{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreihknk45mqdr2k5fx4e365u4x5eqbkq3tsyerirmgau7sm4pc65tuu",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mhdtvggct7k2"
  },
  "path": "/t/gpt-5-4-mini-not-working-with-batch-api-model-not-found/1377101#post_1",
  "publishedAt": "2026-03-18T15:25:06.000Z",
  "site": "https://community.openai.com",
  "textContent": "`gpt-5.4-mini` works fine with the Responses API but fails when used through the Batch API. The batch endpoint resolves it to `gpt-5.4-mini-2026-03-17-batch`, which returns a `model_not_found` error.\n\n\n    {\n      \"error\": {\n        \"message\": \"The requested model 'gpt-5.4-mini-2026-03-17-batch' does not exist.\",\n        \"type\": \"invalid_request_error\",\n        \"param\": \"model\",\n        \"code\": \"model_not_found\"\n      }\n    }\n\n\nI’ve got _gpt-5.4-mini_ on the code, the date and batch were added automatically on the OpenAI API",
  "title": "Gpt-5.4-mini not working with Batch API — model_not_found"
}