From 4d6b86ebe0c57426dfffd3c74c309ae32b849aef Mon Sep 17 00:00:00 2001 From: 9qeklajc Date: Thu, 1 Oct 2026 11:46:49 +0200 Subject: [PATCH] docs: clarify decisions model errors and point clients to /v1/models id --- docs/api/endpoints.md | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/docs/api/endpoints.md b/docs/api/endpoints.md index 53743643..ebd2a4b6 100644 --- a/docs/api/endpoints.md +++ b/docs/api/endpoints.md @@ -299,7 +299,10 @@ request, and settles from the response's `usage` like embeddings. **Notes:** - Only the `openai` provider serves this endpoint. A model that no OpenAI - provider on the node offers returns `400 unsupported_request`. + provider on the node offers returns `400 unsupported_request`, and a model + the node does not list at all returns `400 invalid_model`. Use the model id + from `/v1/models` (`gpt-6-luna`); the `openai/gpt-6-luna` alias resolves to + OpenRouter's copy and returns `400 unsupported_request`. - Pricing uses the node's catalog rate for the requested model. ## Images (Coming Soon)