Providers
The labs, clouds and routers whose models are in the catalog. The prices shown are OPTES prices, not theirs.
OPTES
Model labs
AI21 LabsThe Jamba family of long-context models.2 modelsAnthropicThe Claude family (Fable, Opus, Sonnet, Haiku) through the Claude API.4 modelsCohereCanadian lab focused on enterprise models; Aya Expanse is its multilingual line.1 modelsCore42 CompassG42's model platform in the UAE, home of the Arabic-first Seraj model.5 modelsGoogle AI StudioThe Gemini family through the Gemini API (Google AI Studio).6 modelsMetaMeta's Model API (public preview) with the Muse family; Llama models run on other providers.4 modelsMistral AIFrench lab: Mistral Medium, Large and Small, Codestral, Ministral and embeddings.6 modelsOpenAIThe GPT-6 and GPT-5.x families through OpenAI's own API platform.4 modelsPerplexitySonar, a search-grounded model, plus selected third-party models through its Agent API.3 modelsReka AIMultimodal models that read text, images, video and audio.3 modelsUpstageKorean lab: the Solar models and document AI.3 modelsWriterEnterprise lab behind the Palmyra models with 1M-token context.3 modelsxAIThe Grok family, including Grok Build for code and Grok Imagine for images.4 models
Chinese labs, international platforms
Alibaba Cloud Model StudioThe Qwen family through Alibaba Cloud's international Model Studio.3 modelsBytePlus ModelArkByteDance's international platform: the Seed models and hosted DeepSeek and GLM.3 modelsDeepSeekDeepSeek's own platform: V4 Pro and V4.1 Flash, with 1M context and a 50% off-peak discount.2 modelsMiniMaxMiniMax's international platform: the M-series text models with 1M context.2 modelsMoonshot AIThe Kimi models through Moonshot's international platform.4 modelsStepFunStepFun's international platform: Step 5 and the fast Step 3.x Flash models.3 modelsTencent Cloud TokenHubTencent's international hub: the Hy models plus Kimi, GLM, DeepSeek and MiniMax.3 modelsXiaomi MiMoXiaomi's MiMo models, priced low outside China.2 modelsZ.aiThe GLM family through Z.ai's international platform.5 models
Cloud platforms
Amazon BedrockAWS's model service: Claude, GPT-6 Astra, Amazon Nova, Llama, Mistral, DeepSeek, Kimi and Grok.13 modelsGoogle Cloud Vertex AIGoogle Cloud's model platform: Gemini plus Claude, Llama and Mistral on one bill.7 modelsIBM watsonx.aiIBM's model platform: Granite plus Llama, Mistral and gpt-oss.5 modelsMicrosoft Azure AI FoundryMicrosoft's model platform: OpenAI models plus DeepSeek, Grok, Kimi, Llama and Mistral.11 modelsOracle OCI Generative AIOracle Cloud's model service, with regions in Dubai, Abu Dhabi and Riyadh.5 models
Inference providers
AkashMLOpen models on the decentralised Akash GPU network.7 modelsBasetenAmong the fastest providers for gpt-oss-120b and Kimi K3, with near-lowest prices.8 modelsCerebrasThe fastest published speeds in the research: about 3,000 tokens a second on gpt-oss-120b.2 modelsChutesDecentralised inference where every model runs inside a trusted execution environment (TEE).9 modelsCloudflare Workers AIModels served on Cloudflare's network, priced per 1M tokens from its Neuron units.13 modelsCoreWeaveGPU cloud with serverless inference (formerly W&B Inference) and a very recent catalog.14 modelsCrusoeManaged inference with low cached-input prices: DeepSeek, Kimi, GLM, gpt-oss and Nemotron.9 modelsDeepInfraAmong the lowest prices for gpt-oss, GLM-5.3, DeepSeek V4 Flash and MiniMax M3.15 modelsfalA marketplace of image, video and audio generation models.3 modelsFeatherlessMore than 4,000 open models and fine-tunes from Hugging Face behind one API.12 modelsFireworks AIFast serverless inference with Standard and Fast tiers for the big open models.7 modelsFriendliAIFast inference engine; a focused serverless list around GLM-5.x, DeepSeek and MiniMax.8 modelsGMI CloudGPU cloud with an inference engine for DeepSeek, Kimi, GLM, Qwen and MiniMax.11 modelsGroqVery fast inference on its own LPU chips; a small public catalog.6 modelsinference.netInference platform with open models and its own Schematron extraction models.10 modelsio.netDecentralised GPU network with IO Intelligence, an API for open models.12 modelsModalServerless GPU platform with a shared per-token API for Kimi K3, GLM-5.3 and more.4 modelsNebius Token FactoryEuropean inference cloud that publishes a measured speed for every model.14 modelsNovita AIA broad catalog of 120 open models for text, images, video and audio.17 modelsNscaleBritish AI cloud with serverless endpoints for gpt-oss, Llama and Qwen.7 modelsOVHcloud AI EndpointsEuropean serverless endpoints for gpt-oss, Llama 3.3 and Qwen.6 modelsParasailDay-zero support for big open models and some of the lowest DeepSeek and gpt-oss prices.17 modelsReplicateA large catalog of image, video and audio models; a few language models.2 modelsRunpodGPU cloud with public endpoints for Kimi models, including Kimi K3 with 1M context.4 modelsSambaNovaInference on SambaNova's own chips: DeepSeek, Llama, gpt-oss, MiniMax and Gemma.7 modelsSiliconFlowInternational platform with some of the lowest prices for DeepSeek V4.1 Flash and gpt-oss.14 modelsTogether AIOne of the widest catalogs of open-weights models: DeepSeek, Kimi, GLM, Qwen, Llama and more.12 models
Routers and gateways
302.AIA gateway to Western and Chinese models plus image, video and audio generation.1 modelsAIHubMixA gateway to text, image, video and audio models from the big labs.4 modelsEden AIOne API over 500+ models, including specialised expert models.3 modelsHugging Face Inference ProvidersHugging Face's router over partner providers, at the partners' prices.10 modelsOpenRouterA router over 500+ models from 80+ providers.3 modelsRequestyA router over 600+ models from 20+ providers.3 modelsTokenGOSelf-operated open models: DeepSeek, Kimi, GLM, Qwen and MiniMax.4 models