Alibaba DashScopehttps://dashscope.aliyun.comQwen model endpoints. Anthropichttps://console.anthropic.comClaude frontier models. AWS Bedrockhttps://aws.amazon.com/bedrockManaged multi-provider model service. Azure OpenAIhttps://azure.microsoft.com/products/ai-services/openai-serviceOpenAI models on Azure. Cerebras Inferencehttps://cerebras.aiWafer-scale fast inference, free tier. DeepSeekhttps://platform.deepseek.comDeepSeek models, very low cost. Fireworks AIhttps://fireworks.aiFast open-model inference. GitHub Modelshttps://github.com/marketplace/modelsFree model playground + API for GitHub accounts. Google AI Studio / Gemini APIhttps://aistudio.google.comGemini family with a genuinely free tier. Google Vertex AIhttps://cloud.google.com/vertex-aiGCP's managed model + agent platform. Groqhttps://groq.comUltra-fast LPU inference for open models. HuggingFace Inferencehttps://huggingface.co/inference-apiHosted inference across the HF model hub. Hyperbolichttps://hyperbolic.xyzCheap open-model GPU inference. Mistral La Plateformehttps://console.mistral.aiMistral models; free experiment tier. Moonshot / Kimihttps://platform.moonshot.aiKimi models, long context. MorphLLMhttps://morphllm.comFast apply/edit model endpoints. Novita AIhttps://novita.aiServerless GPU model APIs. NVIDIA NIMhttps://build.nvidia.comHosted open-model endpoints with free credits. Ollama Cloudhttps://ollama.com/cloudHosted Ollama-compatible inference. OpenAIhttps://platform.openai.comGPT frontier models, images, audio, video. OpenRouterhttps://openrouter.aiUnified API over hundreds of models incl. a free pool. Perplexity Sonarhttps://docs.perplexity.aiSearch-grounded answer models. SambaNovahttps://sambanova.aiRDU inference + free cloud tier. Together AIhttps://together.aiOpen-model inference + fine-tuning. xAI / Grokhttps://console.x.aiGrok models. Z.ai GLMhttps://z.aiGLM model family.