Qwen3.8 27B
Qwen3.8 27B scores 20.1 on the Artificial Analysis Intelligence Index (#44 of 65 ranked models) and costs $0.06 per million input tokens and $2.20 per million output tokens. Qwen3.8 27B is an AI model from Qwen, released on Aug 14, 2026.
Intelligence
20.1
#44 of 65
Usage
—
Outside the top 20
Reading price
$0.06
for the text you give it, per 1M tokens (about 750,000 words)
Writing price
$2.20
for the text it writes, per 1M tokens (about 750,000 words)
Reads at once
~1,600 pages
how much text it keeps in mind (1,024,000 tokens)
Speed
446 per second
word pieces written; starts after 0.2s
How Qwen3.8 27B compares
| # | Model | Intelligence | Reading price | Writing price |
|---|---|---|---|---|
| 42 | DeepSeek V4 Pro 0813 · DeepSeek | 23.1 | $0.11 | $4.44 |
| 43 | DeepSeek V4 Pro 0423 · DeepSeek | 20.8 | $0.90 | $1.50 |
| 44 | Qwen3.8 27B · Qwen | 20.1 | $0.06 | $2.20 |
| 45 | MiniMax M3 · MiniMax | 18.9 | $0.30 | $1.20 |
| 46 | Beam 1.0 501B A23B · Reflection | 17.7 | $0.30 | $1.00 |
Price and score history
Nov 17, 2026Nov 19, 2026
Nov 17, 2026Nov 19, 2026
See all 376 models View on OpenRouter ↗
Updated Nov 19, 2026. Prices and usage: OpenRouter. Intelligence: Artificial Analysis Intelligence Index. Always confirm the price with the provider before you build on it.