feat: add gpt-5.2 model to openai-native provider #10024
Merged
Conversation
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
- Add gpt-5.2 model with 400k context, 128k max output tokens - Support reasoning efforts: none, low, medium, high, xhigh - Pricing: $1.75/M input, $14/M output (standard tier) - Flex tier: $0.875/M input, $7/M output - Priority tier: $3.50/M input, $28/M output - Set gpt-5.2 as the new default model - Update test to expect new default model
Contributor
Reviewing your PR now. Feedback coming up! Mention @roomote in a comment to request specific changes to this pull request or fix all unresolved issues. |
Contributor
PeterDaveHello
left a comment
There was a problem hiding this comment.
There are also gpt-5.2-pro and gpt-5.2-chat-latest should bd added ;)
Contributor
|
Though it may be duplicated, I prepared a more complete version here: #10026 |
- Add gpt-5.2-chat-latest with 128k context, 16k max output tokens - Pricing: $1.75/M input, $0.175/M cache, $14.00/M output - Optimized for conversational AI and chat use cases
Collaborator
Author
Pro does not work properly in Roo at this time due to its timeout requirements |
cte
approved these changes
Dec 11, 2025
Add tool restrictions to gpt-5.2-chat-latest for consistency with gpt-5-chat-latest and other GPT-5 model definitions.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Summary
Add OpenAI's new flagship model
gpt-5.2to the openai-native provider and set it as the new default model.Changes
gpt-5.2model definition with:none,low,medium,high,xhighgpt-5.1togpt-5.2Important
Add
gpt-5.2model to OpenAI provider, set as default, and update tests accordingly.gpt-5.2model toopenai.tswith 400,000 context window, 128,000 max output tokens, and various pricing tiers.gpt-5.1togpt-5.2inopenai.ts.openai-native.spec.tsto expectgpt-5.2as the default model.gpt-5.2model handling inopenai-native.spec.ts.This description was created by
for eb44189. You can customize this summary. It will automatically update as commits are pushed.