9qeklajcandGitHub 9be2afd66a Merge pull request #752 from Routstr/fix/cache-fold-double-count ...

fix(usage): don't fold cache tokens into inclusive prompt_tokens

2026-09-21 16:12:09 +02:00

..

clients

fix: switch openai NOT_GIVEN to omit for openai 2.x compat

2026-04-26 22:42:39 +02:00

__init__.py

feat(systemone): add TypeSafe System One decision endpoint

2026-09-19 16:19:18 +00:00

anthropic.py

refactor(upstream): resolve a provider's own row by primary key

2026-07-01 12:53:31 +02:00

auto_topup.py

chore: trim redundant comments

2026-08-26 22:51:09 +02:00

azure.py

revert: remove unrelated repository formatting

2026-07-26 20:12:12 +02:00

base.py

fix(usage): don't fold cache tokens into inclusive prompt_tokens

2026-09-21 16:06:48 +03:00

cache_breakpoints.py

explicit cache

2026-06-13 23:40:39 +02:00

count_tokens.py

refactor: share x-cashu usage estimation and log full refunds

2026-09-08 22:05:07 +02:00

deepseek_v4_pricing_shim.py

update-pricing

2026-06-27 16:01:45 +02:00

ehbp.py

fix(ehbp): bill the routed model object, not its bare id via the alias map

2026-09-17 22:50:23 +02:00

fireworks.py

refactor(upstream): resolve a provider's own row by primary key

2026-07-01 12:53:31 +02:00

gemini_messages.py

revert: remove unrelated repository formatting

2026-07-26 20:12:12 +02:00

gemini.py

revert: remove unrelated repository formatting

2026-07-26 20:12:12 +02:00

generic.py

fix(generic): carry Venice's native cache_input price into input_cache_read

2026-09-21 16:26:01 +03:00

groq.py

revert: remove unrelated repository formatting

2026-07-26 20:12:12 +02:00

helpers.py

feat(systemone): add TypeSafe System One decision endpoint

2026-09-19 16:19:18 +00:00

litellm_routing.py

revert: remove unrelated repository formatting

2026-07-26 20:12:12 +02:00

messages_dispatch.py

feat: expose per-model reasoning effort on /v1/models

2026-09-09 13:31:19 +02:00

model_paths.py

feat: drop provider id from model paths and route them to the cheapest provider

2026-09-20 15:37:41 +02:00

ollama.py

feat: expose per-model reasoning effort on /v1/models

2026-09-09 13:31:19 +02:00

openai.py

refactor(upstream): resolve a provider's own row by primary key

2026-07-01 12:53:31 +02:00

openrouter.py

fix: address follow-up model path review

2026-07-27 23:17:13 +02:00

perplexity.py

refactor(upstream): resolve a provider's own row by primary key

2026-07-01 12:53:31 +02:00

ppqai.py

fix: address review findings on cooldowns, melt sizing, and stream finalization

2026-08-26 23:15:40 +02:00

pricing_resolver.py

fix(pricing): a rate spelled as a boolean is not a rate

2026-08-26 15:44:29 +02:00

rate_limit.py

revert: remove unrelated repository formatting

2026-07-26 20:12:12 +02:00

reasoning_effort.py

feat: expose per-model reasoning effort on /v1/models

2026-09-09 13:31:19 +02:00

request_correction.py

guard spend-shaping params from strip to prevent overcharge

2026-08-23 14:27:31 +02:00

routstr.py

revert: remove unrelated repository formatting

2026-07-26 20:12:12 +02:00

tinfoil_trailer.py

fix(ehbp): raise upstream timeout default to 600s

2026-09-20 17:28:15 +03:00

tinfoil.py

Add Tinfoil cached prompt pricing support

2026-09-17 20:10:44 +02:00

typesafe.py

refactor(typesafe): simplify catalog assembly, seed versioned ids, log fetch failures, drop session report doc

2026-09-20 15:57:55 +02:00

xai.py

revert: remove unrelated repository formatting

2026-07-26 20:12:12 +02:00