chore: update model catalog from bot issues

[github-actions]

Automated daily batch of model catalog updates from bot issues.

Included issues

• Closes [BOT ISSUE] Databricks: add missing databricks-glm-5-3-flash #1179: [BOT ISSUE] Databricks: add missing databricks-glm-5-3-flash
• Closes [BOT ISSUE] Fireworks: add missing accounts/fireworks/models/glm-5p3 #1180: [BOT ISSUE] Fireworks: add missing accounts/fireworks/models/glm-5p3
• Closes [BOT ISSUE] Together: add together provider to zai-org/GLM-5.3 #1182: [BOT ISSUE] Together: add together provider to zai-org/GLM-5.3
• Closes [BOT ISSUE] Fireworks: add missing accounts/fireworks/models/glm-5p3-flash #1183: [BOT ISSUE] Fireworks: add missing accounts/fireworks/models/glm-5p3-flash

Summary

Issue	Provider	Primary model	Changed models	Added models	Updated models	Verification sources
#1179	databricks	databricks-glm-5-3-flash	databricks-glm-5-3-flash	databricks-glm-5-3-flash	None	1 2
#1180	fireworks	accounts/fireworks/models/glm-5p3	accounts/fireworks/models/glm-5p3	accounts/fireworks/models/glm-5p3	None	1 2
#1182	together	zai-org/GLM-5.3	zai-org/GLM-5.3	None	zai-org/GLM-5.3	1
#1183	fireworks	accounts/fireworks/models/glm-5p3-flash	accounts/fireworks/models/glm-5p3-flash	accounts/fireworks/models/glm-5p3-flash	None	1 2

Verified metadata

#1179: [BOT ISSUE] Databricks: add missing databricks-glm-5-3-flash

Model	Display name	Parent	Providers	Format	Flavor	Token limits	Pricing	Lifecycle
databricks-glm-5-3-flash	GLM 5.3 Flash		databricks	openai	chat	input=1048576, output=131072	n/a	multimodal=true; reasoning=true

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
databricks-glm-5-3-flash	catalog entry	present	missing	None

#1180: [BOT ISSUE] Fireworks: add missing accounts/fireworks/models/glm-5p3

Model	Display name	Parent	Providers	Format	Flavor	Token limits	Pricing	Lifecycle
accounts/fireworks/models/glm-5p3	GLM 5.3		fireworks	openai	chat	input=1048576, output=131072	in/out=1.4/4.4 per 1M; cache read=0.26 per 1M	reasoning=true

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
accounts/fireworks/models/glm-5p3	catalog entry	present	missing	None

#1182: [BOT ISSUE] Together: add together provider to zai-org/GLM-5.3

Model	Display name	Parent	Providers	Format	Flavor	Token limits	Pricing	Lifecycle
zai-org/GLM-5.3	GLM 5.3		baseten, together	openai	chat	input=1048576, output=262144	in/out=1.4/4.4 per 1M; cache read=0.14 per 1M	reasoning=true

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
zai-org/GLM-5.3	catalog entry	present	missing	None

#1183: [BOT ISSUE] Fireworks: add missing accounts/fireworks/models/glm-5p3-flash

Model	Display name	Parent	Providers	Format	Flavor	Token limits	Pricing	Lifecycle
accounts/fireworks/models/glm-5p3-flash	GLM 5.3 Flash		fireworks	openai	chat	input=1048576, output=131072	in/out=0.15/0.5 per 1M; cache read=0.029 per 1M	multimodal=true; reasoning=true

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
accounts/fireworks/models/glm-5p3-flash	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	Aug 29, 2026 10:16am

[github-actions]

Codex (@codex) review

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: a16f1cd3c2

ℹ️ About Codex in GitHub

Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "Codex (@codex) review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "Codex (@codex) address that feedback".

[chatgpt-codex-connector]

Apply endpoint mappings in the active gateway

These endpoint mappings—and the Together mapping added above—modify only the deprecated proxy, so they do not make the models routable through the active production gateway. Apply the routing changes in the parent repository's gateway/ directory; only the accompanying model_list.json catalog updates belong here.

AGENTS.md reference: AGENTS.md:L10-L15

Useful? React with 👍 / 👎.