add glm-5 model from fireworks

[Barrett Pyke (barrettpyke)]

User would like to add the glm-5 model to the proxy list for Fireworks.

Pulled cost and max_input_tokens from:
https://fireworks.ai/models/fireworks/glm-5
https://docs.z.ai/guides/llm/glm-5


Pulled max_output_tokens from:
https://docs.z.ai/guides/llm/glm-5

[vercel]

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

Project	Deployment	Actions	Updated (UTC)
ai-proxy	Ready	Preview, Comment	Mar 31, 2026 7:05pm

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: d203661622

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]

Add endpoint mapping for new Fireworks model

This new glm-5 entry is only added to model_list.json, but getModelEndpointTypes resolves providers from AvailableEndpointTypes first and otherwise falls back to DefaultEndpointTypes by format (openai => openai/azure in schema/index.ts). Since fireworks_ai/accounts/fireworks/models/glm-5 is missing from that endpoint map, the fallback credential path in edge/index.ts (when control-plane key lookup fails/unavailable) will classify the bearer token as OpenAI instead of Fireworks and send requests to the wrong provider base URL.

Useful? React with 👍 / 👎.