-5.4-nano
OpenAI GPT-5.4 Nano ultra-lightweight model, ultra-low cost for simple classification and summarization
available · 2026-10-15T02:47:32.214330330+00:00Gpt-5.4-xhigh
OpenAI GPT-5.4 extra-high performance tier for the most complex reasoning and analysis tasks
available · 2026-10-15T02:47:32.214333767+00:00Gpt-5.5
GPT-5.5 擅长编写和调试代码、在线研究、分析数据、创建文档和电子表格、操作软件,以及在任务完成前跨越工具进行操作。
available · 2026-10-15T02:47:32.214338873+00:00Gpt-5.5-high
GPT-5.5 擅长编写和调试代码、在线研究、分析数据、创建文档和电子表格、操作软件,以及在任务完成前跨越工具进行操作。
available · 2026-10-15T02:47:32.214343041+00:00Gpt-5.5-low
GPT-5.5 擅长编写和调试代码、在线研究、分析数据、创建文档和电子表格、操作软件,以及在任务完成前跨越工具进行操作。
available · 2026-10-15T02:47:32.214347009+00:00Gpt-5.5-medium
GPT-5.5 擅长编写和调试代码、在线研究、分析数据、创建文档和电子表格、操作软件,以及在任务完成前跨越工具进行操作。
available · 2026-10-15T02:47:32.214352043+00:00Gpt-5.5-xhigh
GPT-5.5 擅长编写和调试代码、在线研究、分析数据、创建文档和电子表格、操作软件,以及在任务完成前跨越工具进行操作。
available · 2026-10-15T02:47:32.214356342+00:00Gpt-5.6-luna
GPT-5.6 Luna text model
available · 2026-10-15T02:47:32.214359687+00:00Gpt-5.6-sol
GPT-5.6 Sol text model
available · 2026-10-15T02:47:32.214363143+00:00Gpt-5.6-terra
GPT-5.6 Terra text model
available · 2026-10-15T02:47:32.214366602+00:00Gpt-6
OpenAI GPT-6 general-purpose text model
available · 2026-10-15T02:47:32.214371724+00:00Gpt-6-astra
OpenAI GPT-6 Astra general-purpose text model
available · 2026-10-15T02:47:32.214375877+00:00Gpt-6-luna
GPT-6 Luna general-purpose model
available · 2026-10-15T02:47:32.214380091+00:00Gpt-6-sol
GPT-6 Sol general-purpose model
available · 2026-10-15T02:47:32.214384410+00:00Gpt-6.1-sol
GPT-6.1 Sol Codex coding model
available · 2026-10-15T02:47:32.214388695+00:00Gpt-image-1
OpenAI GPT image generation model
available · 2026-10-15T02:47:32.214392770+00:00Gpt-image-1-vip
OpenAI 最新最先进的图像生成模型。它是一个原生的多模态语言模型，可以接受文本和图像输入，并生成图像输出。
available · 2026-10-15T02:47:32.214397154+00:00Gpt-image-1.5
OpenAI's latest image generation model with better instruction following and adherence to prompts
available · 2026-10-15T02:47:32.214401655+00:00Gpt-image-2
GPT Image 2 on the new Deeprouter endpoint
available · 2026-10-15T02:47:32.214405850+00:00Gpt-image-2-pro
该模型尚未补充完整说明，欢迎联系 InferLink 获取更多资料。
available · 2026-10-15T02:47:32.214410087+00:00Gpt-image-2.5-flare
GPT Image 2.5 Flare on the new Deeprouter endpoint
available · 2026-10-15T02:47:32.214414535+00:00Gpt-image-2.5-sunburst
GPT Image 2.5 Sunburst on the new Deeprouter endpoint
available · 2026-10-15T02:47:32.214419361+00:00Gpt-oss-120b
120b open-weight language model from OpenAI
available · 2026-10-15T02:47:32.214423906+00:00Gpt-oss-20b
20b open-weight language model from OpenAI
available · 2026-10-15T02:47:32.214428603+00:00Granite-4.0-h-small
Granite-4.0-H-Small is a 32B parameter long-context instruct model finetuned from Granite-4.0-H-Small-Base using a combination of open source instruction datasets with permissive license and internally collected synthetic datasets.
available · 2026-10-15T02:47:32.214434638+00:00Granite-8b-code-instruct-128k
Join the Granite community where you can find numerous recipe workbooks to help you get started with a wide variety of use cases using this model. https://github.com/ibm-granite-community
available · 2026-10-15T02:47:32.214441067+00:00Granite-vision-3.3-2b
Granite-vision-3.3-2b is a compact and efficient vision-language model, specifically designed for visual document understanding, enabling automated content extraction from tables, charts, infographics, plots, diagrams, and more.
available · 2026-10-15T02:47:32.214447217+00:00Grok-3-deepsearch
DeepSearch 旨在综合关键信息，对相互冲突的事实和观点进行推理，并从复杂性中提炼出清晰度。
available · 2026-10-15T02:47:32.214453024+00:00Grok-3-reasoning
思考模型。Grok-3 是马斯克旗下xAI公司开发的人工智能模型，具备128,000个Token的上下文处理能力，支持函数调用和系统提示，并计划推出多模态版本以处理图像。
available · 2026-10-15T02:47:32.214457997+00:00Grok-4
Grok 4 is xAI’s most advanced reasoning model. Excels at logical thinking and in-depth analysis. Ideal for insightful discussions and complex problem-solving.
available · 2026-10-15T02:47:32.214464721+00:00Grok-4-0709
xAI 最新的推理模型，拥有 256k 的上下文窗口。它支持并行工具调用、结构化输出以及图像和文本输入。
available · 2026-10-15T02:47:32.214472154+00:00Grok-4-image
xAI 最新的推理模型，拥有 256k 的上下文窗口。它支持并行工具调用、结构化输出以及图像和文本输入。
available · 2026-10-15T02:47:32.214479808+00:00Grok-4.1-fast
Grok 4.1版本在创造性、情感化和协作性互动方面表现卓越。它更能洞察细腻的意图，交谈更具吸引力，个性更加连贯，同时完全保留了前代产品锐利的智能与可靠性。
available · 2026-10-15T02:47:32.214486469+00:00Grok-4.2
xAI 最新的推理模型，拥有 256k 的上下文窗口。它支持并行工具调用、结构化输出以及图像和文本输入。
available · 2026-10-15T02:47:32.214494151+00:00Grok-4.2-image
xAI 最新的推理模型，拥有 256k 的上下文窗口。它支持并行工具调用、结构化输出以及图像和文本输入。
available · 2026-10-15T02:47:32.214500629+00:00Grok-4.6-high
Grok 4.6 reasoning model
available · 2026-10-15T02:47:32.214506759+00:00Grok-4.6-max
Grok 4.6 reasoning model
available · 2026-10-15T02:47:32.214512058+00:00Grok-4.6-xhigh
Grok 4.6 reasoning model
available · 2026-10-15T02:47:32.214517733+00:00Happyhorse-1.0-video-edit
Alibaba HappyHorse 1.0 video editing model
available · 2026-10-15T02:47:32.214522698+00:00Happyhorse-1.1-i2v
Alibaba HappyHorse 1.1 image-to-video model
available · 2026-10-15T02:47:32.214527636+00:00Happyhorse-1.1-r2v
Alibaba HappyHorse 1.1 reference-to-video model
available · 2026-10-15T02:47:32.214532710+00:00Happyhorse-1.1-t2v
Alibaba HappyHorse 1.1 text-to-video model
available · 2026-10-15T02:47:32.214538500+00:00Hunyuan-image-2.1
Generate high-quality 2K resolution images from text prompts
available · 2026-10-15T02:47:32.214544513+00:00Ideogram-v2
An excellent image model with state of the art inpainting, prompt comprehension and text rendering
available · 2026-10-15T02:47:32.214558099+00:00Ideogram-v2-turbo
A fast image model with state of the art inpainting, prompt comprehension and text rendering.
available · 2026-10-15T02:47:32.214564074+00:00Ideogram-v2a
Like Ideogram v2, but faster and cheaper
available · 2026-10-15T02:47:32.214570102+00:00Ideogram-v2a-turbo
Like Ideogram v2 turbo, but now faster and cheaper
available · 2026-10-15T02:47:32.214575582+00:00Ideogram-v3-balanced
Balance speed, quality and cost. Ideogram v3 creates images with stunning realism, creative designs, and consistent styles
available · 2026-10-15T02:47:32.214581810+00:00Ideogram-v3-quality
The highest quality Ideogram v3 model. v3 creates images with stunning realism, creative designs, and consistent styles
available · 2026-10-15T02:47:32.214587738+00:00Ideogram-v3-turbo
Turbo is the fastest and cheapest Ideogram v3. v3 creates images with stunning realism, creative designs, and consistent styles
available · 2026-10-15T02:47:32.214593592+00:00Image-01
MiniMax image-01 native text-to-image and image-to-image model
available · 2026-10-15T02:47:32.214599089+00:00Image-3.2
Commercial-ready, trained entirely on licensed data, text-to-image model. With only 4B parameters provides exceptional aesthetics and text rendering. Evaluated to be on par to other leading models in the market
available · 2026-10-15T02:47:32.214621835+00:00Imagen-3
Google's highest quality text-to-image model, capable of generating images with detail, rich lighting and beauty
available · 2026-10-15T02:47:32.214628420+00:00Imagen-3-fast
A faster and cheaper Imagen 3 model, for when price or speed are more important than final image quality
available · 2026-10-15T02:47:32.214634355+00:00Imagen-4
Google's Imagen 4 flagship model
available · 2026-10-15T02:47:32.214640259+00:00Imagen-4-fast
Use this fast version of Imagen 4 when speed and cost are more important than quality
available · 2026-10-15T02:47:32.214645233+00:00Kimi-k2-thinking
Kimi K2 Thinking is the latest, most capable version of an open-source thinking model.
available · 2026-10-15T02:47:32.214649456+00:00Kimi-k2.5
kimi-k2.5 是 Kimi 迄今最全能的模型，原生的多模态架构设计，同时支持视觉与文本输入、思考与非思考模式、对话与 Agent 任务
available · 2026-10-15T02:47:32.214653854+00:00Llama-2-7b-chat
A 7 billion parameter language model from Meta, fine tuned for chat completions
available · 2026-10-15T02:47:32.214659214+00:00Llama-4-maverick-instruct
A 17 billion parameter model with 128 experts
available · 2026-10-15T02:47:32.214664147+00:00Llama-4-scout-instruct
A 17 billion parameter model with 16 experts
available · 2026-10-15T02:47:32.214669563+00:00Lucid-origin
Artistic and high-quality visuals with improved prompt adherence, diversity, and definition
available · 2026-10-15T02:47:32.214674710+00:00Lyria-2
Lyria 2 is a music generation model that produces 48kHz stereo audio through text-based prompts
available · 2026-10-15T02:47:32.214680314+00:00Lyria-3
Generate 30-second music clips from text prompts or images with Lyria 3, Google's music generation model
available · 2026-10-15T02:47:32.214685923+00:00Meta-llama-3-70b-instruct
A 70 billion parameter language model from Meta, fine tuned for chat completions
available · 2026-10-15T02:47:32.214691485+00:00Meta-llama-3-8b-instruct
An 8 billion parameter language model from Meta, fine tuned for chat completions
available · 2026-10-15T02:47:32.214697211+00:00Minilm-embedding-int4
由 InferLink 可信共享算力网络提供的轻量向量模型
available · 2026-10-15T02:47:32.214702852+00:00Minimax-h3
MiniMax H3 native multimodal video generation model
available · 2026-10-15T02:47:32.214708072+00:00Minimax-m1
MiniMax-M1 是一款专为长上下文和高效率推理设计的大规模、开放权重推理模型。它利用混合专家模型（MoE）架构结合自定义的“闪电注意力”机制，使其能够处理长序列——最多达 100 万 token——同时保持具有竞争力的 FLOP 效率。该版本拥有 4560 亿总参数，每个 token 激活 459 亿参数，专为复杂的多步推理任务进行了优化。
available · 2026-10-15T02:47:32.214713041+00:00Minimax-m2
MiniMax M2 text model
available · 2026-10-15T02:47:32.214717233+00:00Minimax-m2.1
MiniMax M2.1 text model
available · 2026-10-15T02:47:32.214722189+00:00Minimax-m2.1-highspeed
MiniMax M2.1 highspeed text model
available · 2026-10-15T02:47:32.214726887+00:00Minimax-m2.5
MiniMax M2.5 text model
available · 2026-10-15T02:47:32.214731756+00:00Minimax-m2.5-highspeed
MiniMax M2.5 highspeed text model
available · 2026-10-15T02:47:32.214736382+00:00Minimax-m2.7
MiniMax M2.7 text model
available · 2026-10-15T02:47:32.214742093+00:00Minimax-m2.7-highspeed
MiniMax M2.7 highspeed text model
available · 2026-10-15T02:47:32.214746402+00:00Minimax-m3
MiniMax M3 coding and agent model
available · 2026-10-15T02:47:32.214751387+00:00Minimax-m3
MiniMax M3 native supplier isolated validation alias
available · 2026-10-15T02:47:32.214757852+00:00Nano-banana
Google's latest image editing model in Gemini 2.5
available · 2026-10-15T02:47:32.214763101+00:00Nano-banana-pro
Google's state of the art image generation and editing model 🍌🍌
available · 2026-10-15T02:47:32.214768463+00:00O1
OpenAI's first o-series reasoning model
available · 2026-10-15T02:47:32.214774906+00:00O4-mini
OpenAI's fast, lightweight reasoning model
available · 2026-10-15T02:47:32.214780459+00:00P-image
A sub 1 second text-to-image model built for production use cases.
available · 2026-10-15T02:47:32.214785228+00:00Phoenix-1.0
Leonardo AI’s first foundational model produces images up to 5 megapixels (fast, quality and ultra modes)
available · 2026-10-15T02:47:32.214790773+00:00Photon
High-quality image generation model optimized for creative professional workflows and ultra-high fidelity outputs
available · 2026-10-15T02:47:32.214797881+00:00Photon-flash
Accelerated variant of Photon prioritizing speed while maintaining quality
available · 2026-10-15T02:47:32.214804392+00:00Qvq-plus
QVQ multimodal reasoning model by Alibaba
available · 2026-10-15T02:47:32.214809800+00:00Qwen-coder-plus
Qwen code-specialized model by Alibaba
available · 2026-10-15T02:47:32.214813705+00:00Qwen-coder-turbo
Qwen code-specialized model by Alibaba
available · 2026-10-15T02:47:32.214817597+00:00Qwen-coder-turbo-0919
Qwen code-specialized model by Alibaba
available · 2026-10-15T02:47:32.214821275+00:00Qwen-coder-turbo-latest
Qwen code-specialized model by Alibaba
available · 2026-10-15T02:47:32.214825623+00:00Qwen-flash
Aliyun · Text 2 — auto-staged by test_pipeline
available · 2026-10-15T02:47:32.214829477+00:00Qwen-image
A 20B MMDiT model for next-gen text-to-image generation
available · 2026-10-15T02:47:32.214833937+00:00Qwen-image-2
A next-generation image generation and editing model from Alibaba's Qwen team. Supports text-to-image and image editing with strong text rendering, especially for Chinese.
available · 2026-10-15T02:47:32.214838165+00:00Qwen-image-2-pro
The pro version of Qwen Image 2 from Alibaba's Qwen team. Enhanced text rendering, realism, and semantic adherence for high-quality image generation and editing.
available · 2026-10-15T02:47:32.214842051+00:00Qwen-image-2.0
Aliyun Qwen Image 2.0 native image generation
available · 2026-10-15T02:47:32.214845740+00:00Qwen-image-2.0-pro
qwen-image-2.0-pro language model by Alibaba DashScope
available · 2026-10-15T02:47:32.214849624+00:00Qwen-image-2512
Qwen Image 2512 is an improved version of Qwen Image with more realistic human generation, finer textures, and stronger text rendering
available · 2026-10-15T02:47:32.214853734+00:00Qwen-image-max
Qwen Max — Alibaba's flagship large language model
available · 2026-10-15T02:47:32.214857876+00:00Qwen-long
Qwen Long — Alibaba's long-context language model
available · 2026-10-15T02:47:32.214861461+00:00Qwen-math-plus
Qwen Plus — Alibaba's powerful mid-tier language model
available · 2026-10-15T02:47:32.214865193+00:00Qwen-math-plus-0919
Qwen Plus — Alibaba's powerful mid-tier language model
available · 2026-10-15T02:47:32.214868663+00:00Qwen-math-plus-latest
Qwen Plus — Alibaba's powerful mid-tier language model
available · 2026-10-15T02:47:32.214872842+00:00Qwen-math-turbo
Qwen Turbo — Alibaba's fast cost-efficient language model
available · 2026-10-15T02:47:32.214876875+00:00Qwen-math-turbo-0919
Qwen Turbo — Alibaba's fast cost-efficient language model
available · 2026-10-15T02:47:32.214880819+00:00Qwen-math-turbo-latest
Qwen Turbo — Alibaba's fast cost-efficient language model
available · 2026-10-15T02:47:32.214885024+00:00Qwen-max
Qwen Max
available · 2026-10-15T02:47:32.214889354+00:00Qwen-max-0107
Qwen Max — Alibaba's flagship large language model
available · 2026-10-15T02:47:32.214892956+00:00Qwen-max-0428
Qwen Max — Alibaba's flagship large language model
available · 2026-10-15T02:47:32.214896763+00:00Qwen-max-0919
Qwen Max — Alibaba's flagship large language model
available · 2026-10-15T02:47:32.214900470+00:00Qwen-max-1201
Qwen Max — Alibaba's flagship large language model
available · 2026-10-15T02:47:32.214904168+00:00Qwen-mt-turbo
Qwen Turbo — Alibaba's fast cost-efficient language model
available · 2026-10-15T02:47:32.214908212+00:00Qwen-omni-turbo
Aliyun · Audio 1 (Omni) — auto-staged by test_pipeline
available · 2026-10-15T02:47:32.214911721+00:00Qwen-plus
Aliyun · Text 1 — auto-staged by test_pipeline
available · 2026-10-15T02:47:32.214916293+00:00Qwen-plus-latest
Qwen Plus — Alibaba's powerful mid-tier language model
available · 2026-10-15T02:47:32.214920077+00:00Qwen-turbo
Qwen Turbo
available · 2026-10-15T02:47:32.214923330+00:00Qwen-turbo-0919
Qwen Turbo — Alibaba's fast cost-efficient language model
available · 2026-10-15T02:47:32.214927206+00:00Qwen-turbo-latest
Qwen Turbo — Alibaba's fast cost-efficient language model
available · 2026-10-15T02:47:32.214930870+00:00Qwen-vl-max
Aliyun · Vision 1 — auto-staged by test_pipeline
available · 2026-10-15T02:47:32.214948061+00:00Qwen-vl-max-latest
Qwen vision-language model by Alibaba
available · 2026-10-15T02:47:32.214952382+00:00Qwen-vl-ocr
Qwen vision-language model by Alibaba
available · 2026-10-15T02:47:32.214956186+00:00Qwen-vl-ocr-latest
Qwen vision-language model by Alibaba
available · 2026-10-15T02:47:32.214959917+00:00Qwen-vl-plus
Qwen vision-language model by Alibaba
available · 2026-10-15T02:47:32.214963818+00:00Qwen-vl-plus-latest
Qwen vision-language model by Alibaba
available · 2026-10-15T02:47:32.214967769+00:00Qwen1.5-110b-chat
qwen1.5-110b-chat language model by Alibaba DashScope
available · 2026-10-15T02:47:32.214972049+00:00Qwen1.5-32b-chat
qwen1.5-32b-chat language model by Alibaba DashScope
available · 2026-10-15T02:47:32.214975881+00:00Qwen2-57b-a14b-instruct
qwen2-57b-a14b-instruct language model by Alibaba DashScope
available · 2026-10-15T02:47:32.214979620+00:00Qwen2-7b-instruct
qwen2-7b-instruct language model by Alibaba DashScope
available · 2026-10-15T02:47:32.214983313+00:00Qwen2.5-14b-instruct
qwen2.5-14b-instruct language model by Alibaba DashScope
available · 2026-10-15T02:47:32.214987376+00:00Qwen2.5-32b-instruct
qwen2.5-32b-instruct language model by Alibaba DashScope
available · 2026-10-15T02:47:32.214991279+00:00Qwen2.5-72b-instruct
qwen2.5-72b-instruct language model by Alibaba DashScope
available · 2026-10-15T02:47:32.214994802+00:00Qwen2.5-7b-instruct
qwen2.5-7b-instruct language model by Alibaba DashScope
available · 2026-10-15T02:47:32.214998767+00:00Qwen2.5-coder-14b-instruct
Qwen code-specialized model by Alibaba
available · 2026-10-15T02:47:32.215002856+00:00Qwen2.5-coder-32b-instruct
Qwen code-specialized model by Alibaba
available · 2026-10-15T02:47:32.215006514+00:00Qwen2.5-coder-7b-instruct
Qwen code-specialized model by Alibaba
available · 2026-10-15T02:47:32.215010226+00:00Qwen2.5-math-7b-instruct
qwen2.5-math-7b-instruct language model by Alibaba DashScope
available · 2026-10-15T02:47:32.215014541+00:00Qwen2.5-vl-32b-instruct
Qwen vision-language model by Alibaba
available · 2026-10-15T02:47:32.215018229+00:00Qwen3-0.6b
InferLink local Qwen3-0.6B model
available · 2026-10-15T02:47:32.215022040+00:00Qwen3-14b
qwen3-14b language model by Alibaba DashScope
available · 2026-10-15T02:47:32.215025764+00:00Qwen3-235b-a22b
qwen3-235b-a22b language model by Alibaba DashScope
available · 2026-10-15T02:47:32.215029165+00:00Qwen3-235b-a22b-instruct-2507
qwen3-235b-a22b-instruct-2507 language model by Alibaba DashScope
available · 2026-10-15T02:47:32.215033507+00:00Qwen3-235b-a22b-instruct-2507
Updated Qwen3 model for instruction following
available · 2026-10-15T02:47:32.215037513+00:00Qwen3-235b-a22b-thinking-2507
qwen3-235b-a22b-thinking-2507 language model by Alibaba DashScope
available · 2026-10-15T02:47:32.215041822+00:00Qwen3-30b-a3b
qwen3-30b-a3b language model by Alibaba DashScope
available · 2026-10-15T02:47:32.215045988+00:00Qwen3-30b-a3b-instruct-2507
qwen3-30b-a3b-instruct-2507 language model by Alibaba DashScope
available · 2026-10-15T02:47:32.215050136+00:00Qwen3-30b-a3b-thinking-2507
qwen3-30b-a3b-thinking-2507 language model by Alibaba DashScope
available · 2026-10-15T02:47:32.215054218+00:00Qwen3-32b
qwen3-32b language model by Alibaba DashScope
available · 2026-10-15T02:47:32.215058340+00:00Qwen3-4b
qwen3-4b language model by Alibaba DashScope
available · 2026-10-15T02:47:32.215063041+00:00Qwen3-8b
qwen3-8b language model by Alibaba DashScope
available · 2026-10-15T02:47:32.215067346+00:00Qwen3-asr-flash
Aliyun Qwen3 ASR Flash sync STT
available · 2026-10-15T02:47:32.215071104+00:00Qwen3-asr-flash-filetrans
Aliyun Qwen3 ASR Flash Filetrans async STT
available · 2026-10-15T02:47:32.215074913+00:00Qwen3-coder-480b-a35b-instruct
Qwen code-specialized model by Alibaba
available · 2026-10-15T02:47:32.215078674+00:00Qwen3-coder-flash
Qwen code-specialized model by Alibaba
available · 2026-10-15T02:47:32.215082382+00:00Qwen3-coder-next
Qwen code-specialized model by Alibaba
available · 2026-10-15T02:47:32.215086499+00:00Qwen3-coder-plus
Qwen3 Coder Plus
available · 2026-10-15T02:47:32.215090398+00:00Qwen3-max-preview
Qwen Max — Alibaba's flagship large language model
available · 2026-10-15T02:47:32.215094523+00:00Qwen3-next-80b-a3b-instruct
qwen3-next-80b-a3b-instruct language model by Alibaba DashScope
available · 2026-10-15T02:47:32.215098350+00:00Qwen3-next-80b-a3b-thinking
qwen3-next-80b-a3b-thinking language model by Alibaba DashScope
available · 2026-10-15T02:47:32.215102130+00:00Qwen3-omni-flash
qwen3-omni-flash language model by Alibaba DashScope
available · 2026-10-15T02:47:32.215105895+00:00Qwen3-tts
{"zh":"Qwen3 TTS 统一语音合成，支持预置音色、声音克隆与声音设计三种模式，自动识别40+语言","en":"Qwen3 TTS: unified TTS with preset voices, voice cloning, and voice design modes; auto-detects 40+ languages","de":"Qwen3 TTS: einheitliche Sprachsynthese mit voreingestellten Stimmen, Stimmenklonen und Stimmdesign","fr":"Qwen3 TTS: synthèse vocale unifiée avec voix prédéfinies, clonage et conception vocale","ko":"Qwen3 TTS: 사전 설정 음성, 음성 복제, 음성 디자인 모드를 지원하는 통합 TTS"}
available · 2026-10-15T02:47:32.215110272+00:00Qwen3-vl-flash
Qwen vision-language model by Alibaba
available · 2026-10-15T02:47:32.215114714+00:00Qwen3-vl-plus
Qwen vision-language model by Alibaba
available · 2026-10-15T02:47:32.215118137+00:00Qwen3.5-122b-a10b
qwen3.5-122b-a10b language model by Alibaba DashScope
available · 2026-10-15T02:47:32.215121807+00:00Qwen3.5-397b-a17b
qwen3.5-397b-a17b language model by Alibaba DashScope
available · 2026-10-15T02:47:32.215125786+00:00Qwen3.5-omni-flash
qwen3.5-omni-flash language model by Alibaba DashScope
available · 2026-10-15T02:47:32.215129406+00:00Qwen3.5-omni-plus
Qwen Plus — Alibaba's powerful mid-tier language model
available · 2026-10-15T02:47:32.215133202+00:00Qwen3.6-plus
Qwen Plus — Alibaba's powerful mid-tier language model
available · 2026-10-15T02:47:32.215137136+00:00Qwq-plus
QwQ reasoning model by Alibaba
available · 2026-10-15T02:47:32.215142814+00:00Rd-fast
Fast pixel art image generation
available · 2026-10-15T02:47:32.215149015+00:00Rd-plus
High quality and authentic pixel art image generation
available · 2026-10-15T02:47:32.215154382+00:00Recraft-20b
Affordable and fast images
available · 2026-10-15T02:47:32.215159057+00:00Recraft-20b-svg
Affordable and fast vector images
available · 2026-10-15T02:47:32.215162300+00:00Seedream-3
A text-to-image model with support for native high-resolution (2K) image generation
available · 2026-10-15T02:47:32.215165808+00:00Seedream-4
Unified text-to-image generation and precise single-sentence editing at up to 4K resolution
available · 2026-10-15T02:47:32.215169129+00:00Seedream-5-lite
Seedream 5.0 lite: image generation with built-in reasoning, example-based editing, and deep domain knowledge
available · 2026-10-15T02:47:32.215172065+00:00Sora-2
OpenAI video generation model capable of creating realistic video content from text prompts, supporting various scenes and styles.
available · 2026-10-15T02:47:32.215176105+00:00Sora-2-hd
Sora 2 HD is OpenAI higher-resolution video generation model offering finer video quality, suitable for professional video production.
available · 2026-10-15T02:47:32.215178723+00:00Sora-2-pro
Sora 2 Pro is OpenAI highest-end video generation model offering maximum video quality, longest duration, and finest creative control for professional video production.
available · 2026-10-15T02:47:32.215181699+00:00Spark-x
Spark X
available · 2026-10-15T02:47:32.215188518+00:00Speech-2.8-turbo
{"zh":"MiniMax Speech 2.8 Turbo 高质量语音合成，支持40+语言、声音克隆与情感控制","en":"MiniMax Speech 2.8 Turbo: natural TTS with voice cloning, emotion control, and 40+ languages","de":"MiniMax Speech 2.8 Turbo: natürliche TTS mit Stimmklonen und Emotionssteuerung","fr":"MiniMax Speech 2.8 Turbo: synthèse vocale naturelle avec clonage et contrôle des émotions","ko":"MiniMax Speech 2.8 Turbo: 자연스러운 음성 합성, 40개 이상 언어 및 감정 제어 지원"}
available · 2026-10-15T02:47:32.215193138+00:00Stable-audio-2.5
Generate high-quality music and sound from text prompts
available · 2026-10-15T02:47:32.215197955+00:00Text-embedding-3-large
OpenAI 功能最强大的嵌入模型，适用于英语和非英语任务。嵌入是文本的数字表示，可用于衡量两段文本之间的相关性。嵌入对于搜索、聚类、推荐、异常检测和分类任务非常有用。
available · 2026-10-15T02:47:32.215202966+00:00Text-embedding-3-small
性能更优的 ada 嵌入模型版本。嵌入是文本的数值表示，可用于衡量两段文本之间的相关性。嵌入对于搜索、聚类、推荐、异常检测和分类任务非常有用
available · 2026-10-15T02:47:32.215207625+00:00Text-embedding-ada-002
改进的、性能更优的 ada 嵌入模型版本。嵌入是文本的数值表示，可用于衡量两段文本之间的相关性。嵌入对搜索、聚类、推荐、异常检测和分类任务非常有用。
available · 2026-10-15T02:47:32.215212391+00:00Veo-3.1-fast
Google Veo 3.1 Fast, quick video generation with faster rendering speed.
available · 2026-10-15T02:47:32.215217452+00:00Veo3.1
Google于2025年10月发布的Veo 3.1升级版本。改进提示词追随性和音视频质量，支持1分钟以上视频生成（Extend功能）、丰富音声生成、多种编辑功能（Ingredients to Video、Frames to Video、Insert）。2026年1月更新增加角色一致性、背景物体一致性、4K升频和原生竖屏输出。
available · 2026-10-15T02:47:32.215223990+00:00Veo_3_1
Google Veo 3.1 - high quality text-to-video generation model with superior output quality, billed per request.
available · 2026-10-15T02:47:32.215228822+00:00Veo_3_1-fast
Google Veo 3.1 Fast - text-to-video generation model with fast rendering speed, billed per request.
available · 2026-10-15T02:47:32.215231799+00:00Wan2.2-i2v-flash
Alibaba Wan 2.2 image-to-video via native DashScope API
available · 2026-10-15T02:47:32.215234573+00:00Wan2.2-t2v-plus
Alibaba Wan 2.2 text-to-video via native DashScope API
available · 2026-10-15T02:47:32.215237381+00:00Wan2.7-i2v-2026-04-25
Alibaba Wan 2.7 image-to-video model
available · 2026-10-15T02:47:32.215240084+00:00Wan2.7-r2v-2026-06-12
Alibaba Wan 2.7 reference-to-video model
available · 2026-10-15T02:47:32.215243573+00:00Wan2.7-t2v-2026-06-12
Alibaba Wan 2.7 text-to-video model
available · 2026-10-15T02:47:32.215247335+00:00Wan2.7-videoedit
Alibaba Wan 2.7 video editing model
available · 2026-10-15T02:47:32.215250219+00:00Whisper-1
Whisper is a general-purpose speech recognition model trained on a large and diverse audio dataset. It can also be used as a multitask model for multilingual speech recognition, speech translation, and language identification.
available · 2026-10-15T02:47:32.215253849+00:00