All times Eastern (ET)Provider pages checked daily at
ProSign inRSS
Heads-upReleasesQwen

qwen-flash-character: Max output tokens 32,768 tokens → 4,096 tokens

See the change on the model page

What to doCheck max_tokens in requests to qwen-flash-character: the limit is now 4,096 tokens.
Provider
Qwen
Source
the model page on AIWire
Models
Qwen Flash Characterqwen-flash-character

All items on the wire