Refresh OpenCode model pricing and endpoint routing - #46
Merged
Merged
Conversation
Correct the offline DeepSeek V4 Flash rate to the published Go price and route every Grok and Qwen model id to its family endpoint, so new ids stay correctly routed when models.dev omits a package name.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
deepseek-v4-flashfrom $0.22 / $0.007 / $0.66 to the current models.devopencode-gorate of $0.15 / $0.003 / $0.60. Live discovery still wins whenever it reports a cost.grok*andqwen*families. Every live model of both families is served as responses or messages, and models.dev omits thenpmpackage name for some of them (qwen3.8-max), which previously was the only routing signal. Zenminimaxstays on chat completions on purpose.No new supplemental metadata entries were needed: the authenticated ids missing from models.dev were already mirrored, and ids with no upstream data stay unenriched rather than guessed.
Test plan
npm testqwen3.8-maxandgrok-4.7and confirm the native endpoint shape