{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreifcolivw45aktijickmjqjeur6lxzct4vmqxjnrtaaamsmapsve5a",
"uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mkktjdchdwy2"
},
"path": "/t/not-able-to-request-batch-api-of-gpt-5-2/1379954#post_5",
"publishedAt": "2026-04-28T14:11:35.000Z",
"site": "https://community.openai.com",
"tags": [
"help.openai.com",
"Error Message \"Does not have acces to model `gpt-4o-mini-2024-07-18-batch`\"",
"Bugs"
],
"textContent": "Was this a status that was immediately received as a response to job submission, or was it the final report of the batch job?\n\n### Reproduction?\n\n\n [1/5] JSONL file written: repro_batch_input.jsonl\n Contents:\n {\"custom_id\": \"repro-request-1\", \"method\": \"POST\", \"url\": \"/v1/responses\", \"body\": {\"model\": \"gpt-5.2\", \"max_output_tokens\": 64, \"input\": \"Reply with exactly one sentence: what is the capital of France?\"}}\n\n [2/5] Uploading repro_batch_input.jsonl to Files API …\n\n ────────────────────────────────────────────────────────────────────────\n Files API – upload response\n HTTP 200 OK\n ────────────────────────────────────────────────────────────────────────\n {\n \"object\": \"file\",\n \"id\": \"file-PqZwFghKRKVKJt5XoDss8c\",\n \"purpose\": \"batch\",\n \"filename\": \"repro_batch_input.jsonl\",\n \"bytes\": 207,\n \"created_at\": 1777384613,\n \"expires_at\": 1779976613,\n \"status\": \"processed\",\n \"status_details\": null\n }\n\n Uploaded file ID: file-PqZwFghKRKVKJt5XoDss8c\n\n [3/5] Creating batch job (endpoint=/v1/responses, model=gpt-5.2) …\n\n ────────────────────────────────────────────────────────────────────────\n Batches API – create response\n HTTP 200 OK\n ────────────────────────────────────────────────────────────────────────\n {\n \"id\": \"batch_69f0bca659cc8190bd3b6f4abc6d30e4\",\n \"object\": \"batch\",\n \"endpoint\": \"/v1/responses\",\n \"model\": null,\n \"errors\": null,\n \"input_file_id\": \"file-PqZwFghKRKVKJt5XoDss8c\",\n \"completion_window\": \"24h\",\n \"status\": \"validating\",\n \"output_file_id\": null,\n \"error_file_id\": null,\n \"created_at\": 1777384614,\n \"in_progress_at\": null,\n \"expires_at\": 1777471014,\n \"finalizing_at\": null,\n \"completed_at\": null,\n \"failed_at\": null,\n \"expired_at\": null,\n \"cancelling_at\": null,\n \"cancelled_at\": null,\n \"request_counts\": {\n \"total\": 0,\n \"completed\": 0,\n \"failed\": 0\n },\n \"usage\": {\n \"input_tokens\": 0,\n \"output_tokens\": 0,\n \"total_tokens\": 0,\n \"input_tokens_details\": {\n \"cached_tokens\": 0\n },\n \"output_tokens_details\": {\n \"reasoning_tokens\": 0\n }\n },\n \"metadata\": {\n \"description\": \"Bug repro \\u2013 gpt-5.2 batch model-name exposure\"\n }\n }\n\n Batch ID : batch_69f0bca659cc8190bd3b6f4abc6d30e4\n Status : validating\n\n [4/5] Polling status every 60s …\n\n [06:56:55] Poll # 1 status=validating total=0 completed=0 failed=0\n [06:57:56] Poll # 2 status=validating total=0 completed=0 failed=0\n\n\n### Success Result\n\n`{\"id\": \"batch_req_69f0bd1bfd0c81908abc6f4c88ed8c40\", \"custom_id\": \"repro-request-1\", \"response\": {\"status_code\": 200, \"request_id\": \"51d2a899-6032-4205-a500-cf5738640d0e\", \"body\": {\"id\": \"resp_0672a70fd833dc4b0069f0bcf0668481a08623b7b2cc64efa7\", \"object\": \"response\", \"created_at\": 1777384688, \"status\": \"completed\", \"background\": false, \"billing\": {\"payer\": \"openai\"}, \"completed_at\": 1777384689, \"error\": null, \"frequency_penalty\": 0.0, \"incomplete_details\": null, \"instructions\": null, \"max_output_tokens\": 64, \"max_tool_calls\": null, \"model\": \"gpt-5.2-2025-12-11\", \"moderation\": null, \"output\": [{\"id\": \"msg_0672a70fd833dc4b0069f0bcf1189c81a08c6cf9f659940e39\", \"type\": \"message\", \"status\": \"completed\", \"content\": [{\"type\": \"output_text\", \"annotations\": [], \"logprobs\": [], \"text\": \"The capital of France is Paris.\"}], \"role\": \"assistant\"}], \"parallel_tool_calls\": true, \"presence_penalty\": 0.0, \"previous_response_id\": null, \"prompt_cache_key\": null, \"prompt_cache_retention\": \"in_memory\", \"reasoning\": {\"effort\": \"none\", \"summary\": null}, \"safety_identifier\": null, \"service_tier\": \"default\", \"store\": true, \"temperature\": 1.0, \"text\": {\"format\": {\"type\": \"text\"}, \"verbosity\": \"medium\"}, \"tool_choice\": \"auto\", \"tools\": [], \"top_logprobs\": 0, \"top_p\": 0.98, \"truncation\": \"disabled\", \"usage\": {\"input_tokens\": 19, \"input_tokens_details\": {\"cached_tokens\": 0}, \"output_tokens\": 11, \"output_tokens_details\": {\"reasoning_tokens\": 0}, \"total_tokens\": 30}, \"user\": null, \"metadata\": {}}}, \"error\": null} `\n\nIt seems that it is not platform-wide. You can persist with different “project” methods, such as default org with no special permissions or limits, or even a legacy user key if your org has that by having used them in the past.\n\nYou will need to contact via help.openai.com and see if there is an org provisioning issue causing the `-batch` suffix to be exposed as an error result, including similar information for action about the job ID or error status of the call or the job as I show. In your message, give the bot or front line support nothing to ask about further, so that your message will result in escalation to staff.\n\nSimilar case, among many, demonstrating a fault with the way the batch endpoint works, that goes way back.\n\nError Message \"Does not have acces to model `gpt-4o-mini-2024-07-18-batch`\" Bugs\n\n> I have used the batch API for my application but have encountered with an unexpected error with status code 403 and error message “Project … does not have access to model gpt-4o-mini-2024-07-18-batch”. But when I check the list accessed models, I don’t see any model named “gpt-4o-mini-2024-07-18-batch”. How can I resolve the problem? Below are the details of the messages. { “id”:“batch_req_6768d577967881908e5bc881d5******”, “custom_id”:“106311”, “response”:{ “status_code”:403, “request_id”:“…",
"title": "Not able to request batch api of GPT 5.2"
}