Fireworks AI
Cloud API provider for fast open-model inference via api.fireworks.ai.
Fireworks AI provides fast inference for open-weight models with an OpenAI-compatible API at api.fireworks.ai.
Configuration
[backend]
name = "fireworks"
url = "https://api.fireworks.ai"
model = "accounts/fireworks/models/llama-v3p3-70b-instruct"
api_key = "fw_..."Notes
Model names use the accounts/fireworks/models/<model> prefix format.
Default Endpoint
POST https://api.fireworks.ai/inference/v1/chat/completions