Qwen3.5 397B A17B
qwen3.5-397b-a17bThe Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers... Built by Qwen.
Prices updated
Input price
$0.45
per 1M tokens · Standard
Output price
$3.00
per 1M tokens · Standard
Input limit
262K
tokens
Output limit
82K
tokens
Input formats
Output formats
Qwen3.5 397B A17B price history
4 price records since 9/25/2026 · 2 changes
Qwen3.5 397B A17B cost calculator
$24/month
Standard pricing
Overview
What is Qwen3.5 397B A17B?
Qwen3.5 397B A17B is a text & reasoning and vision model from Qwen. The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers... Its 262K context window and $0.45 input price make it a candidate for quality-focused production applications.
Benchmarks
Qwen3.5 397B A17B benchmarks & speed
How Qwen3.5 397B A17B scores on standardized evaluations, and where it lands among every model we track.
18.4
Intelligence Index
86tok/s
Output speed
1183
DesignArena Elo
Reasoning
GPQA Diamond
89.3%
Graduate-level scientific reasoning · top 30%
HLE
29.0%
Humanity's Last Exam · top 38%
Coding
SciCode
44.8%
Python for scientific computing · top 71%
Latency & design
- Time to first token
- 2.26s
- DesignArena win rate
- 52.6%
- Design battles judged
- 8,130
Independent scores from Artificial Analysis and DesignArena · updated 10/8/2026. Higher is better; ranks compare against every model we track with that score.
Rates
Qwen3.5 397B A17B pricing
Pricing is based on token usage. Provider-specific caching, batch, regional, and tool charges may affect the final cost.
Input · Standard
$0.45
Per 1M tokens
Cached input · Standard
$0.22
Per 1M tokens
Capabilities
Qwen3.5 397B A17B Tools
Tools available when using Qwen3.5 397B A17B through supported provider APIs.
Function calling
Supported
Structured outputs
Supported
JSON mode
Supported
Reasoning
Supported
Built-in web search
Not supported
Log probabilities
Supported
Deterministic seed
Supported
Parallel tool calls
Not supported
Prompt caching
Supported
Strengths and limitations
Strengths
- Measured results (AA Intelligence 18.4 · DesignArena Elo 1183) position it for demanding production work.
- 262K context supports large documents, repositories and extended conversations.
- Supports text & reasoning and vision workloads in one model.
Limitations
- Generated tokens cost 7× more than input tokens, which matters for verbose responses.
- Large context capacity does not guarantee consistent retrieval across the entire prompt.
- Arena Elo and MMLU-Pro are directional; test accuracy, latency and reliability on your own workload before committing.
Arena Elo, MMLU-Pro and pricing figures are illustrative; validate current vendor terms before purchase.
Same provider