feat: add custom_pricing (standard/batch/fast) for Claude Opus 4.6/4.7/4.8#720
feat: add custom_pricing (standard/batch/fast) for Claude Opus 4.6/4.7/4.8#720bhishmendramahala-crypto wants to merge 1 commit into
Conversation
bhishmendramahala-crypto
force-pushed
the
pricing-update/anthropic-multi-layer
branch
3 times, most recently
from
b213848 to
8bce4f4
Compare
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.
| "price": 0.0008250000000000001 | ||
| }, | ||
| "cache_write_input_token": { | ||
| "price": 0.00020625000000000003 |
There was a problem hiding this comment.
US-region Sonnet batch cache_write_input_token.price is 0.00020625000000000003 (float artifact). Please simplify to 0.00020625 for consistency and readability.
| "price": 0.00020625000000000003 | |
| "price": 0.00020625 |
| "request_token": { | ||
| "price": 0.0033000000000000004 | ||
| }, |
There was a problem hiding this comment.
The US fast-mode request_token price is written as 0.0033000000000000004 (float precision artifact). Please normalize this to 0.0033 (and similarly for any other uplift-derived values) for consistency and to avoid unnecessary diffs.
| "price": 0.0013750000000000001 | ||
| }, | ||
| "cache_write_input_token": { | ||
| "price": 0.00034375000000000003 | ||
| }, |
There was a problem hiding this comment.
More US-region batch prices show float precision artifacts (e.g., response_token.price is 0.0013750000000000001). Please normalize these values (e.g., 0.001375) to avoid noisy diffs and improve readability.
| "price": 0.00034375000000000003 | ||
| }, | ||
| "cache_read_input_token": { | ||
| "price": 0.000027500000000000004 |
There was a problem hiding this comment.
cache_read_input_token.price under US batch pricing is 0.000027500000000000004 (float artifact). Please simplify to 0.0000275 (or the intended exact decimal) for consistency.
| "price": 0.000027500000000000004 | |
| "price": 0.0000275 |
| "price": 0.0016500000000000002 | ||
| }, | ||
| "cache_write_input_token": { | ||
| "price": 0.00041250000000000005 |
There was a problem hiding this comment.
US-region Sonnet cache_write_input_token.price is 0.00041250000000000005 (float artifact). Please simplify to 0.0004125 (or the intended exact decimal) for consistency.
| "price": 0.00041250000000000005 | |
| "price": 0.0004125 |
| "price": 0.0027500000000000003 | ||
| }, | ||
| "cache_write_input_token": { | ||
| "price": 0.0006875000000000001 | ||
| }, |
There was a problem hiding this comment.
US-region prices contain floating-point precision artifacts (e.g., response_token.price is 0.0027500000000000003). Please normalize these numeric literals to their intended decimal forms (e.g., 0.00275) to keep the JSON readable and reduce downstream stringify/diff churn.
| "price": 0.0006875000000000001 | ||
| }, | ||
| "cache_read_input_token": { | ||
| "price": 0.00005500000000000001 |
There was a problem hiding this comment.
cache_read_input_token.price is written as 0.00005500000000000001 (float artifact). Please simplify this to the exact decimal value (e.g., 0.000055) for consistency with the rest of the file.
| "price": 0.00005500000000000001 | |
| "price": 0.000055 |
| "price": 0.000165 | ||
| }, | ||
| "response_token": { | ||
| "price": 0.0008250000000000001 |
There was a problem hiding this comment.
US-region Sonnet batch response_token.price is 0.0008250000000000001 (float artifact). Please normalize this to 0.000825 to keep numeric formatting consistent.
| "price": 0.0008250000000000001 | |
| "price": 0.000825 |
bhishmendramahala-crypto
force-pushed
the
pricing-update/anthropic-multi-layer
branch
from
8bce4f4 to
2f9ccfc
Compare
…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
2f9ccfc to
685e09a
Compare
bhishmendramahala-crypto
changed the title
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