fix: add Together models Qwen/Qwen3.6-Plus +2 more

[github-actions]

fix: add Together models Qwen/Qwen3.6-Plus +2 more

Closes #520

Source issue: #520

Summary

Field	Value
Provider	together
Primary model	Qwen/Qwen3.6-Plus
Changed models	Qwen/Qwen3.6-Plus zai-org/GLM-5.1 MiniMaxAI/MiniMax-M2.7
Added models	Qwen/Qwen3.6-Plus zai-org/GLM-5.1 MiniMaxAI/MiniMax-M2.7
Updated models	None
Verification sources	1 2

Verified metadata

Model	Display name	Parent	Providers	Format	Flavor	Token limits	Pricing	Lifecycle
Qwen/Qwen3.6-Plus	Qwen3.6 Plus		together	openai	chat	input=1000000, output=not provided	in/out=0.5/3 per 1M	active
zai-org/GLM-5.1	GLM 5.1		together	openai	chat	input=202752, output=128000	in/out=1.4/4.4 per 1M	reasoning=true
MiniMaxAI/MiniMax-M2.7	MiniMax M2.7		together	openai	chat	input=202752, output=not provided	in/out=0.3/1.2 per 1M; cache read=0.06 per 1M	active

Verification notes

No LLM verification step ran — model metadata was already complete in the issue.

sync_models vs proposed update

sync_models cross-check found differences. Official provider verification was used for the applied values, and sync_models discrepancies are listed below for review.

Model	Field	Proposed update	sync_models	sync_models source models
Qwen/Qwen3.6-Plus	catalog entry	present	missing	None
zai-org/GLM-5.1	catalog entry	present	missing	None
MiniMaxAI/MiniMax-M2.7	catalog entry	present	missing	None

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Actions	Updated (UTC)
ai-proxy	Ready	Preview, Comment	May 6, 2026 1:57am

[github-actions]

Proxy model verification

Verification completed successfully.

Passed: 3
Failed: 0

Tested models

• Qwen/Qwen3.6-Plus
• zai-org/GLM-5.1
• MiniMaxAI/MiniMax-M2.7

Passed models

• Qwen/Qwen3.6-Plus
• zai-org/GLM-5.1
• MiniMaxAI/MiniMax-M2.7

Failed models

• None