feat(openrouter/cognitivecomputations/dolphin-mistral-24b-venice-edition): add new models [bot]#1742
Conversation
…ion): add new models [bot]
|
/test-models |
Gateway test results
Skipped (4)
Skip reason
Skip reason
Skip reason
Skip reason |
…phin-mistral-24b-venice-edition-20260711-000808
|
/test-models |
There was a problem hiding this comment.
Cursor Bugbot has reviewed your changes using default effort and found 1 potential issue.
❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.
Reviewed by Cursor Bugbot for commit b49f470. Configure here.
| - json_output | ||
| limits: | ||
| context_window: 128000 | ||
| max_output_tokens: 8192 |
There was a problem hiding this comment.
Output limit conflicts defaults
Medium Severity
limits.max_output_tokens is 8192, but the file does not set limits.max_tokens or a params override for max_tokens. OpenRouter’s default.yaml still caps max_tokens at 4096, so advertised output capacity and enforced request limits can disagree.
Reviewed by Cursor Bugbot for commit b49f470. Configure here.
Gateway test results
Successes (4)
Output
Output
Output
Output |


Auto-generated by model-addition-agent for
openrouter/cognitivecomputations/dolphin-mistral-24b-venice-edition.Note
Low Risk
Declarative model metadata only; no runtime, auth, or routing logic changes.
Overview
Adds a new OpenRouter provider YAML for
cognitivecomputations/dolphin-mistral-24b-venice-edition(the paid tier), alongside the existing:freeentry.The new catalog defines per-token costs ($0.0000002 input / $0.0000009 output), a 128k context window with 8192 max output tokens, json_output, text-in/text-out chat mode, and serverless provisioning with an OpenRouter source URL.
Reviewed by Cursor Bugbot for commit b49f470. Bugbot is set up for automated code reviews on this repo. Configure here.