ارائه‌دهندگان
آزمایشگاه‌ها، ابرها و مسیریاب‌هایی که مدل‌هایشان در کاتالوگ است. قیمت‌های نشان‌داده‌شده قیمت OPTES است، نه آن‌ها.
OPTES
آزمایشگاه‌های مدل
AI21 LabsThe Jamba family of long-context models.2 مدلAnthropicThe Claude family (Fable, Opus, Sonnet, Haiku) through the Claude API.4 مدلCohereCanadian lab focused on enterprise models; Aya Expanse is its multilingual line.1 مدلCore42 CompassG42's model platform in the UAE, home of the Arabic-first Seraj model.5 مدلGoogle AI StudioThe Gemini family through the Gemini API (Google AI Studio).6 مدلMetaMeta's Model API (public preview) with the Muse family; Llama models run on other providers.4 مدلMistral AIFrench lab: Mistral Medium, Large and Small, Codestral, Ministral and embeddings.6 مدلOpenAIThe GPT-6 and GPT-5.x families through OpenAI's own API platform.4 مدلPerplexitySonar, a search-grounded model, plus selected third-party models through its Agent API.3 مدلReka AIMultimodal models that read text, images, video and audio.3 مدلUpstageKorean lab: the Solar models and document AI.3 مدلWriterEnterprise lab behind the Palmyra models with 1M-token context.3 مدلxAIThe Grok family, including Grok Build for code and Grok Imagine for images.4 مدل
آزمایشگاه‌های چینی، درگاه‌های بین‌المللی
Alibaba Cloud Model StudioThe Qwen family through Alibaba Cloud's international Model Studio.3 مدلBytePlus ModelArkByteDance's international platform: the Seed models and hosted DeepSeek and GLM.3 مدلDeepSeekDeepSeek's own platform: V4 Pro and V4.1 Flash, with 1M context and a 50% off-peak discount.2 مدلMiniMaxMiniMax's international platform: the M-series text models with 1M context.2 مدلMoonshot AIThe Kimi models through Moonshot's international platform.4 مدلStepFunStepFun's international platform: Step 5 and the fast Step 3.x Flash models.3 مدلTencent Cloud TokenHubTencent's international hub: the Hy models plus Kimi, GLM, DeepSeek and MiniMax.3 مدلXiaomi MiMoXiaomi's MiMo models, priced low outside China.2 مدلZ.aiThe GLM family through Z.ai's international platform.5 مدل
سکوهای ابری
Amazon BedrockAWS's model service: Claude, GPT-6 Astra, Amazon Nova, Llama, Mistral, DeepSeek, Kimi and Grok.13 مدلGoogle Cloud Vertex AIGoogle Cloud's model platform: Gemini plus Claude, Llama and Mistral on one bill.7 مدلIBM watsonx.aiIBM's model platform: Granite plus Llama, Mistral and gpt-oss.5 مدلMicrosoft Azure AI FoundryMicrosoft's model platform: OpenAI models plus DeepSeek, Grok, Kimi, Llama and Mistral.11 مدلOracle OCI Generative AIOracle Cloud's model service, with regions in Dubai, Abu Dhabi and Riyadh.5 مدل
ارائه‌دهندگان استنتاج
AkashMLOpen models on the decentralised Akash GPU network.7 مدلBasetenAmong the fastest providers for gpt-oss-120b and Kimi K3, with near-lowest prices.8 مدلCerebrasThe fastest published speeds in the research: about 3,000 tokens a second on gpt-oss-120b.2 مدلChutesDecentralised inference where every model runs inside a trusted execution environment (TEE).9 مدلCloudflare Workers AIModels served on Cloudflare's network, priced per 1M tokens from its Neuron units.13 مدلCoreWeaveGPU cloud with serverless inference (formerly W&B Inference) and a very recent catalog.14 مدلCrusoeManaged inference with low cached-input prices: DeepSeek, Kimi, GLM, gpt-oss and Nemotron.9 مدلDeepInfraAmong the lowest prices for gpt-oss, GLM-5.3, DeepSeek V4 Flash and MiniMax M3.15 مدلfalA marketplace of image, video and audio generation models.3 مدلFeatherlessMore than 4,000 open models and fine-tunes from Hugging Face behind one API.12 مدلFireworks AIFast serverless inference with Standard and Fast tiers for the big open models.7 مدلFriendliAIFast inference engine; a focused serverless list around GLM-5.x, DeepSeek and MiniMax.8 مدلGMI CloudGPU cloud with an inference engine for DeepSeek, Kimi, GLM, Qwen and MiniMax.11 مدلGroqVery fast inference on its own LPU chips; a small public catalog.6 مدلinference.netInference platform with open models and its own Schematron extraction models.10 مدلio.netDecentralised GPU network with IO Intelligence, an API for open models.12 مدلModalServerless GPU platform with a shared per-token API for Kimi K3, GLM-5.3 and more.4 مدلNebius Token FactoryEuropean inference cloud that publishes a measured speed for every model.14 مدلNovita AIA broad catalog of 120 open models for text, images, video and audio.17 مدلNscaleBritish AI cloud with serverless endpoints for gpt-oss, Llama and Qwen.7 مدلOVHcloud AI EndpointsEuropean serverless endpoints for gpt-oss, Llama 3.3 and Qwen.6 مدلParasailDay-zero support for big open models and some of the lowest DeepSeek and gpt-oss prices.17 مدلReplicateA large catalog of image, video and audio models; a few language models.2 مدلRunpodGPU cloud with public endpoints for Kimi models, including Kimi K3 with 1M context.4 مدلSambaNovaInference on SambaNova's own chips: DeepSeek, Llama, gpt-oss, MiniMax and Gemma.7 مدلSiliconFlowInternational platform with some of the lowest prices for DeepSeek V4.1 Flash and gpt-oss.14 مدلTogether AIOne of the widest catalogs of open-weights models: DeepSeek, Kimi, GLM, Qwen, Llama and more.12 مدل
مسیریاب‌ها و درگاه‌ها
302.AIA gateway to Western and Chinese models plus image, video and audio generation.1 مدلAIHubMixA gateway to text, image, video and audio models from the big labs.4 مدلEden AIOne API over 500+ models, including specialised expert models.3 مدلHugging Face Inference ProvidersHugging Face's router over partner providers, at the partners' prices.10 مدلOpenRouterA router over 500+ models from 80+ providers.3 مدلRequestyA router over 600+ models from 20+ providers.3 مدلTokenGOSelf-operated open models: DeepSeek, Kimi, GLM, Qwen and MiniMax.4 مدل