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