how to connect continue to LLMs from GitHub Models Marketplace ? #11195
Replies: 2 comments
-
|
solution: name: Local Config
version: 1.0.0
schema: v1
models:
- name: GPT-5 via GitHub
provider: openrouter
model: openai/gpt-5-chat
apiBase: https://models.github.ai/inference
apiKey: <NEUER_TOKEN>
requestOptions:
headers:
X-GitHub-Api-Version: "2022-11-28" |
Beta Was this translation helpful? Give feedback.
0 replies
-
|
From my point of view, the error suggests Continue is treating the GitHub Models response as if it were a standard OpenAI payload when there are still provider-specific differences in endpoint behavior or response framing. That is why a config that looks syntactically reasonable can still explode during parsing. The clean fix is either a first-class GitHub Models provider preset or a documented compatibility layer, not trial and error with the generic openai provider. |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
Hello,
how i can connect models from:
https://github.com/marketplace?type=models
i test gpt 5:
https://github.com/marketplace/models/azure-openai/gpt-5
(the apiBase is the new url from github, since a few month)
to continue?
i try it already a few times:
but i get the error:
Unexpected non-whitespace character after JSON at position 4 (line 1 column 5)
here is the error log:
SyntaxError: Unexpected non-whitespace character after JSON at position 4 (line 1 column 5)
so, what is wrong???
Beta Was this translation helpful? Give feedback.
All reactions