Skip to content

Qwen 3.5 397B A17B

by DigitalOcean · family qwen3.5 · listed Feb 2026RTVW

Qwen instruction model for multilingual chat, reasoning, and tool use

Current rates USD per 1M tokens

Input$0.302

Output$1.93

Cache read$0.111

Cache write—

Against the market

Input price vs. maker flagships ($/1M tokens)

Output price vs. maker flagships ($/1M tokens)

On the record

Model id: qwen3.5-397b-a17b
Context window: 131K tokens
Max output: 131K tokens
Input modalities: text, image, video
Output modalities: text
Reasoning: yes
Tool calls: yes
Open weights: yes
Knowledge cutoff: —
Released: 2026-02-15
Last updated: 2026-04-30
Provider docs: docs.digitalocean.com/products/gradient-ai-platform/details/models/

Back of the envelope

Input M tokensOutput M tokens

≈

Also listed at

Nvidiafree in · free out
OrcaRouter$0.172 in · $1.03 out
Merge Gateway$0.172 in · $1.03 out
SiliconFlow (China)$0.29 in · $1.74 out
Vultr$0.30 in · $2.00 out
CrofAI$0.35 in · $1.75 out
OpenRouter$0.39 in · $2.34 out
SiliconFlow$0.39 in · $2.34 out
Kilo Gateway$0.39 in · $2.34 out
Alibaba (China)$0.43 in · $2.58 out
Deep Infra$0.45 in · $3.00 out
NanoGPT$0.55 in · $3.50 out
Ofox$0.55 in · $3.50 out
Mixlayer$0.60 in · $3.60 out
Jalapeno Cloud$0.60 in · $3.60 out

← All DigitalOcean listings