chore(llm_config): refresh OpenRouter model pricing#642
Merged
Conversation
Pull current per-million-token prices from OpenRouter for every paid model entry in baseline.json, premium.json, and frontier.json, and sync the embedded prices in each "comment" field. baseline.json: - gpt-oss-20b: $0.05/$0.20 → $0.03/$0.14 - gemini-2.5-flash-lite-preview-09-2025: $0.30/$2.55 → $0.10/$0.40 (also corrected created date to Sep 25, 2025 and added context_window: 1048576) - gemini-2.0-flash-001: $0.075/$0.30 → $0.10/$0.40 (price hike + ~half throughput; demoted from priority 1) - gemma4-26b-a4b-it: $0.13/$0.40 → $0.06/$0.33 - qwen3-30b-a3b: output $0.29 → $0.28 premium.json: - qwen3.5-397b-a17b: $0.15/$1.00 → $0.39/$2.34 (tiered pricing dropped) frontier.json: - moonshotai-kimi-k2-5: input $0.40 → $0.44 - qwen3.5-397b-a17b: $0.15/$1.00 → $0.39/$2.34 - google-gemini-2.5-flash-lite: $0.40/$2.20 → $0.10/$0.40 OpenAI gpt-5-nano / gpt-5-mini and the Alibaba qwen-flash entries are not on OpenRouter and were left untouched in this pass. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
baseline.json,premium.json, andfrontier.json, with embedded prices in eachcommentfield updated to match.gemini-2.0-flash-001andgemini-2.5-flash-lite-preview-09-2025reprice to $0.10/$0.40;qwen3.5-397b-a17bjumps to $0.39/$2.34 (tiered pricing gone);gemini-2.5-flash-litedrops $0.40/$2.20 → $0.10/$0.40;gemma4-26b-a4b-itandgpt-oss-20bboth drop.gpt-5-nano,gpt-5-mini) and Alibaba (qwen-flash-2025-07-28) entries are not on OpenRouter and were left untouched in this pass.Test plan
pricingblock against the relevant OpenRouter model pagecommentfields match the new numbers