Skip to content

feat(llmgateway): add MiniMax M3 and Qwen3.7 Plus#2053

Open
smakosh wants to merge 3 commits into
anomalyco:devfrom
smakosh:add-llmgateway-minimax-m3-qwen37-plus
Open

feat(llmgateway): add MiniMax M3 and Qwen3.7 Plus#2053
smakosh wants to merge 3 commits into
anomalyco:devfrom
smakosh:add-llmgateway-minimax-m3-qwen37-plus

Conversation

@smakosh
Copy link
Copy Markdown
Contributor

@smakosh smakosh commented Jun 7, 2026

Adds two new text models from the LLM Gateway catalog, following the existing [extends] convention — each llmgateway entry extends a canonical provider model.

Models

Model Provider canonical Context Output Input $/1M Output $/1M
minimax-m3 minimax/MiniMax-M3 1,048,576 131,072 0.60 2.40
qwen3.7-plus alibaba/qwen3.7-plus 1,000,000 65,536 0.40 1.60

Both support text + image input, reasoning, tool calling, and temperature. Pricing and context length come directly from the LLM Gateway API; output-token limits and modalities follow the established sibling entries (minimax/MiniMax-M2.7, alibaba/qwen3.6-plus, alibaba/qwen3.7-max).

Files

  • providers/minimax/models/MiniMax-M3.toml (canonical)
  • providers/alibaba/models/qwen3.7-plus.toml (canonical)
  • providers/llmgateway/models/minimax-m3.toml (extends)
  • providers/llmgateway/models/qwen3.7-plus.toml (extends)

bun validate passes.

🤖 Generated with Claude Code

smakosh and others added 2 commits June 7, 2026 18:20
Add two new text models from the LLM Gateway catalog
(https://api.llmgateway.io/v1/models), each as an llmgateway entry
extending a canonical provider model:

- minimax-m3 -> minimax/MiniMax-M3
- qwen3.7-plus -> alibaba/qwen3.7-plus

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
…ax-m3-qwen37-plus

# Conflicts:
#	providers/alibaba/models/qwen3.7-plus.toml
#	providers/minimax/models/MiniMax-M3.toml
@@ -1,31 +1,23 @@
name = "Qwen3.7 Plus"
Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

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

use base_model syntax.

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

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

Yep, on it

…7 Plus

Upstream renamed the inheritance keyword from [extends].from to
base_model. Switch both new llmgateway entries to base_model so they
inherit the shared canonical metadata and only override llmgateway cost.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@smakosh smakosh requested a review from rekram1-node June 7, 2026 17:56
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.

2 participants