feat(google-gemini/gemini-omni-1.1-flash): add new models [bot] - #2466
Merged
LordGameleo merged 3 commits intoSep 1, 2026
Merged
Conversation
Contributor
|
/test-models |
![cursor[bot]](https://avatars.githubusercontent.com/in/1210556?s=60&v=4){kind=small}
There was a problem hiding this comment.
Cursor Bugbot has reviewed your changes using default effort and found 3 potential issues.
❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.
Reviewed by Cursor Bugbot for commit 4e4b49c. Configure here.
… output modalities Addresses the three Bugbot review comments on #2466, verified against Google's published docs (2026-09-01): - costs: the video output rate ($17.50/1M) was sitting in output_cost_per_token, which is the *text* output rate ($9.00/1M). Split them and add output_cost_per_video_token, matching both gemini-omni-flash-preview entries. - costs: drop output_cost_per_second_{360p,720p,1080p,4k}. Google bills Omni purely by output tokens (5,792 tokens per second of 720p video) and publishes no per-second table; those four values trace to secondhand write-ups. No other model in this repo mixes per-second with per-video-token pricing, and _360p appears nowhere else. - limits: context window is 1,048,576 (model page), not 131,072 — that figure is the Cloud/Enterprise input cap. Drop the invented max_output_tokens: 65536; no output limit is published for this model. - modalities.output: add audio and text. The model card describes output as "high-quality, high-resolution video with audio", and the pricing page bills a separate text output rate. - removeParams: add tool_choice, for parity with the sibling entry. - sources: add the model and pricing pages the figures come from. Co-Authored-By: Claude <noreply@anthropic.com>
Contributor
|
/test-models |
LordGameleo
approved these changes
Sep 1, 2026
LordGameleo
deleted the
bot/add-google-gemini-gemini-omni-1.1-flash-20260828-000553
branch
September 1, 2026 13:41
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Auto-generated by model-addition-agent for
google-gemini/gemini-omni-1.1-flash.Note
Low Risk
Adds a static provider model YAML with no runtime or auth changes; behavior is limited to catalog/metadata for routing and billing.
Overview
Registers
gemini-omni-1.1-flashundergoogle-geminias an active, serverless video model with the same token limits and pricing pattern as the existing Omni Flash preview (including per-video output token cost).The definition enables multimodal input (text, image, audio, video) and output text, audio, and video, and strips standard sampling/tool params via
removeParamsfor Omni-style API usage. Documentation source links include Google’s Omni docs and pricing/model-card URLs.Reviewed by Cursor Bugbot for commit b5ebfb3. Bugbot is set up for automated code reviews on this repo. Configure here.