Quick Answer
- GPT-Image-2.5 supports Text-to-Video, Image-to-Video, R2V, and Video Edit in one workflow.
- Use this model guide page to validate parameters with minimal request/response examples.
- Stabilize prompts here first, then move to production API integration.
Key Parameters
- model | string | required | gpt-image-2.5-flare | - | Model identifier. Use the fixed value `gpt-image-2.5-flare`.
- prompt | string | required | - | - | Main instruction describing the subject, action, scene, and style.
- aspect_ratio | string | optional | 16:9 | 16:9 | 9:16 | 1:1 | Video aspect ratio. Defaults to `16:9`; supports `16:9 | 9:16 | 1:1`.
- duration | integer | optional | 6 | 5 | 10 | 15 | 20 | Output duration in seconds. Defaults to `6`; supports `5 | 10 | 15 | 20`.
- resolution | string | optional | 720P | 720P | Output resolution. Defaults to `720P`; supports `720P`.
Common Errors
- 400 invalid_request_error: trigger=Request payload misses required fields or has invalid field types.; fix=Validate model, mode, and input schema before request.; retry=Retry only after fixing payload; avoid blind retries.
- 401 authentication_error: trigger=Missing Authorization header or invalid API key.; fix=Verify Bearer token format and API key scope.; retry=Retry after auth fix; rotate key if repeated failures continue.
- 429 rate_limit_exceeded: trigger=Request rate, concurrency, or current quota hits upstream rate limiting.; fix=Apply exponential backoff first, then review request rate, concurrency, and quota usage.; retry=Use exponential backoff (e.g., 1s/2s/4s) with jitter; if it persists, reduce submission pressure.
- 500 internal_error: trigger=Transient upstream error or internal processing failure.; fix=Capture request id and trigger retry workflow.; retry=Retry 2-3 times with short delays; escalate if persistent.
