Chase Xu 993a4c1f5b fix: remove double-counting of reasoning_tokens in OpenAI usage ...

OpenAI's completion_tokens already includes reasoning_tokens as a subset,
so adding them again was incorrectly inflating token counts by ~2x for
all reasoning models (o1, o3, o4-mini, etc.).

This aligns with other OpenAI-compatible providers (OpenRouter, Vercel,
Cerebras, Groq) which use completion_tokens directly.

Note: This is different from Google Gemini where thinking_tokens ARE
reported separately and need to be added.

Fixes #4065

2026-02-10 05:32:13 -06:00

..

chat.py

fix: remove double-counting of reasoning_tokens in OpenAI usage

2026-02-10 05:32:13 -06:00

like.py

removed confusing docstrings

2025-06-24 14:13:41 +02:00

responses_serializer.py

feat: add support for openai responses model

2025-12-22 22:16:56 -08:00

serializer.py

bump openai and fix new types for tool calling

2025-08-07 19:53:05 +01:00