Skip to content

Lite guides: GLM's OpenAI-compatible address, usable from 2026.10.5 - #63

Merged
fylorn merged 1 commit into
mainfrom
glm-openai-address
Oct 5, 2026
Merged

fylorn merged 1 commit into
mainfrom
glm-openai-address

Conversation

@fylorn

@fylorn fylorn commented Oct 5, 2026

Copy link
Copy Markdown
Contributor

ThinkWatch Lite 2026.10.5 (core 0.62.0, ThinkWatch-Core#288) no longer appends `/v1` to a base URL that ends with its own version. The Claude Code guide now gives GLM's OpenAI-compatible addresses next to the Anthropic one it recommends; the Codex guide uses GLM as its Chat Completions example, including the separate Coding Plan endpoint `…/api/coding/paas/v4` (per Z.ai's docs, the general and Coding Plan endpoints are not interchangeable).

🤖 Generated with Claude Code

ThinkWatch Lite 2026.10.5 (core 0.62.0) no longer appends /v1 to a base
URL that ends with its own version. The Claude Code guide now gives GLM's
OpenAI-compatible addresses next to the Anthropic one it recommends, and
the Codex guide gives GLM as its example of a Chat Completions relay,
including the separate Coding Plan endpoint (…/api/coding/paas/v4).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
@fylorn
fylorn merged commit 5bc130e into main Oct 5, 2026
1 check passed
@fylorn
fylorn deleted the glm-openai-address branch October 5, 2026 05:57
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.

1 participant