Fireworks AI
Fireworks-hosted models for chat, Responses, completions and embeddings.
Route models hosted on Fireworks AI through DeepintShield with a single Fireworks API key.
What works
- Chat Completions and the native Responses API
- Text completions, including streaming
- Embeddings and list models
- Tool calling and SSE streaming
Limits to know: Image generation, speech, transcription, files and batch are not exposed through the DeepintShield Fireworks integration.
How to connect
Add your Fireworks API key in Model Hub → AI Providers, create a Virtual Key, then call fireworks/<model> through https://app.deepintshield.com/v1 with any OpenAI-compatible client.
Read the Fireworks AI provider docs. Requests get the same Virtual Key budgets, guardrails and logs as every other provider on the AI gateway.