Qwen3.8 27B

alibaba/qwen3.8-27b

A chat model with a 1M-token context window, at $0.525 per million input tokens and $3.15 per million output tokens.

Details

Maker: alibaba
Kind: Chat
Context window: 1,000,000 tokens
Max output: 131,072 tokens
Input: $0.525 per million tokens
Cached input: $0.105 per million tokens, 80% off
Cache write: $0.65625 per million tokens
Output: $3.15 per million tokens
Capabilities: Reasoning, tool use, vision, file input
Takes: Text, image, pdf, video
Returns: Text
Zero data retention: Not on every provider
No training on requests: Not on every provider
Released: 2026-08-14

Description

Built on the architectural foundation of Qwen3.5, Qwen3.8 delivers substantial gains across coding, professional work, research, and long-horizon agentic tasks. Qwen3.8-27B brings these advances to a compact, deployment-friendly dense model: a native vision-language model that understands images and videos, with flexible thinking control, designed to carry complex, multi-step tasks through to completion with greater reliability.

Call it

curl

curl https://phantom.codes/v1/chat/completions \
  -H "Authorization: Bearer $PHANTOM_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "alibaba/qwen3.8-27b",
    "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