Repository navigation
Add GPT-6.1 Terra to the model registry - #184
Draft
adambalogh wants to merge 8 commits into
Draft
adambalogh wants to merge 8 commits into
adambalogh wants to merge 8 commits into
Conversation
* wavespeed qwen 3.0 pro * disable prompt expansion
…#175) Claude-Session: https://claude.ai/code/session_01P5F3RE1C4HEEkC9QoN81d1 Co-authored-by: Claude <noreply@anthropic.com>
* deepseek provider updates * price update * cleanup
Claude-Session: https://claude.ai/code/session_01Vox7ji4vqJRTqof1wjfHjV Co-authored-by: Claude <noreply@anthropic.com>
* Price Gemini 4 Argon at the standard $4/$20 rate, not the introductory rate Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01QPvRPRRbVVpzmR3kr13Yd3 * Restore unrelated cost assertions Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01QPvRPRRbVVpzmR3kr13Yd3 * Restore opus 5.5 cost assertion Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01QPvRPRRbVVpzmR3kr13Yd3 --------- Co-authored-by: Claude <noreply@anthropic.com>
Gemini 4 Argon is registered with supports_temperature=False, so the backend passed temperature=None. Every other langchain-<provider> package reads None as "omit the field", but langchain-google-genai types temperature as a plain float and rejects None at construction, so each Argon request died with a pydantic ValidationError (HTTP 500) before reaching Google. Construct the Google model without temperature and clear it afterwards; a None temperature is dropped from the GenerationConfig, so the request carries no temperature, as the flag intends. The existing registry-wide TestTemperatureOmission test already failed on this; added an Argon case that also checks the outgoing generation config. Claude-Session: https://claude.ai/code/session_01PPgg6GMvTUcvZaEXu9JfQZ Co-authored-by: Claude <noreply@anthropic.com>
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01SQvDLzzfdqUV8jEEcNJzrP
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
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
gpt-6.1-terra(OpenAI, released 2026-10-26) with aliasesgpt-6.1-terra/gpt-6-1-terra.supports_temperature=False(launch docs list no parameter restrictions; this mirrors the sibling).gpt-5.6-terrastays registered so existing callers resolve.Stacking
This PR is stacked on #173 (GPT-6.1 Sol) so the two don't overlap; it also merges current
mainto resolve doc-table conflicts. Retarget tomainonce #173 lands.Companion chat-api PR: https://github.com/OpenGradient/chat-api/pull/447
Test plan
python -m unittest tests.test_pricing(172 tests OK)🤖 Generated with Claude Code
https://claude.ai/code/session_01SQvDLzzfdqUV8jEEcNJzrP