Skip to content

feat(openrouter/x-ai/grok-4.3:batch): add new models [bot] - #2808

Open
models-bot[bot] wants to merge 2 commits into
mainfrom
bot/add-openrouter-x-ai-grok-4.3-batch-20260905-000751
Open

feat(openrouter/x-ai/grok-4.3:batch): add new models [bot]#2808
models-bot[bot] wants to merge 2 commits into
mainfrom
bot/add-openrouter-x-ai-grok-4.3-batch-20260905-000751

Conversation

@models-bot

@models-bot models-bot Bot commented Sep 5, 2026

Copy link
Copy Markdown
Contributor

Auto-generated by model-addition-agent for openrouter/x-ai/grok-4.3:batch.


Note

Low Risk
Adds a new provider model config only; no runtime or auth logic changes.

Overview
Adds OpenRouter catalog metadata for x-ai/grok-4.3:batch, the batch-priced variant of Grok 4.3.

The new YAML defines lower per-token costs than the standard grok-4.3 entry, the same chat capabilities (tools, JSON/structured output, prompt caching, thinking), a 1M context window with 900K max output tokens, and input modalities including text, image, and PDF.

Reviewed by Cursor Bugbot for commit 10d9def. Bugbot is set up for automated code reviews on this repo. Configure here.

@cursor cursor Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Cursor Bugbot has reviewed your changes using default effort and found 1 potential issue.

Fix All in Cursor

❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.

Reviewed by Cursor Bugbot for commit 4a1d216. Configure here.

- tool_choice
limits:
context_window: 1000000
max_output_tokens: 900000

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Missing max_tokens override

Medium Severity

This fuller entry sets limits.max_output_tokens to 900000 but does not override inherited params.max_tokens. OpenRouter default.yaml caps max_tokens.maxValue at 4096, so callers cannot request the advertised output length.

Fix in Cursor Fix in Web

Triggered by learned rule: Override max_tokens maxValue to match limits

Reviewed by Cursor Bugbot for commit 4a1d216. Configure here.

@github-actions

github-actions Bot commented Sep 5, 2026

Copy link
Copy Markdown
Contributor

/test-models

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

0 participants