Private AI

Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Search
 
 
 
 
All conversations

Create

Chat
Studio

Explore

Models
Pricing
AI Apps
Blog

Library

Gallery
Workspace
Usage & billing
API
Suggestions and bugs
Use cases

|

Terms

|

Privacy

|

Refunds
Usage & billing
Teams
Referrals
Presets
Settings
FAQPress & mediaBrand assetsBenchmarksNano RPCEarn crypto
  1. Models
  2. Text
  3. Qwen

Qwen3.5 397B A17B Thinking

Qwen 3.5's open-source 397B MoE model (17B active params) with hybrid linear attention and extended reasoning. Supports text and image input with a 256K context window.

  • Reasoning
  • Vision

Added Feb 16, 2026

Model weights

Pricing

Auto routing · per 1M tokens
Input
$0.39
Output
$2.34
Compare provider prices

Specifications

Context window
262.1K
Max output
65.5K
Parameters
397B / 17B
Total / active
Avg output (7d)
8.2K tokens
Longer than 99% of models

Benchmarks

No public benchmark scores for this model yet.

Providers

Choose or restrict providers with the API. Provider-selection prices include the selection markup. Provider selection guide · Pricing API (JSON, USD per 1K tokens)

Auto
Auto (ZDR)
$0.45$3.00$0.22N/AN/A
Auto
Auto (Anonymized)
$0.39$2.34N/AN/AN/A
Alibaba
Alibaba
SG
$0.41$2.46N/A1.2s51 tps
DeepInfra
DeepInfra
FP8
US
$0.472$3.15$0.2310.8s39 tps
Parasail
Parasail
FP8
US
$0.525$3.78$0.3151s47 tps
AtlasCloud
AtlasCloud
FP8
US
$0.578$3.68$0.5781.8s47.5 tps
Uomi
Uomi
GLB
$0.579$3.78N/AN/AN/A
GMICloud
GMICloud
FP8
US
$0.63$3.78N/A2.7s44.5 tps
Novita
Novita
US
$0.63$3.78N/A2s44 tps
StreamLake
StreamLake
CN
$0.63$3.78$0.1261.5s141 tps
IONOS
IONOS
EU
$0.704$4.20N/AN/AN/A
Venice
Venice
US
$0.787$4.73N/A1.9s50 tps
Privacy:ZDR, prompts not retainedNo training on promptsBest latency and throughput are highlighted.
Batch API
ProviderInputOutputCached input
Auto
Autoqwen/qwen3.5-397b-a17b:thinking
$0.39/M$2.34/MN/A

Batch rows for this model use normal routing and cost the same as standard API requests. Set provider in a row to choose a provider.

Related text models

Compare Qwen3.5 397B A17B Thinking with similar models from the same provider or model family.

Qwen3.5 397B A17B

qwen/qwen3.5-397b-a17b

Qwen 3.5's open-source 397B MoE model (17B active params) with hybrid linear attention. Supports text, image, and video input with a 256K context window.

Qwen 3.8 27B Antislop

qwen/qwen3.8-27b-antislop

Qwen 3.8 27B Antislop is a creative-writing finetune designed to reduce formulaic prose. Available capabilities include image understanding, tool calling, and optional reasoning, with context windows up to 262,144 tokens.

Qwen 3.8 27B DarkIdol

qwen/qwen3.8-27b-darkidol

Qwen 3.8 27B DarkIdol is a creative finetune served by Aoru in NVFP4 with a 262,144-token context window. It supports image understanding, tool calling, and optional reasoning.

Qwen 3.8 27B Fimi

qwen/qwen3.8-27b-fimi

Qwen 3.8 27B Fimi is a creative finetune served by Aoru in NVFP4 with a 262,144-token context window. It supports image understanding, tool calling, and optional reasoning.

Qwen 3.8 27B Kimiko

qwen/qwen3.8-27b-kimiko

Qwen 3.8 27B Kimiko is a creative finetune served by Aoru in NVFP4 with a 262,144-token context window. It supports image understanding, tool calling, and optional reasoning.

Qwen 3.8 27B Kiwen

qwen/qwen3.8-27b-kiwen

Qwen 3.8 27B Kiwen is a creative finetune served by Aoru in NVFP4 with a 262,144-token context window. It supports image understanding, tool calling, and optional reasoning.