提供商
其模型收录在目录中的实验室、云平台和路由服务。所示价格为 OPTES 价格，并非对方价格。
OPTES
模型实验室
AI21 LabsThe Jamba family of long-context models.2 个模型AnthropicThe Claude family (Fable, Opus, Sonnet, Haiku) through the Claude API.4 个模型CohereCanadian lab focused on enterprise models; Aya Expanse is its multilingual line.1 个模型Core42 CompassG42's model platform in the UAE, home of the Arabic-first Seraj model.5 个模型Google AI StudioThe Gemini family through the Gemini API (Google AI Studio).6 个模型MetaMeta's Model API (public preview) with the Muse family; Llama models run on other providers.4 个模型Mistral AIFrench lab: Mistral Medium, Large and Small, Codestral, Ministral and embeddings.6 个模型OpenAIThe GPT-6 and GPT-5.x families through OpenAI's own API platform.4 个模型PerplexitySonar, a search-grounded model, plus selected third-party models through its Agent API.3 个模型Reka AIMultimodal models that read text, images, video and audio.3 个模型UpstageKorean lab: the Solar models and document AI.3 个模型WriterEnterprise lab behind the Palmyra models with 1M-token context.3 个模型xAIThe Grok family, including Grok Build for code and Grok Imagine for images.4 个模型
中国实验室（国际站）
Alibaba Cloud Model StudioThe Qwen family through Alibaba Cloud's international Model Studio.3 个模型BytePlus ModelArkByteDance's international platform: the Seed models and hosted DeepSeek and GLM.3 个模型DeepSeekDeepSeek's own platform: V4 Pro and V4.1 Flash, with 1M context and a 50% off-peak discount.2 个模型MiniMaxMiniMax's international platform: the M-series text models with 1M context.2 个模型Moonshot AIThe Kimi models through Moonshot's international platform.4 个模型StepFunStepFun's international platform: Step 5 and the fast Step 3.x Flash models.3 个模型Tencent Cloud TokenHubTencent's international hub: the Hy models plus Kimi, GLM, DeepSeek and MiniMax.3 个模型Xiaomi MiMoXiaomi's MiMo models, priced low outside China.2 个模型Z.aiThe GLM family through Z.ai's international platform.5 个模型
云平台
Amazon BedrockAWS's model service: Claude, GPT-6 Astra, Amazon Nova, Llama, Mistral, DeepSeek, Kimi and Grok.13 个模型Google Cloud Vertex AIGoogle Cloud's model platform: Gemini plus Claude, Llama and Mistral on one bill.7 个模型IBM watsonx.aiIBM's model platform: Granite plus Llama, Mistral and gpt-oss.5 个模型Microsoft Azure AI FoundryMicrosoft's model platform: OpenAI models plus DeepSeek, Grok, Kimi, Llama and Mistral.11 个模型Oracle OCI Generative AIOracle Cloud's model service, with regions in Dubai, Abu Dhabi and Riyadh.5 个模型
推理服务商
AkashMLOpen models on the decentralised Akash GPU network.7 个模型BasetenAmong the fastest providers for gpt-oss-120b and Kimi K3, with near-lowest prices.8 个模型CerebrasThe fastest published speeds in the research: about 3,000 tokens a second on gpt-oss-120b.2 个模型ChutesDecentralised inference where every model runs inside a trusted execution environment (TEE).9 个模型Cloudflare Workers AIModels served on Cloudflare's network, priced per 1M tokens from its Neuron units.13 个模型CoreWeaveGPU cloud with serverless inference (formerly W&B Inference) and a very recent catalog.14 个模型CrusoeManaged inference with low cached-input prices: DeepSeek, Kimi, GLM, gpt-oss and Nemotron.9 个模型DeepInfraAmong the lowest prices for gpt-oss, GLM-5.3, DeepSeek V4 Flash and MiniMax M3.15 个模型falA marketplace of image, video and audio generation models.3 个模型FeatherlessMore than 4,000 open models and fine-tunes from Hugging Face behind one API.12 个模型Fireworks AIFast serverless inference with Standard and Fast tiers for the big open models.7 个模型FriendliAIFast inference engine; a focused serverless list around GLM-5.x, DeepSeek and MiniMax.8 个模型GMI CloudGPU cloud with an inference engine for DeepSeek, Kimi, GLM, Qwen and MiniMax.11 个模型GroqVery fast inference on its own LPU chips; a small public catalog.6 个模型inference.netInference platform with open models and its own Schematron extraction models.10 个模型io.netDecentralised GPU network with IO Intelligence, an API for open models.12 个模型ModalServerless GPU platform with a shared per-token API for Kimi K3, GLM-5.3 and more.4 个模型Nebius Token FactoryEuropean inference cloud that publishes a measured speed for every model.14 个模型Novita AIA broad catalog of 120 open models for text, images, video and audio.17 个模型NscaleBritish AI cloud with serverless endpoints for gpt-oss, Llama and Qwen.7 个模型OVHcloud AI EndpointsEuropean serverless endpoints for gpt-oss, Llama 3.3 and Qwen.6 个模型ParasailDay-zero support for big open models and some of the lowest DeepSeek and gpt-oss prices.17 个模型ReplicateA large catalog of image, video and audio models; a few language models.2 个模型RunpodGPU cloud with public endpoints for Kimi models, including Kimi K3 with 1M context.4 个模型SambaNovaInference on SambaNova's own chips: DeepSeek, Llama, gpt-oss, MiniMax and Gemma.7 个模型SiliconFlowInternational platform with some of the lowest prices for DeepSeek V4.1 Flash and gpt-oss.14 个模型Together AIOne of the widest catalogs of open-weights models: DeepSeek, Kimi, GLM, Qwen, Llama and more.12 个模型
路由与网关
302.AIA gateway to Western and Chinese models plus image, video and audio generation.1 个模型AIHubMixA gateway to text, image, video and audio models from the big labs.4 个模型Eden AIOne API over 500+ models, including specialised expert models.3 个模型Hugging Face Inference ProvidersHugging Face's router over partner providers, at the partners' prices.10 个模型OpenRouterA router over 500+ models from 80+ providers.3 个模型RequestyA router over 600+ models from 20+ providers.3 个模型TokenGOSelf-operated open models: DeepSeek, Kimi, GLM, Qwen and MiniMax.4 个模型