mirror of
https://github.com/BerriAI/litellm.git
synced 2026-10-10 03:28:53 +00:00
feat(moonshot): add kimi-k2.6 model with supports_reasoning
Fixes #26156: Moonshot kimi-k2.6 was missing from the model pricing file, causing supports_reasoning() to return False. This prevented fill_reasoning_content() from being called in multi-turn tool calling flows, which caused the Moonshot API to return 400 errors due to missing reasoning_content in assistant messages. kimi-k2.6 has thinking/reasoning enabled by default, like kimi-k2.5. Pricing is modeled after kimi-k2.5 (to be verified with official docs).
This commit is contained in:
parent
26fcbc93e5
commit
d408f864d1
1 changed files with 38548 additions and 38532 deletions
File diff suppressed because it is too large
Load diff
Loading…
Add table
Reference in a new issue