Fireworks AI

Fireworks AI provides enterprise-grade LLM inference with industry-leading speed. Supports serverless and on-demand deployments of open-source models with fine-tuning, LoRA adapters, and function calling. Used by companies requiring fast, reliable AI inference at scale.

Official Website Documentation

Endpoints

POST

Chat Completions

/v1/chat/completions

Fast chat completions with OpenAI-compatible API.

Streaming

Vision

Function Calling

Models

accounts/fireworks/models/llama-v3p3-70b-instructaccounts/fireworks/models/mixtral-8x22b-instructaccounts/fireworks/models/qwen2p5-72b-instruct

Pricing

Model	Input Price	Output Price	Context Window
Llama 3.3 70B	$0.90	$0.90	128.0K
Mixtral 8x22B	$0.90	$0.90	65.5K

Capabilities

Streaming

Function Calling

Tool Use

Vision

JSON Mode

Fine-tuning

Embeddings

Image Input

Long Context

Try it in Playground

Test Fireworks AI APIs directly in our interactive playground with your own API key.

Try it in Playground

Fireworks AI

Endpoints

Chat Completions

Capabilities

Try it in Playground

Overview

Fireworks AI

Endpoints

Chat Completions

Capabilities

Try it in Playground

Overview