Remy Reference/models/Qwen3.8 Flash

Qwen3.8 Flash

Qwen3.8 Flash, a language model from Alibaba Cloud.

modelOverride: { model: "qwen-3.8-flash" }

Qwen·served via

Alibaba Cloud·Released August 2026

Pricing

Input: $0.16 / 1M
Output: $0.47 / 1M

Specifications

Context window: 1,000,000 tokens
Max output: 65,536 tokens
Released: August 2026
Model string: qwen3.8-flash
Capabilities: VisionFastLarge contextReasoning

Parameters

Model options, passed in modelOverride.config.

Parameter	Type	Default	Range / options
`enable_thinking` When enabled, the model performs an internal chain-of-thought reasoning process before producing its final answer. Improves quality on complex tasks but increases latency and token usage.	Boolean	false

Use this model

await mindstudio.generateText({
  message: "...",
  modelOverride: {
    model: "qwen-3.8-flash",
    config: {
      enable_thinking: "false",
    },
  },
});