So verwendest du die GLM 4.6 Derestricted v5 API
-
API-Schlüssel erstellen: Lege in deinem Muapi-Dashboard einen Schlüssel an.
-
Prompt senden: Sende prompt (optional auch system_prompt und max_tokens, bis zu 32768) per POST an /api/v1/glm-4-6-derestricted-v5.
curl -X POST https://api.muapi.ai/api/v1/glm-4-6-derestricted-v5 \
-H "x-api-key: $MUAPI_KEY" \
-H "Content-Type: application/json" \
-d '{"prompt": "Explain how attention works in transformers."}'
- Poll or stream: Poll
GET /api/v1/predictions/{request_id}/result until status ist completed, or stream tokens live from /api/v1/glm-4-6-derestricted-v5/stream.
curl -X POST https://api.muapi.ai/api/v1/glm-4-6-derestricted-v5/stream \
-H "x-api-key: $MUAPI_KEY" \
-H "Content-Type: application/json" \
-d '{"prompt": "Explain how attention works in transformers."}'
- Read the result: The generated text ist returned in
outputs. Usage ist billed on actual token counts.