AI hosting, APIs and inference

20 listed

• AWS Bedrock

  Amazon Bedrock is AWS's managed service for foundation models from several vendors, including Amazon, AI21 Labs, Stability AI, Writer, xAI and others, through one API.

  • Cloud AI platform (hyperscaler)
• Anthropic API

  Anthropic's API bills per token.

  • Model / inference API
• Cloudflare Pages

  Cloudflare Pages hosts static sites and front ends from a Git repository, and we list it because many agent-built apps from tools like Lovable, Bolt and Cursor end up there.

  • Agent and app hosting
• Cloudflare Workers AI

  Workers AI is Cloudflare's way to run open models from a Worker or over a REST API.

  • Model / inference API
• Cohere

  Inference provider headquartered in US. Serves models through OpenRouter as "Cohere".

  • Model / inference API
• DeepSeek API

  The DeepSeek API bills per token.

  • Model / inference API
• Fireworks AI

  Fireworks AI serves open models by the token and states zero data retention by default.

  • Model / inference API
  • OpenAI compatible
• Google AI (Gemini API)

  The Gemini API prices per token.

  • Model / inference API
• Groq

  GroqCloud serves open models on its own inference hardware, with speed as the draw.

  • Model / inference API
  • OpenAI compatible
• Hugging Face Inference

  Hugging Face Inference Endpoints deploys a model from the Hub onto dedicated, autoscaling hardware.

  • Model / inference API
• Lambda Cloud

  Lambda Cloud rents on-demand GPU instances and states that it charges no egress fees.

  • GPU cloud
• Meta Llama API

  Inference provider headquartered in US. Serves models through OpenRouter as "Meta".

  • Model / inference API
• Mistral AI API

  Mistral AI's API prices Large 4 at $0.70 per million input tokens and $2.10 output with a 1M context, on our 31 October 2026 read.

  • Model / inference API
• Modal

  Modal runs Python code on GPUs and bills by the second, with no servers to manage: you decorate functions and Modal builds the container and scales it.

  • Serverless GPU
• OpenAI API

  OpenAI's API bills per token.

  • Model / inference API
• OpenRouter

  OpenRouter routes more than 600 models through one API key.

  • Model gateway (router)
  • OpenAI compatible
• Replicate

  Replicate runs models through an API and bills either by the second of hardware or by output, depending on the model.

  • Model / inference API
• RunPod

  Runpod rents GPUs by the second, either as pods you control or as serverless endpoints.

  • GPU cloud
• Together AI

  Together AI serves open models by the token and also rents GPUs.

  • Model / inference API
  • OpenAI compatible
• xAI API

  Inference provider headquartered in US. Serves models through OpenRouter as "xAI".

  • Model / inference API