Bake in Grok 4.6 launch pricing until catalogs catch up - #130
Merged
Conversation
Released today (2026-08-12); no public catalog carries it yet, so Grok 4.6 spend showed the unpriced warning. Rates from docs.x.ai/docs/pricing: $2 in / $0.50 cached / $6 out per MTok, doubling for >=200k-prompt requests (whole-request tiering, matching request_cost at the default 200k threshold); cache writes bill as plain input. The 2x fast variant resolves through the existing -fast multiplier path. Catalog entries outrank this the moment one ships. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
- builtin_price strips Cursor''s "cursor-" branding: the CSV logs cursor-grok-4.6-xhigh, which showed $0.00 for 20.6M real tokens until it resolved to the baked rate card. - grok_price backstop: 4.6''s "fast" is a 2x premium tier (launch post), never the old cheap grok-4-fast branch. - CORRECTIONS_REV bump so persisted spend re-prices under the new baked entry. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
A generic cursor- prefix strip let every cursor-branded slug reach the whole baked table; cursor-grok-4.6 spellings are now explicit match arms instead, so future Cursor slugs that bill at Cursor rates can never silently price off vendor rate cards. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This was referenced Aug 13, 2026
Merged
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Grok 4.6 shipped 2026-08-12; no public catalog carries it yet, so Grok 4.6 spend showed the unpriced ⚠. One change: bake in the vendor rate card until catalogs learn the model (same self-retiring pattern as kimi-k3 / qwen3.8-max — a real catalog entry outranks it the moment one ships).
Rates from docs.x.ai/docs/pricing:
request_cost's whole-request tiering at the default 200k threshold Grok spend already passes-fastresolution path applies the default 2× multiplier to this rate card, long-context tier includedbuiltin_pricealso strips Cursor'scursor-branding — verified against a real launch-day CSV wherecursor-grok-4.6-xhighleft 20.6M tokens at $0.00grok_pricebackstop updated so 4.6's premium "fast" can never fall into the old cheapgrok-4-fastbranch (contradiction flagged by Devin on the earlier bundled PR Grok 4.6 launch pricing, Cursor slug handling, DeepSeek v4 builtins #129)Split out of #129 per the one-change-per-PR rule; the DeepSeek v4 builtins follow in their own PR.
Testing
New unit test covers every observed spelling (
grok-4.6,grok-4-6,xai/-prefixed, effort suffixes,cursor-grok-4.6-xhigh) plus fast/long-context scaling. Full suite 57/57. Verified live on a real machine: the Cursor card's Grok 4.6 session now prices.🤖 Generated with Claude Code