fix(model-catalog): correct qwen3.5-flash, qwen3.5-plus, qwen3-max entries#899
Closed
dvrd wants to merge 2 commits intoRightNow-AI:mainfrom
Closed
fix(model-catalog): correct qwen3.5-flash, qwen3.5-plus, qwen3-max entries#899dvrd wants to merge 2 commits intoRightNow-AI:mainfrom
dvrd wants to merge 2 commits intoRightNow-AI:mainfrom
Conversation
…tries - qwen3.5-flash: output_cost 2.00→0.60, context_window 991K→1M, remove self-alias, supports_vision true→false, max_output_tokens 64K→8192 - qwen3.5-plus: output_cost 4.80→3.20, context_window 991K→1M, supports_vision true→false, max_output_tokens 64K→8192 - qwen3-max: tier Frontier (not Smart), context_window 1M (not 252K or 131K), supports_vision false, max_output_tokens 64K→8192 - test_catalog_has_providers: replace brittle hardcoded count (41) with named-provider assertions
Author
|
Closing — submitting against our fork instead. |
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Fixes 11 data errors in the three new Qwen model entries added in #879:
output_cost_per_m2.00→0.60 (3.3× overcharge),context_window991K→1M, removed self-alias,supports_visiontrue→false,max_output_tokens64K→8192output_cost_per_m4.80→3.20 (published Alibaba rate),context_window991K→1M,supports_visiontrue→false,max_output_tokens64K→8192tierSmart→Frontier (it's Alibaba's top-tier managed endpoint),context_window252K→1M,supports_visiontrue→false,max_output_tokens64K→8192== 41) with named-provider checksAll three models are text-only (vision belongs to the separate
qwen3.5-vlfamily).max_output_tokens: 64_000does not appear in Alibaba Cloud docs for any of these models — all Qwen models in the catalog use 8_192.Test plan
cargo test -p openfang-runtime— 846 passed, 0 failedcargo build --workspace --lib— clean build