Fireworks AI
Overview
Section titled “Overview”Fireworks AI is an OpenAI-compatible provider offering the same API interface with identical parameter handling. Key features:
- Full OpenAI compatibility - Identical request/response format
- Streaming support - Server-Sent Events with delta-based updates
- Tool calling - Complete function definition and execution support
- Native text completions - Served directly via
/v1/completions - Embeddings - Served directly via
/v1/embeddings
Supported Operations
Section titled “Supported Operations”| Operation | Non-Streaming | Streaming | Endpoint |
|---|---|---|---|
| Chat Completions | ✅ | ✅ | /v1/chat/completions |
| Responses API | ✅ | ✅ | /v1/responses |
| Text Completions | ✅ | ✅ | /v1/completions |
| Embeddings | ✅ | - | /v1/embeddings |
| List Models | ✅ | - | /v1/models |
| Image Generation | ❌ | ❌ | - |
| Speech (TTS) | ❌ | ❌ | - |
| Transcriptions (STT) | ❌ | ❌ | - |
| Files | ❌ | ❌ | - |
| Batch | ❌ | ❌ | - |
Configuration
Section titled “Configuration”Add Fireworks AI as a provider with a single API key. The default base URL is https://api.fireworks.ai/inference; override it per workspace if you front Fireworks behind a custom gateway.
{ "provider": "fireworks", "keys": [{ "value": "env.FIREWORKS_API_KEY", "models": [], "weight": 1.0 }]}Model identifiers use Fireworks’ fully-qualified form, e.g. accounts/fireworks/models/llama-v3p1-70b-instruct.
1. Chat Completions
Section titled “1. Chat Completions”Request Parameters
Section titled “Request Parameters”Fireworks AI supports all standard OpenAI chat completion parameters. For full parameter reference and behavior, see OpenAI Chat Completions.
2. Responses API
Section titled “2. Responses API”Unlike chat-only OpenAI-compatible providers, Fireworks exposes a native Responses endpoint, so DeepIntShield forwards Responses requests directly to /v1/responses rather than converting them to chat completions.
3. Text Completions
Section titled “3. Text Completions”Fireworks supports the legacy completions endpoint natively at /v1/completions, including streaming.
4. Embeddings
Section titled “4. Embeddings”Embedding requests are forwarded to /v1/embeddings using the standard OpenAI embedding request/response shape.
5. List Models
Section titled “5. List Models”Fireworks’ model listing endpoint returns available models with their context lengths and capabilities at /v1/models.