Provedores

Os laboratórios, nuvens e roteadores cujos modelos estão no catálogo. Os preços mostrados são da OPTES, não deles.

OPTES

OPTESOPTES's own model family: text, code, vision, images, video, voice, music and search under one key.12 modelos

Laboratórios de modelos

AI21 LabsThe Jamba family of long-context models.2 modelos AnthropicThe Claude family (Fable, Opus, Sonnet, Haiku) through the Claude API.4 modelos CohereCanadian lab focused on enterprise models; Aya Expanse is its multilingual line.1 modelos Core42 CompassG42's model platform in the UAE, home of the Arabic-first Seraj model.5 modelos Google AI StudioThe Gemini family through the Gemini API (Google AI Studio).6 modelos MetaMeta's Model API (public preview) with the Muse family; Llama models run on other providers.4 modelos Mistral AIFrench lab: Mistral Medium, Large and Small, Codestral, Ministral and embeddings.6 modelos OpenAIThe GPT-6 and GPT-5.x families through OpenAI's own API platform.4 modelos PerplexitySonar, a search-grounded model, plus selected third-party models through its Agent API.3 modelos Reka AIMultimodal models that read text, images, video and audio.3 modelos UpstageKorean lab: the Solar models and document AI.3 modelos WriterEnterprise lab behind the Palmyra models with 1M-token context.3 modelos xAIThe Grok family, including Grok Build for code and Grok Imagine for images.4 modelos

Laboratórios chineses, plataformas internacionais

Alibaba Cloud Model StudioThe Qwen family through Alibaba Cloud's international Model Studio.3 modelos BytePlus ModelArkByteDance's international platform: the Seed models and hosted DeepSeek and GLM.3 modelos DeepSeekDeepSeek's own platform: V4 Pro and V4.1 Flash, with 1M context and a 50% off-peak discount.2 modelos MiniMaxMiniMax's international platform: the M-series text models with 1M context.2 modelos Moonshot AIThe Kimi models through Moonshot's international platform.4 modelos StepFunStepFun's international platform: Step 5 and the fast Step 3.x Flash models.3 modelos Tencent Cloud TokenHubTencent's international hub: the Hy models plus Kimi, GLM, DeepSeek and MiniMax.3 modelos Xiaomi MiMoXiaomi's MiMo models, priced low outside China.2 modelos Z.aiThe GLM family through Z.ai's international platform.5 modelos

Plataformas de nuvem

Amazon BedrockAWS's model service: Claude, GPT-6 Astra, Amazon Nova, Llama, Mistral, DeepSeek, Kimi and Grok.13 modelos Google Cloud Vertex AIGoogle Cloud's model platform: Gemini plus Claude, Llama and Mistral on one bill.7 modelos IBM watsonx.aiIBM's model platform: Granite plus Llama, Mistral and gpt-oss.5 modelos Microsoft Azure AI FoundryMicrosoft's model platform: OpenAI models plus DeepSeek, Grok, Kimi, Llama and Mistral.11 modelos Oracle OCI Generative AIOracle Cloud's model service, with regions in Dubai, Abu Dhabi and Riyadh.5 modelos

Provedores de inferência

AkashMLOpen models on the decentralised Akash GPU network.7 modelos BasetenAmong the fastest providers for gpt-oss-120b and Kimi K3, with near-lowest prices.8 modelos CerebrasThe fastest published speeds in the research: about 3,000 tokens a second on gpt-oss-120b.2 modelos ChutesDecentralised inference where every model runs inside a trusted execution environment (TEE).9 modelos Cloudflare Workers AIModels served on Cloudflare's network, priced per 1M tokens from its Neuron units.13 modelos CoreWeaveGPU cloud with serverless inference (formerly W&B Inference) and a very recent catalog.14 modelos CrusoeManaged inference with low cached-input prices: DeepSeek, Kimi, GLM, gpt-oss and Nemotron.9 modelos DeepInfraAmong the lowest prices for gpt-oss, GLM-5.3, DeepSeek V4 Flash and MiniMax M3.15 modelos falA marketplace of image, video and audio generation models.3 modelos FeatherlessMore than 4,000 open models and fine-tunes from Hugging Face behind one API.12 modelos Fireworks AIFast serverless inference with Standard and Fast tiers for the big open models.7 modelos FriendliAIFast inference engine; a focused serverless list around GLM-5.x, DeepSeek and MiniMax.8 modelos GMI CloudGPU cloud with an inference engine for DeepSeek, Kimi, GLM, Qwen and MiniMax.11 modelos GroqVery fast inference on its own LPU chips; a small public catalog.6 modelos inference.netInference platform with open models and its own Schematron extraction models.10 modelos io.netDecentralised GPU network with IO Intelligence, an API for open models.12 modelos ModalServerless GPU platform with a shared per-token API for Kimi K3, GLM-5.3 and more.4 modelos Nebius Token FactoryEuropean inference cloud that publishes a measured speed for every model.14 modelos Novita AIA broad catalog of 120 open models for text, images, video and audio.17 modelos NscaleBritish AI cloud with serverless endpoints for gpt-oss, Llama and Qwen.7 modelos OVHcloud AI EndpointsEuropean serverless endpoints for gpt-oss, Llama 3.3 and Qwen.6 modelos ParasailDay-zero support for big open models and some of the lowest DeepSeek and gpt-oss prices.17 modelos ReplicateA large catalog of image, video and audio models; a few language models.2 modelos RunpodGPU cloud with public endpoints for Kimi models, including Kimi K3 with 1M context.4 modelos SambaNovaInference on SambaNova's own chips: DeepSeek, Llama, gpt-oss, MiniMax and Gemma.7 modelos SiliconFlowInternational platform with some of the lowest prices for DeepSeek V4.1 Flash and gpt-oss.14 modelos Together AIOne of the widest catalogs of open-weights models: DeepSeek, Kimi, GLM, Qwen, Llama and more.12 modelos

Roteadores e gateways

302.AIA gateway to Western and Chinese models plus image, video and audio generation.1 modelos AIHubMixA gateway to text, image, video and audio models from the big labs.4 modelos Eden AIOne API over 500+ models, including specialised expert models.3 modelos Hugging Face Inference ProvidersHugging Face's router over partner providers, at the partners' prices.10 modelos OpenRouterA router over 500+ models from 80+ providers.3 modelos RequestyA router over 600+ models from 20+ providers.3 modelos TokenGOSelf-operated open models: DeepSeek, Kimi, GLM, Qwen and MiniMax.4 modelos