| name | appnz-provider-fireworks |
| description | Use this skill when the user asks to use Fireworks AI, provider fireworks, or any fireworks model through app.nz; covers model selection when present, BYOK setup, OpenAI-compatible routing, provider-specific endpoints, aliases, and debugging gateway headers. |
Fireworks AI on app.nz
Route Fireworks AI through app.nz with one app.nz key. Use this skill when a user asks for Fireworks AI, fireworks, one of its model ids, aliases, product integrations, or BYOK setup for this provider.
Workflow
- Use
/api/gateway/models?provider=fireworks to confirm the current public model list if exact availability matters.
- Call app.nz at
https://app.nz/v1 with Authorization: Bearer pk_live_...; do not call https://api.fireworks.ai/inference directly unless the user explicitly asks to bypass app.nz.
- Store a user-owned upstream key with
POST /api/gateway/provider-keys using provider fireworks when BYOK is required. The upstream secret is never returned by app.nz.
- Prefer a model matching the task modality. If unsure, start with
fireworks/gpt-oss-120b or app/auto.
- Read
X-Gateway-Provider and X-Gateway-Model response headers when debugging routing.
BYOK
curl -sX POST https://app.nz/api/gateway/provider-keys \
-H "Authorization: Bearer pk_live_..." \
-H "Content-Type: application/json" \
-d '{"provider":"fireworks","api_key":"REDACTED_UPSTREAM_KEY"}'
Chat Example
curl -s https://app.nz/v1/chat/completions \
-H "Authorization: Bearer pk_live_..." \
-H "Content-Type: application/json" \
-d '{"model":"fireworks/gpt-oss-120b","messages":[{"role":"user","content":"Give me one practical idea."}]}'
Models
| Model | Modality | Aliases | Caps |
|---|
| fireworks/glm-5 | chat | fireworks-glm-5 | stream, tools |
| fireworks/gpt-oss-120b | chat | gpt-oss-120b, gpt-oss | stream, tools |
| whisper-v3-large | transcription | fireworks-whisper | - |
| whisper-v3-large-turbo | transcription | fireworks-whisper-turbo | - |
