Penyedia
Lab, cloud, dan router yang modelnya ada di katalog. Harga yang ditampilkan adalah harga OPTES, bukan harga mereka.
OPTES
Lab model
AI21 LabsThe Jamba family of long-context models.2 modelAnthropicThe Claude family (Fable, Opus, Sonnet, Haiku) through the Claude API.4 modelCohereCanadian lab focused on enterprise models; Aya Expanse is its multilingual line.1 modelCore42 CompassG42's model platform in the UAE, home of the Arabic-first Seraj model.5 modelGoogle AI StudioThe Gemini family through the Gemini API (Google AI Studio).6 modelMetaMeta's Model API (public preview) with the Muse family; Llama models run on other providers.4 modelMistral AIFrench lab: Mistral Medium, Large and Small, Codestral, Ministral and embeddings.6 modelOpenAIThe GPT-6 and GPT-5.x families through OpenAI's own API platform.4 modelPerplexitySonar, a search-grounded model, plus selected third-party models through its Agent API.3 modelReka AIMultimodal models that read text, images, video and audio.3 modelUpstageKorean lab: the Solar models and document AI.3 modelWriterEnterprise lab behind the Palmyra models with 1M-token context.3 modelxAIThe Grok family, including Grok Build for code and Grok Imagine for images.4 model
Lab Tiongkok, platform internasional
Alibaba Cloud Model StudioThe Qwen family through Alibaba Cloud's international Model Studio.3 modelBytePlus ModelArkByteDance's international platform: the Seed models and hosted DeepSeek and GLM.3 modelDeepSeekDeepSeek's own platform: V4 Pro and V4.1 Flash, with 1M context and a 50% off-peak discount.2 modelMiniMaxMiniMax's international platform: the M-series text models with 1M context.2 modelMoonshot AIThe Kimi models through Moonshot's international platform.4 modelStepFunStepFun's international platform: Step 5 and the fast Step 3.x Flash models.3 modelTencent Cloud TokenHubTencent's international hub: the Hy models plus Kimi, GLM, DeepSeek and MiniMax.3 modelXiaomi MiMoXiaomi's MiMo models, priced low outside China.2 modelZ.aiThe GLM family through Z.ai's international platform.5 model
Platform cloud
Amazon BedrockAWS's model service: Claude, GPT-6 Astra, Amazon Nova, Llama, Mistral, DeepSeek, Kimi and Grok.13 modelGoogle Cloud Vertex AIGoogle Cloud's model platform: Gemini plus Claude, Llama and Mistral on one bill.7 modelIBM watsonx.aiIBM's model platform: Granite plus Llama, Mistral and gpt-oss.5 modelMicrosoft Azure AI FoundryMicrosoft's model platform: OpenAI models plus DeepSeek, Grok, Kimi, Llama and Mistral.11 modelOracle OCI Generative AIOracle Cloud's model service, with regions in Dubai, Abu Dhabi and Riyadh.5 model
Penyedia inferensi
AkashMLOpen models on the decentralised Akash GPU network.7 modelBasetenAmong the fastest providers for gpt-oss-120b and Kimi K3, with near-lowest prices.8 modelCerebrasThe fastest published speeds in the research: about 3,000 tokens a second on gpt-oss-120b.2 modelChutesDecentralised inference where every model runs inside a trusted execution environment (TEE).9 modelCloudflare Workers AIModels served on Cloudflare's network, priced per 1M tokens from its Neuron units.13 modelCoreWeaveGPU cloud with serverless inference (formerly W&B Inference) and a very recent catalog.14 modelCrusoeManaged inference with low cached-input prices: DeepSeek, Kimi, GLM, gpt-oss and Nemotron.9 modelDeepInfraAmong the lowest prices for gpt-oss, GLM-5.3, DeepSeek V4 Flash and MiniMax M3.15 modelfalA marketplace of image, video and audio generation models.3 modelFeatherlessMore than 4,000 open models and fine-tunes from Hugging Face behind one API.12 modelFireworks AIFast serverless inference with Standard and Fast tiers for the big open models.7 modelFriendliAIFast inference engine; a focused serverless list around GLM-5.x, DeepSeek and MiniMax.8 modelGMI CloudGPU cloud with an inference engine for DeepSeek, Kimi, GLM, Qwen and MiniMax.11 modelGroqVery fast inference on its own LPU chips; a small public catalog.6 modelinference.netInference platform with open models and its own Schematron extraction models.10 modelio.netDecentralised GPU network with IO Intelligence, an API for open models.12 modelModalServerless GPU platform with a shared per-token API for Kimi K3, GLM-5.3 and more.4 modelNebius Token FactoryEuropean inference cloud that publishes a measured speed for every model.14 modelNovita AIA broad catalog of 120 open models for text, images, video and audio.17 modelNscaleBritish AI cloud with serverless endpoints for gpt-oss, Llama and Qwen.7 modelOVHcloud AI EndpointsEuropean serverless endpoints for gpt-oss, Llama 3.3 and Qwen.6 modelParasailDay-zero support for big open models and some of the lowest DeepSeek and gpt-oss prices.17 modelReplicateA large catalog of image, video and audio models; a few language models.2 modelRunpodGPU cloud with public endpoints for Kimi models, including Kimi K3 with 1M context.4 modelSambaNovaInference on SambaNova's own chips: DeepSeek, Llama, gpt-oss, MiniMax and Gemma.7 modelSiliconFlowInternational platform with some of the lowest prices for DeepSeek V4.1 Flash and gpt-oss.14 modelTogether AIOne of the widest catalogs of open-weights models: DeepSeek, Kimi, GLM, Qwen, Llama and more.12 model
Router dan gateway
302.AIA gateway to Western and Chinese models plus image, video and audio generation.1 modelAIHubMixA gateway to text, image, video and audio models from the big labs.4 modelEden AIOne API over 500+ models, including specialised expert models.3 modelHugging Face Inference ProvidersHugging Face's router over partner providers, at the partners' prices.10 modelOpenRouterA router over 500+ models from 80+ providers.3 modelRequestyA router over 600+ models from 20+ providers.3 modelTokenGOSelf-operated open models: DeepSeek, Kimi, GLM, Qwen and MiniMax.4 model