Qwen 3.8 Flash

alibaba/qwen3.8-flash

A chat model with a 991K-token context window, at $0.1575 per million input tokens and $0.4935 per million output tokens.

Details

Maker: alibaba
Kind: Chat
Context window: 991,000 tokens
Max output: 128,000 tokens
Input: $0.1575 per million tokens
Cached input: $0.0168 per million tokens, 89% off
Cache write: $0.21 per million tokens
Output: $0.4935 per million tokens
Capabilities: Reasoning, tool use, vision, file input
Takes: Text, image, pdf
Returns: Text
Zero data retention: Yes, on every provider
No training on requests: Yes, on every provider
Released: 2026-08-26

Description

Qwen3.8-Flash is Qwen’s fast, cost-efficient multimodal model, combining advanced reasoning and generation with a native 1M-token context window. Built for coding, agentic workflows, and visual understanding, it handles large codebases, long documents, charts, videos, and desktop applications.

Call it

curl

curl https://phantom.codes/v1/chat/completions \
  -H "Authorization: Bearer $PHANTOM_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "alibaba/qwen3.8-flash",
    "messages": [
      {"role": "user", "content": "Hello"}
    ]
  }'

Set PHANTOM_KEY to your key. Any OpenAI client works with the base URL https://phantom.codes/v1.

Get a key Compare with another model