GET
/v1/schemas/replicate/chat/models/openai/gpt-4.1-mini/predictions?kind=output
Accept:
| field | recorded source |
|---|---|
| schema | Source linked above. upstream-spec Source trace72d2e792835d9344a1b4a8765f49dac55d686a04533709e64157c851047c4f56{
"fetchedAt": 1794375035,
"extractorVersion": "2",
"verifiedAt": null
} |
Response body
17 properties · 10 required · 1 $defs| property | type | description | constraints |
|---|---|---|---|
| created_at* | string | The time that the prediction was created | format: date-time |
| data_removed* | boolean | Whether the prediction output has been deleted | |
| error* | string | An error string if the model status is `"failed"` | |
| id* | string | ||
| input* | object | The prediction input | |
| model* | string | The name of the model that created the prediction | |
| output* | string[] | ||
| status* | enum | The prediction status. `canceled` means the prediction was canceled (either by the user or because it reached its deadline while running). `aborted` means the prediction was terminated before it started running (for example, when a deadline is reached before t… | starting | processing | succeeded | failed | canceled | aborted |
| urls* | object | URLs for working with the prediction | |
| version* | string | enum | ||
| completed_at | string | The time that the model completed the prediction and all outputs were uploaded | format: date-time |
| deadline | string | The absolute time at which the prediction will be automatically canceled if it has not completed | format: date-time |
| deployment | string | The name of the deployment that created the prediction | |
| logs | string | The log output from the model | |
| metrics | object | Additional metrics associated with the prediction | |
| source | enum | Indicates how the prediction was created | web | api |
| started_at | string | The time that the model began the prediction | format: date-time |
Types
1 $defsOutputstring[]
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"replicate","endpointId":"models/openai/gpt-4.1-mini/predictions","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}