GPT-5-Codex over GitHub copilot does not work #2977
Description
So, I've been trying to make GPT 5 Codex to work (through copilot), but the farthest I could was to this:
Error: {
code = "unsupported_api_for_model",
message = "model gpt-5-codex is not accessible via the /chat/completions endpoint"
}
These are some important debug information from copilot:
{
"capabilities": {
"family": "gpt-5-codex",
"limits": {
"max_context_window_tokens": 200000,
"max_output_tokens": 64000,
"max_prompt_tokens": 128000,
"vision": {
"max_prompt_image_size": 3145728,
"max_prompt_images": 1,
"supported_media_types": [
"image/jpeg",
"image/png",
"image/webp",
"image/gif"
]
}
},
"object": "model_capabilities",
"supports": {
"parallel_tool_calls": true,
"streaming": true,
"structured_outputs": true,
"tool_calls": true,
"vision": true
},
"tokenizer": "o200k_base",
"type": "chat"
},
"id": "gpt-5-codex",
"model_picker_category": "powerful",
"model_picker_enabled": true,
"name": "GPT-5-Codex (Preview)",
"object": "model",
"policy": {
"state": "enabled",
"terms": "Enable access to the latest GPT-5-Codex model from OpenAI. [Learn more about how GitHub Copilot serves GPT-5-Codex](https://gh.io/copilot-openai)."
},
"preview": true,
"supported_endpoints": [
"/responses"
],
"vendor": "OpenAI",
"version": "gpt-5-codex"
}
It uses the new API /responses which may need a specific parser too.