Add new LLM Gateway text models (gpt-5.5, grok-4-3, gemini-3.1-flash-lite, qwen3.6, MiMo v2)#1730
Merged
rekram1-node merged 5 commits intoanomalyco:devfrom May 8, 2026
Merged
Conversation
Add gemini-3.1-flash-lite, grok-4-3, gpt-5.5, gpt-5.5-pro, qwen3.6 and MiMo v2 models that exist in llmgateway.io but were missing from models.dev. Adds parent definitions for grok-4-3, gemini-3.1-flash-lite, and qwen3.6-max-preview where they did not already exist. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
# Conflicts: # providers/alibaba/models/qwen3.6-max-preview.toml # providers/llmgateway/models/qwen3.6-max-preview.toml
Apply the canonical TOML provided by the LLM Gateway team for the Qwen3.6 Max Preview and Grok 4.3 parent definitions, replacing the upstream-merged variants whose dates and pricing did not match. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
rekram1-node
reviewed
May 8, 2026
rekram1-node
reviewed
May 8, 2026
Collaborator
|
claude is breaking the models why is it editing the release dates and stuff |
…d grok-4.3" This reverts commit 70ac6fc.
# Conflicts: # providers/google/models/gemini-3.1-flash-lite.toml
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Adds 14 new model files spanning text/coding models that LLM Gateway exposes via
https://api.llmgateway.io/v1/modelsbut were missing from models.dev.New parent provider definitions (4)
providers/xai/models/grok-4-3.tomlproviders/google/models/gemini-3.1-flash-lite.tomlproviders/google-vertex/models/gemini-3.1-flash-lite.toml(extendsgoogle)providers/alibaba/models/qwen3.6-max-preview.tomlLLM Gateway extends (11)
gpt-5.5,gpt-5.5-pro→ openaigrok-4-3→ xaigemini-3.1-flash-lite→ googlemimo-v2-omni,mimo-v2-pro,mimo-v2.5,mimo-v2.5-pro→ xiaomiqwen3.6-35b-a3b,qwen3.6-max-preview,qwen3.6-plus→ alibabaPricing, context lengths, and modalities for the new parent files come from the LLM Gateway model catalog. Image and video generation models from the catalog (cogview-4, glm-image, gpt-image-2, qwen-image*, seedream-4-, veo-3.1-, etc.) were intentionally excluded — this PR only covers text models.
Test plan
bun installbun run validatepasses