feat(zai): update GLM-5 model specs with correct pricing and token limits

[roomote]

Related GitHub Issue

Closes: #11438

Description

This PR attempts to address Issue #11438 by updating the GLM-5 model entries in the Z.ai provider with correct specs from the official docs, as provided by contributors in the issue comments.

The previous PR #11443 had merge conflicts, so this is a fresh implementation on current main.

International (z.ai) GLM-5 changes:

• maxTokens: 16,384 -> 128,000 (128k max output per docs)
• contextWindow: 202,752 -> 200,000 (200k per docs)
• inputPrice: $0.60 -> $1.00 per 1M tokens
• outputPrice: $2.20 -> $3.20 per 1M tokens
• cacheReadsPrice: $0.11 -> $0.20 per 1M tokens

Mainland China (bigmodel.cn) GLM-5 changes:

• maxTokens: 16,384 -> 128,000
• contextWindow: 202,752 -> 200,000
• Pricing scaled proportionally using the same international/mainland ratio as GLM-4.7

Features (already correctly configured, unchanged):

• Thinking/reasoning mode: Yes (supportsReasoningEffort)
• Prompt caching: Yes
• Image support: No (text only)

Feedback and guidance are welcome.

Test Procedure

• Ran npx vitest run api/providers/__tests__/zai.spec.ts from src/ directory -- all 33 tests pass
• Full lint passed via pre-commit hooks (turbo lint, 14/14 packages)
• Full type-check passed via pre-push hooks (turbo check-types, 14/14 packages)

Pre-Submission Checklist

• Issue Linked: This PR is linked to an approved GitHub Issue (see "Related GitHub Issue" above).
• Scope: My changes are focused on the linked issue (one major feature/fix per PR).
• Self-Review: I have performed a thorough self-review of my code.
• Testing: New and/or updated tests have been added to cover my changes (if applicable).
• Documentation Impact: I have considered if my changes require documentation updates (see "Documentation Updates" section below).
• Contribution Guidelines: I have read and agree to the Contributor Guidelines.

Documentation Updates

• No documentation updates are required.

Additional Notes

The GLM-5 model entry already existed in the codebase but with placeholder values copied from GLM-4.7. This PR corrects those values using the specs provided by @damianar1984 in the issue comments, sourced from the official z.ai documentation. This replaces the conflicting PR #11443 with a clean implementation on current main.

[roomote]

Rooviewer   See task

Review complete -- no issues found. International GLM-5 pricing and token limits match the official docs. Mainland China pricing is proportionally scaled from GLM-4.7 ratios, which is consistent with the existing pattern. All 33 tests pass.

_{Mention @roomote in a comment to request specific changes to this pull request or fix all unresolved issues.}

[damianar1984]

something is wrong with this bot roomote. 2 days for such an easy adjustment and still not promoted.

[vladon]

@roomote please release this

[damianar1984]

@roomote Approved! Release it now!

[roomote]

Fixaroo   See task

No code issues to fix -- reviewer confirmed the PR is clean. Marked the PR as ready for review.

[roomote]

Rooviewer   See task

Review complete -- no issues found. International GLM-5 pricing ($1.00/$3.20/$0.20 input/output/cached) and token limits (200k context, 128k max output) match the official docs. Mainland China pricing is proportionally scaled from GLM-4.7 ratios, consistent with the existing pattern. Changeset is correct.

_{Mention @roomote in a comment to request specific changes to this pull request or fix all unresolved issues.}

[damianar1984]

@cte, @mrubens, @jr could you please approve and merge.

[uskuklanov]

could you please approve and merge.

[damianar1984]

@roomote: request reviews and merge

[roomote]

Fixaroo   See task

No code changes needed -- the review found no issues. Merging and requesting reviews from maintainers is outside my scope as a fixer agent. A maintainer will need to approve and merge this PR.