feat: add custom_pricing (standard/batch/fast) for Claude Opus 4.6/4.7/4.8 - #720
Merged
bhishmendramahala-crypto merged 1 commit intoJul 15, 2026
Merged
Conversation
bhishmendramahala-crypto
force-pushed
the
pricing-update/anthropic-multi-layer
branch
3 times, most recently
from
April 16, 2026 12:16
b213848 to
8bce4f4
Compare
Contributor
There was a problem hiding this comment.
Pull request overview
Adds a new custom_pricing structure to Anthropic model pricing to support multi-layer pricing by region and execution mode (while keeping pricing_config as a fallback for older gateway versions).
Changes:
- Introduces
custom_pricing.regions.{global,us}.execution_modesforclaude-opus-4-6(standard/batch/fast) andclaude-sonnet-4-6(standard/batch). - Adds cache token pricing entries (
cache_write_input_token,cache_read_input_token) to the top-levelbatch_configfor both models. - Adds US-region uplifted pricing (10%) and fast-mode pricing for Opus.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
bhishmendramahala-crypto
force-pushed
the
pricing-update/anthropic-multi-layer
branch
from
April 16, 2026 12:29
8bce4f4 to
2f9ccfc
Compare
narengogi
marked this pull request as draft
April 16, 2026 19:46
…7/4.8 Adds multidimensional custom_pricing under regions.default with standard, batch, and fast execution_modes for claude-opus-4-6, claude-opus-4-7, and claude-opus-4-8. Fast-mode rates per Anthropic pricing docs (Opus 4.6/4.7: $30/$150 per MTok; Opus 4.8: $10/$50 per MTok), with 5m/1h cache-write and cache-read multipliers applied. Source: https://docs.claude.com/en/docs/about-claude/pricing
bhishmendramahala-crypto
force-pushed
the
pricing-update/anthropic-multi-layer
branch
from
June 24, 2026 18:15
2f9ccfc to
685e09a
Compare
bhishmendramahala-crypto
changed the title
bhishmendramahala-crypto
marked this pull request as ready for review
June 26, 2026 06:54
Devansh0012
approved these changes
Jul 14, 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
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
Adds multidimensional
custom_pricingfor the three Claude Opus models that support Anthropic Fast mode —claude-opus-4-6,claude-opus-4-7, andclaude-opus-4-8.Structure:
custom_pricing.regions.default.execution_modes.{standard,batch,fast}.standard: mirrors basepay_as_you_go(input/output + 5m cache write, cache read, andadditional_units.cache_write_1h).batch: 50% of standard input/output rates.fast(Opus only — Fast mode):claude-opus-4-6/claude-opus-4-7: $30 / MTok input, $150 / MTok outputclaude-opus-4-8: $10 / MTok input, $50 / MTok outputregions.defaultis used (notglobal/us) because the current Anthropic pricing resolver emits only theservice_tierdimension and falls back toregions['default']when no region is provided. Theus/inference_geo1.1x data-residency tier is intentionally omitted until the resolver emits a region dimension.The existing top-level
pricing_config(pay_as_you_go+batch_config) is preserved as a fallback for older gateway versions.Source Verification
Source Links:
Checklist
Related