LLM APIs

Hosted model APIs, studios, and local inference servers.

Best LLM APIs 2026: ranked list → · Free-tier limits · Deprecation tables · Cost calculator

• MiniCPM-V 4.7 Visit model · multimodal

  OpenBMB image-text-to-text model on Hugging Face. Transformers weights, multimodal, MoE.

• OpenAI API Visit api · openai

  API platform for OpenAI models.

• Anthropic Console Visit api · anthropic

  Console and API for Claude models.

• Google AI Studio Visit api · google

  Google's studio for prompting Gemini and getting an API key.

• OpenRouter Visit api · router

  One API that routes requests to many model providers.

• Groq Visit api · inference

  Inference API known for low-latency open models.

• Together AI Visit api · inference

  Inference and fine-tuning API for open models.

• Mistral Visit api

  Mistral's model API and Le Chat product.

• xAI API Visit api · xai

  API documentation for xAI's Grok models.

• Fireworks AI Visit api · inference

  Inference platform for open models.

• DeepSeek Visit api

  DeepSeek's models and API.

• Cohere Visit api

  API for Cohere's command and embed models.

• Cerebras Visit inference

  Wafer-scale inference for open models.

• Hugging Face Visit hub · inference

  Model hub, datasets, and hosted inference.

• Workers AI Visit cloudflare · inference

  Model inference inside Cloudflare Workers.

• Amazon Bedrock Visit aws · api

  AWS API for foundation models, including Anthropic and Amazon models.

• Vertex AI Visit google · api

  Google Cloud platform for Gemini and other models.

• Azure OpenAI Visit azure · api

  OpenAI models hosted on Microsoft Azure.

• Ollama Visit local

  Local app for running open models on your own machine.

• LM Studio Visit local

  Desktop app for running local models with an OpenAI-compatible server.

• NVIDIA NIM Visit nvidia · inference

  NVIDIA's catalog of inference microservices and trial APIs.

• DeepInfra Visit api · inference

  Hosted inference API for open models.

• Replicate Visit api

  API for running published models, including image and language models.

• fal Visit api · media

  Inference API aimed at image, video, and audio models.

• SambaNova Visit inference

  Inference platform for open language models.

• Mercury 3 Visit api · llm

  Inception's diffusion LLM for chat. Launch price is $0.10 per 1M input tokens and $0.35 per 1M output.