product · inferred from evidence
gpt-oss-120b
A reasoning model by Cerebras that uses a separate reasoning key for reasoning tokens.
- Cerebras reasoning model returns reasoning in content key instead of reasoning key
I am using qwen-3-235b-a22b-thinking-2507 with the async Cerebras client and streaming. The reasoning tokens show up in the content key of each chunk instead of a reasoning key. Is this a bug?