qwen-3.8-27b available on public endpoints with image input and configurable reasoning

qwen-3.8-27b is now available on Cerebras public endpoints. Qwen 3.8 27B is a 27-billion-parameter dense multimodal model for agentic coding, tool use, research, and long-running workflows.

It supports text and image inputs, configurable reasoning, streaming, structured outputs, tool calling with strict mode and parallel calls, and prompt caching. Reasoning defaults to high; set reasoning_effort to none to disable it. Image inputs use base64-encoded PNG or JPEG data URIs through Chat Completions.

See the Qwen 3.8 27B model page, Reasoning, and Image Inputs for details.