GPT Image Generator API documentation
Generate images with GPT Image Generator (OpenAI).
Endpoints
| Contract item | Value |
|---|---|
| Capability | gpt-image-generator |
| Submit | POST https://vidmage.ai/api/v1/gpt-image-generator/submit |
| Query | POST https://vidmage.ai/api/v1/gpt-image-generator/query |
| Task identifier | taskId |
| Result field | imageUrl |
Authenticate with Authorization: Bearer YOUR_API_KEY. Save the task identifier and query the same capability. Use a stable Idempotency-Key for submission retries.
Product guide: GPT Image API
Parameters and input rules
| Field | Type | Required | Default | Meaning and limits |
|---|---|---|---|---|
prompt | string | Yes | Not specified | Text prompt describing the image to generate (max 20000 chars). For an unspecified character or figurine, use an original non-branded character with no logos and no resemblance to existing copyrighted superheroes; preserve any character the user explicitly names. Minimum characters: 1Maximum characters: 20000 |
aspectRatio | string | No | Not specified | Output aspect ratio. Values: "960x960", "720x1280", "1280x720", "1168x784", "784x1168" |
model | string | No | "g-4.2" | Choose the GPT image model generation tier. Values: "g-3", "g-4", "g-4.1", "g-4.2" |
text to image
These are public VidMage field names. The server maps them to provider fields. Input media selects the mode; use its limits together with the parameter table.
| Control | Mode-specific rule |
|---|---|
prompt | Required; 1–20000 characters. |
aspectRatio | Values: "960x960", "720x1280", "1280x720", "1168x784", "784x1168". Default: 1280x720. |
resolution | Not used in this mode. |
model | Choose the GPT image model generation tier. Values: "g-3", "g-4", "g-4.1", "g-4.2"Default: "g-4.2" |
Example request
{
"prompt": "Clean product photograph of a minimalist ceramic desk lamp on a warm neutral background",
"aspectRatio": "1280x720",
"model": "g-4.2"
}# Set VIDMAGE_IDEMPOTENCY_KEY to a unique value for this task; preserve it for transport retries.
curl -X POST "https://vidmage.ai/api/v1/gpt-image-generator/submit" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Idempotency-Key: ${VIDMAGE_IDEMPOTENCY_KEY}" \
-H "Content-Type: application/json" \
-d '{"prompt":"Clean product photograph of a minimalist ceramic desk lamp on a warm neutral background","aspectRatio":"1280x720","model":"g-4.2"}'
# -> { "success": true, "taskId": "...", "creditsConsumed": ... }Task results and recovery
URL of the generated image. Read imageUrl from the completed query response. Preserve taskId while the task is running.
curl -X POST "https://vidmage.ai/api/v1/gpt-image-generator/query" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{ "taskId": "TASK_ID_FROM_SUBMIT" }'
# -> { "success": true, "data": { "status": "...", "imageUrl": "https://..." } }Submission and task queries report the available task and usage information. A timeout is not a confirmed failure. Recover the existing task instead of resubmitting.
For face selection and error recovery, follow Task lifecycle. MCP uses the normalized taskId argument in get_task_result, including capabilities whose REST identifier is requestId.
Credits
| Component / option | Rate | Minimum |
|---|---|---|
| Base rate | 5 credits / generation | — |
Base charge is per generation at the selected resolution.
Use the Playground or the MCP credit estimator for your exact inputs. Credits and billing.