API reference
Everything the dashboard does is backed by this API: submit a job, check its status, and list the live models and prices.
Submit a job
POST https://getmecompute.com/api/jobs
Content-Type: application/json
{
"model": "ltx-2-3",
"prompt": "A calm ocean at golden hour, gentle waves",
"image_url": "https://your-bucket.s3.amazonaws.com/frame.jpg",
"duration": "10s",
"aspect_ratio": "16:9",
"resolution": "1080p",
"quality": "standard",
"webhook_url": "https://your-app.com/hooks/video-done"
}| Field | Description |
|---|---|
| model | Required. Model id — wan-2-2 or ltx-2-3. List the live set with GET /api/models. |
| prompt | Required. Describes the motion you want. See Getting great results. |
| image_url | Required. Publicly fetchable URL of the source image (the video's first frame). |
| duration | Required. Clip length as a string, e.g. "5s" or "10s". Must be one of the selected model's offered durations. |
| aspect_ratio | Required. e.g. "16:9", "9:16", "1:1" — from the model's offered ratios. |
| resolution | Required. e.g. "720p" or "1080p" — from the model's offered resolutions. |
| quality | Optional, default standard. One of fast, standard, high, highest (the dashboard labels fast as “Faster”). Affects the per-second rate. |
| webhook_url | Optional. If set, we POST to this URL when the job finishes — see Webhooks & automation. |
All option values are validated against the model's live configuration, and the price is computed server-side from the official rate card — a client can never set its own price.
Response
{
"message": "Job submitted successfully",
"jobId": "385df601-fafb-4549-b8a8-…",
"cost": 0.6
}Errors
| Status | Meaning |
|---|---|
| 400 | A required field is missing, or a value isn't offered by the selected model (the error message names the field). |
| 401 | Not authenticated. |
| 502 | The job couldn't be dispatched for processing; it is marked failed and you are not billed. |
Check a job
GET https://getmecompute.com/api/jobs/385df601-…
Returns the job's status, its settings, the cost, the input image URL (s3_url), and — once completed — the video URL in result_s3_url. Failed jobs include an error_message. You can only read your own jobs (403 otherwise).
| Status value | Meaning |
|---|---|
| pending | Queued and waiting for capacity. |
| running | Rendering now. |
| completed | Done — result_s3_url holds the MP4. |
| failed / failed_oom | Generation failed (failed_oom = the settings exceeded GPU memory). Never billed. |
List models & prices
GET https://getmecompute.com/api/models
Returns the active models with their offered durations, aspect_ratios, resolutions, and the full prices matrix (prices[resolution][quality] = $/second). This is the same data that drives the submit form and the public rate card — use it to build pickers or estimate costs in your own tools.