[models-bot]

Auto-generated by poc-agent for provider cohere.

---

Note

Low Risk
Metadata-only provider YAML changes with no runtime or security impact.

Overview
Updates the north-small-translate-09-2026 Cohere model catalog entry to match current provider capabilities.

The YAML now advertises function calling, image input, explicit token limits (max_output_tokens / max_tokens at 16k, aligned with context window), and thinking: true, on top of existing structured output and chat/completion modes.

^{Reviewed by Cursor Bugbot for commit 7853ffa. Bugbot is set up for automated code reviews on this repo. Configure here.}

[github-actions]

SDK live feature checks

Result: failed (1/1 scenarios)

Informational — does not block merge.

Model	Pass	Fail
cohere/north-small-translate-09-2026	0	1

Failures

• cohere/north-small-translate-09-2026 setup: not found in ai-models.json (missing costs or build skip)

[cursor]

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 7853ffa. Configure here.}

[cursor]

Translate model claims image input

Medium Severity

north-small-translate-09-2026 now lists image under modalities.input, but Cohere documents North Small Translate as text-to-text only and states vision is not offered on the North platform. The gateway will advertise and accept image requests this model cannot handle.

 

^{Reviewed by Cursor Bugbot for commit 7853ffa. Configure here.}