Skip to content

Bake in Grok 4.6 launch pricing until catalogs catch up - #130

Merged
ItsJazii merged 3 commits into
mainfrom
grok-4-6-launch-pricing
Aug 13, 2026
Merged

Bake in Grok 4.6 launch pricing until catalogs catch up#130
ItsJazii merged 3 commits into
mainfrom
grok-4-6-launch-pricing

Conversation

@ItsJazii

@ItsJazii ItsJazii commented Aug 13, 2026

Copy link
Copy Markdown
Owner

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:

  • $2 input / $0.50 cached / $6 output per MTok
  • ≥200k-token prompts bill $4 / $1 / $12 for the whole request — xAI's long-context rule matches request_cost's whole-request tiering at the default 200k threshold Grok spend already passes
  • Cache writes bill as plain input (xAI publishes no separate write rate)
  • The launch post's 2× fast variant needs no entry: the -fast resolution path applies the default 2× multiplier to this rate card, long-context tier included
  • builtin_price also strips Cursor's cursor- branding — verified against a real launch-day CSV where cursor-grok-4.6-xhigh left 20.6M tokens at $0.00
  • grok_price backstop updated so 4.6's premium "fast" can never fall into the old cheap grok-4-fast branch (contradiction flagged by Devin on the earlier bundled PR Grok 4.6 launch pricing, Cursor slug handling, DeepSeek v4 builtins #129)
  • CORRECTIONS_REV bumped so persisted spend re-prices

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


Open in Devin Review

ItsJazii and others added 2 commits August 13, 2026 15:01
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>
devin-ai-integration[bot]

This comment was marked as resolved.

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>
@ItsJazii
ItsJazii merged commit 3a3e90a into main Aug 13, 2026
1 check passed
@ItsJazii
ItsJazii deleted the grok-4-6-launch-pricing branch August 13, 2026 10:15
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant