Come usare l’API GLM 5.3 Flash Abliterated API
-
Ottieni una chiave API: Crea una chiave nella dashboard di Muapi.
-
Invia un prompt: POST prompt (oltre a system_prompt e max_tokens, up to 32768) to /api/v1/glm-5-3-flash-abliterated. Provide an optional public image_url to include an image con your prompt.
curl -X POST https://api.muapi.ai/api/v1/glm-5-3-flash-abliterated \
-H "x-api-key: $MUAPI_KEY" \
-H "Content-Type: application/json" \
-d '{"prompt": "Explain how attention works in transformers.", "image_url": "https://example.com/photo.jpg"}'
- Esegui polling o attiva lo streaming: Esegui il polling su
GET /api/v1/predictions/{request_id}/result finché status non è completed oppure ricevi i token in streaming da /api/v1/glm-5-3-flash-abliterated/stream.
curl -X POST https://api.muapi.ai/api/v1/glm-5-3-flash-abliterated/stream \
-H "x-api-key: $MUAPI_KEY" \
-H "Content-Type: application/json" \
-d '{"prompt": "Explain how attention works in transformers.", "image_url": "https://example.com/photo.jpg"}'
- Leggi il risultato: The generated text non è returned in
outputs. Usage non è billed on actual token counts.