Featherless AI

Featherless AI is a serverless LLM inference platform that serves thousands of open-weight models from the Hugging Face catalog behind a single OpenAI-compatible REST API. It uses flat monthly subscription pricing with unlimited tokens rather than per-token billing, exposing chat completions, text completions, an embeddings endpoint, and a large models catalog.

4 APIs 0 Features

AILLMInferenceServerlessOpen Models

APIs

Featherless Chat Completions API

OpenAI-compatible chat completions across thousands of open-weight Hugging Face models, with streaming, tool calling, vision messages, and the full set of sampling parameters (t...

Featherless Completions API

OpenAI-compatible legacy text completions endpoint accepting a prompt string (or array for parallel inference) against any catalog model, with the same sampling controls as chat...

Featherless Models API

Lists the thousands of open-weight models available for serverless inference, surfaced through an OpenAI-compatible models endpoint for runtime discovery.

Featherless Embeddings API

OpenAI-compatible embeddings endpoint that returns vector representations for a string or array of inputs using open embedding models such as Qwen3-Embedding, with optional enco...

Collections

Featherless AI API

OPEN

Pricing Plans

Featherless Plans Pricing

4 plans

PLANS

Rate Limits

Featherless Rate Limits

3 limits

RATE LIMITS

FinOps

Featherless Finops

FINOPS

Event Specifications

Featherless AI Chat Completions Streaming (HTTP + SSE)

AsyncAPI 2.6 description of Featherless AI's **chat completion streaming** surface. Featherless AI's core inference API is OpenAI-compatible and does not publish a WebSocket API...

ASYNCAPI

Resources

👥

GitHubOrganization

Sources

opencollection: 1.0.0
info:
  name: Featherless AI API
  version: '1.0'
request:
  auth:
    type: bearer
    token: '{{bearerToken}}'
items:
- info:
    name: Chat
    type: folder
  items:
  - info:
      name: Create a chat completion
      type: http
    http:
      method: POST
      url: https://api.featherless.ai/v1/chat/completions
      body:
        type: json
        data: "{\n  \"model\": \"Qwen/Qwen2.5-7B-Instruct\",\n  \"messages\": [\n    { \"role\": \"user\", \"content\": \"\
          Hello!\" }\n  ],\n  \"max_tokens\": 1000,\n  \"stream\": false\n}"
    docs: Generates a model response for a chat conversation. Set stream:true for Server-Sent Events.
- info:
    name: Completions
    type: folder
  items:
  - info:
      name: Create a text completion
      type: http
    http:
      method: POST
      url: https://api.featherless.ai/v1/completions
      body:
        type: json
        data: "{\n  \"model\": \"meta-llama/Meta-Llama-3.1-8B-Instruct\",\n  \"prompt\": \"Your prompt here\",\n  \"max_tokens\"\
          : 1000\n}"
    docs: Generates a text completion for the provided prompt. The prompt may be a string or array of strings (parallel inference).
- info:
    name: Embeddings
    type: folder
  items:
  - info:
      name: Create embeddings
      type: http
    http:
      method: POST
      url: https://api.featherless.ai/v1/embeddings
      body:
        type: json
        data: "{\n  \"model\": \"Qwen/Qwen3-Embedding-8B\",\n  \"input\": \"The quick brown fox\",\n  \"encoding_format\"\
          : \"float\"\n}"
    docs: Returns vector embeddings for the supplied input using an open embedding model.
- info:
    name: Models
    type: folder
  items:
  - info:
      name: List models
      type: http
    http:
      method: GET
      url: https://api.featherless.ai/v1/models
    docs: Lists the open-weight models available for serverless inference.