Add Claude Fable 5.1 to model registry - #152
Open
adambalogh wants to merge 2 commits into
Open
Conversation
Claude Fable 5.1 (Anthropic, GA 2026-09-01) supersedes Claude Fable 5 at the same sticker price. GLM-5.3 and GLM-5.3-Flash (Z.ai, released 2026-08-18 and 2026-08-26) supersede GLM-5.2 as Z.ai's flagship tier; both route directly through Z.ai's own API rather than a BytePlus ModelArk deployment endpoint, since no such endpoint has been provisioned for them yet. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01SZToNkwZzrfbKcHqEo5Ytn
adambalogh
marked this pull request as ready for review
September 3, 2026 17:59
Routing GLM-5.3 chat models directly through Z.ai's own API (rather than the BytePlus ModelArk deployment GLM-5.2 uses) isn't wanted, and there's no ModelArk endpoint provisioned for these models yet, so drop them from this change. Claude Fable 5.1 is unaffected. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01SZToNkwZzrfbKcHqEo5Ytn
adambalogh
changed the title
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Routine check for new releases from providers already integrated in the gateway. This PR adds one confirmed new release:
claude-fable-5-1. Same sticker input/output price as Fable 5 ($10/$50 per MTok); the only pricing change is a 75%-cheaper cached-read rate, which this registry doesn't model (base input/output only).GLM-5.3 / GLM-5.3-Flash— an earlier version of this PR also added these, routed directly through Z.ai's own API since no BytePlus ModelArk deployment endpoint exists for them yet. That routing path isn't wanted, so they've been dropped from this change;glm-5.2is untouched.Changes
tee_gateway/model_registry.py: addedCLAUDE_FABLE_5_1enum entry +_MODEL_LOOKUPalias.tests/test_pricing.py: resolve + cost tests.CLAUDE.md/README.md: updated the "Supported Providers" / "Supported Models" tables.Test plan
PYTHONPATH=. uv run pytest tests/test_pricing.py— 136 passeduv run ruff format --check tee_gateway/uv run ruff check tee_gateway— cleanuv run mypy tee_gateway— no issuesuv.lockuntouched (no dependency changes)Related
Companion PR in
chat-api: OpenGradient/chat-api#283🤖 Generated with Claude Code
https://claude.ai/code/session_01SZToNkwZzrfbKcHqEo5Ytn