docs: paid-catalog refresh — 3 new models, DeepSeek reprice, corrected GPT-5.6 Pro prices - #69
Merged
Merged
Conversation
added 2 commits
August 30, 2026 23:28
… Pro prices corrected Three additions, all probe-verified including image input. Plus the two SKUs whose stale catalog price made them unroutable: OpenAI moved gpt-5.6-terra-pro to $2/$12 and gpt-5.6-luna-pro to $0.20/$1.20. Counts: 73 -> 76 chat, 97 -> 100 total.
… the provider tables DeepSeek raised V4 Pro to $1.32/$3.96 (peak; off-peak is half), so the catalog price moved with it — and because ClawRouter's auto profile is priced on that model, the published savings figure moves 88% -> 84% everywhere it appears, including the worked example.
VickyXAI
added a commit
that referenced
this pull request
Aug 31, 2026
…nd both GPT-5.6 Pro corrections (#70) #69 moved deepseek-v4-pro to $1.32/$3.96 and corrected gpt-5.6-terra-pro / gpt-5.6-luna-pro across api-reference/models.md and intelligence/overview.md. It missed products/intelligence/pricing.md, which is the page a buyer actually reads, so blockrun.ai/docs/products/intelligence/pricing has been quoting: DeepSeek V4 Pro $0.43/$0.87 real $1.32/$3.96 (3.1x in, 4.6x out) GPT-5.6 Terra Pro $1.00/$6.00 real $2.00/$12.00 (2x) GPT-5.6 Luna Pro $0.10/$0.60 real $0.20/$1.20 (2x) The two Pro rows are the same SKUs whose stale catalog price made them unroutable in the gateway's #449 — the catalog was fixed, this sheet was not. Also adds the two DeepSeek SKUs the table never listed (V4 Flash Reasoner, V4 Flash Vision) and fixes the routing example in products/routing/clawrouter.md, which still showed v4-pro at $0.87 output while the worked example three sections below already used $3.96. Every priced row in the sheet now round-trips against the gateway catalog; the gateway repo gains a test that asserts it on every run. Co-authored-by: 1bcMax <viewitter@gmail.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.
Docs half of the paid-catalog refresh.
qwen/qwen3.8-flash,deepseek/deepseek-v4-flash-vision-exp,xiaomi/mimo-v2.5to the model tables and provider rows.gpt-5.6-terra-pro$1/$6 → $2/$12 andgpt-5.6-luna-pro$0.10/$0.60 → $0.20/$1.20 — OpenAI repriced upstream, and the stale numbers made both SKUs unroutable rather than merely mispriced.deepseek/deepseek-v4-pro$0.435/$0.87 → $1.32/$3.96 — DeepSeek's published rate moved (peak; off-peak is half). ClawRouter's auto profile is costed on that model, so the published savings figure moves 88% → 84% everywhere it appears, worked example included.Counts: 73 → 76 chat, 97 → 100 total. Dated changelog entries keep their original numbers.