Fireworks
Use this when your team already runs on Fireworks and you want that vendor family to stay explicit in Loong config instead of disappearing behind a generic compatibility route.At A Glance
| Field | Value |
|---|---|
| Built-in kind | fireworks |
| Provider group | Direct Hosted Providers |
| Protocol family | openai_chat_completions |
| Feature family | openai_compatible |
| Auth scheme | bearer |
| Credential envs | FIREWORKS_API_KEY, FIREWORKS_AI_API_KEY |
| Aliases | fireworks_compatible, fireworks-ai |
| Default base URL | https://api.fireworks.ai |
| Request endpoint | https://api.fireworks.ai/inference/v1/chat/completions |
| Models endpoint | https://api.fireworks.ai/inference/v1/models |
Minimal Config
Verify It
list-models is unreliable for this account or region, pin an explicit provider.model or add preferred_models instead of leaving recovery implicit.
Auth And Routing Contract
| Contract | Value |
|---|---|
| Auth optional | no |
| Model probe auth optional | no |
| Default API key env | FIREWORKS_API_KEY |
| OAuth env | none |
| Primary request route | https://api.fireworks.ai/inference/v1/chat/completions |
| Primary model-catalog route | https://api.fireworks.ai/inference/v1/models |
Related Docs
- Continue to Providers And Models when you still need the broader chooser page.
- Continue to Provider Guides for the full built-in provider matrix.
- Continue to Provider Recipes for representative rollout recipes.
- Continue to Configuration Patterns for the shared provider-profile shape.