| name | appnz-provider-groq |
| description | Use this skill when the user asks to use Groq, provider groq, or any groq model through app.nz; covers model selection when present, BYOK setup, OpenAI-compatible routing, provider-specific endpoints, aliases, and debugging gateway headers. |
Groq on app.nz
Route Groq through app.nz with one app.nz key. Use this skill when a user asks for Groq, groq, one of its model ids, aliases, product integrations, or BYOK setup for this provider.
Workflow
- Use
/api/gateway/models?provider=groq 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.groq.com/openai directly unless the user explicitly asks to bypass app.nz.
- Store a user-owned upstream key with
POST /api/gateway/provider-keys using provider groq when BYOK is required. The upstream secret is never returned by app.nz.
- Prefer a model matching the task modality. If unsure, start with
llama-3.3-70b-versatile 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":"groq","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":"llama-3.3-70b-versatile","messages":[{"role":"user","content":"Give me one practical idea."}]}'
Models
| Model | Modality | Aliases | Caps |
|---|
| distil-whisper-large-v3-en | transcription | distil-whisper, whisper-en | - |
| llama-3.1-8b-instant | chat | llama-8b | stream, tools |
| llama-3.3-70b-versatile | chat | llama-70b | stream, tools |
| mixtral-8x7b-32768 | chat | mixtral | stream, tools |
| whisper-large-v3 | transcription | whisper-v3 | - |
| whisper-large-v3-turbo | transcription | whisper-turbo, groq-whisper | - |