Qwen 3.8 27B

Qwen 3.8 27B is a Cerebras model available in Agent Serve. Qwen 3.8 27B is a Cerebras model tracked in Agent Serve. It supports a 131k token context window. Pricing starts at $0.99/1M input tokens and $1.49/1M output tokens. Key capabilities include Temperature 0-2, Tool choice, Structured outputs.

Qwen 3.8 27B starts at $0.99/1M input tokens, and $1.49/1M output tokens.

Qwen 3.8 27B supports a context window of 131k tokens in Agent Serve. In an agent, this determines how much conversation history, tool outputs, and retrieved documents the model can hold in a single call.

Qwen 3.8 27B supports the following capabilities in Agent Serve: Temperature 0-2, Tool choice, Structured outputs, Reasoning none, low, medium, high, Max output 41k.

Best for reasoning-heavy tasks that need more deliberate model control. When used in an Agent Serve workflow, it can be selected in any Agent block from the model picker.