feat(ai): add GPT-6 Sol and Luna and sync Claude pricing - #3931
Merged
Merged
Conversation
404oops
requested review from
ProgrammerIn-wonderland and
reynaldichernando
as code owners
September 22, 2026 20:47
Contributor
Coverage Report
File Coverage |
Salazareo
approved these changes
Sep 22, 2026
GPT-5.6 and later bill prompt-cache writes at 1.25x input and report them in `cache_write_tokens`, inside the input total. Both OpenAI calculators now split them out of the prompt count and meter them under their own key, and the six GPT-5.6+ models carry the rate. GPT-6, GPT-5.6, GPT-5.5 and GPT-5.4 (incl. Pro) bill a request with more than 272K input tokens at 2x input (cached reads and cache writes included) and 1.5x output for the whole request. Models declare this as `long_context_pricing`, and the ledger overrides, the reported `usd_cents` and the credit gate all apply the multipliers. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
The catalog carried GPT-5.5's $5/$0.50/$30, but OpenAI bills GPT-5.6 Sol at $4/$0.40/$20 per million input/cached/output tokens, promotional through at least 2026-11-21. PUT-1943 tracks re-checking before then. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
reynaldichernando
approved these changes
Sep 23, 2026
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
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds GPT-6 Sol and GPT-6 Luna to both OpenAI chat providers with their aliases, pricing, context windows, output limits, and release metadata. GPT-6 Responses requests now map reasoning and verbosity options into the upstream API's nested fields, including when a namespaced alias is used.
Corrects Claude Sonnet 5 to its published $2/$10 per million input/output token pricing and 128K output limit, uses its required adaptive thinking mode, and corrects Opus 5.5 cache reads to $0.20 per million tokens. Existing versioned model IDs and default models are preserved; no SDK signatures change.
OpenAI usage now bills prompt-cache writes at 1.25x input on GPT-5.6 and later, split out of
input_tokens_details.cache_write_tokens/prompt_tokens_details.cache_write_tokens. GPT-6, GPT-5.6, GPT-5.5 and GPT-5.4 (including Pro) declarelong_context_pricing: a request with more than 272K input tokens is billed at 2x input (cached reads and cache writes included) and 1.5x output for the whole request. The metering overrides, the reportedusd_cents, and the credit gate all apply the multipliers.GPT-5.6 Sol moves from GPT-5.5's $5/$0.50/$30 to OpenAI's promotional $4/$0.40/$20 per million input/cached/output tokens. OpenAI guarantees this price only through November 21, 2026. PUT-1943 tracks re-checking it, with an SLA of November 20, 2026.
Validation:
npm run typecheckpasses with no new errors.no-explicit-anywarnings remain.git diff --checkpasses.Specifications verified against official documentation: OpenAI pricing, OpenAI prompt caching, GPT-5.6 Sol, GPT-6 Sol, GPT-6 Luna, Claude pricing, and Sonnet 5.