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

Qwen3.7 Plus Thinking

Qwen3.7 Plus with thinking mode enabled for deeper multimodal reasoning, coding, tool use, screen reading, and productivity workflows.

  • Reasoning
  • Vision
  • Video Input

Added Jun 1, 2026

Pricing

Auto routing · per 1M tokens
Input
$0.40
Output
$1.60
Cache read
$0.08
Compare provider prices

Specifications

Context window
983.6K
Max output
65.5K
Avg output (7d)
913 tokens
Longer than 65% of models

Benchmarks

Sourced from LMArena.

Arena Score

1455.3

Overall Rank

#72 / 421

Votes

41,318

Confidence Interval

1451.0 - 1459.7

Category Scores

Coding

#82 / 416

11,979 votes

1500.3

Math

#59 / 404

1,881 votes

1465.3

Longer Query

#72 / 399

19,105 votes

1464.8

Creative Writing

#73 / 419

7,663 votes

1431.2

Instruction Following

#72 / 421

14,755 votes

1446.8

Hard Prompts

#82 / 421

27,790 votes

1473.0

Additional Categories
22

German

#55 / 320

743 votes

1465.2

Chinese

#57 / 395

2,579 votes

1501.3

Industry Mathematical

#57 / 401

2,175 votes

1473.1

French

#58 / 301

1,592 votes

1480.0

Russian

#63 / 385

4,558 votes

1458.3

Expert

#69 / 371

4,586 votes

1485.4

Korean

#71 / 289

745 votes

1412.9

Non English

#72 / 421

23,853 votes

1443.1

Exclude Ties

#74 / 421

30,431 votes

1457.8

Industry Medicine And Healthcare

#74 / 390

2,900 votes

1472.2

Industry Software And It Services

#75 / 421

16,841 votes

1490.5

Industry Writing And Literature And Language

#75 / 420

10,627 votes

1436.2

Multi Turn

#76 / 419

6,912 votes

1464.0

Spanish

#76 / 303

1,223 votes

1448.6

English

#77 / 421

17,463 votes

1462.6

Industry Life And Physical And Social Science

#77 / 419

6,617 votes

1471.4

Japanese

#81 / 288

669 votes

1412.3

Hard Prompts English

#82 / 419

11,975 votes

1476.4

Industry Entertainment And Sports And Media

#84 / 419

9,793 votes

1418.2

Industry Business And Management And Financial Operations

#91 / 414

8,225 votes

1445.1

Industry Legal And Government

#91 / 393

3,495 votes

1455.2

Polish

#94 / 244

801 votes

1440.7

Published 2026-11-09 · Matched as Qwen3.7-Plus

LMArena Dataset

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)

Cache write /M
Auto
Auto (Anonymized)
$0.40$1.60$0.08$0.50N/AN/A
>256k$1.20$4.80$0.24$1.50
Alibaba
Alibaba
SG
$0.42$1.68$0.084$0.525N/AN/A
>256k$1.26$5.04$0.252$1.57
Privacy:No training on prompts
Batch API
ProviderInputOutputCached inputCache write
Auto
Autoqwen/qwen3.7-plus:thinking
$0.40/M$1.60/M$0.08/M$0.50/M
>256k$1.20/M$4.80/M$0.24/M$1.50/M

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 Qwen3.7 Plus Thinking with similar models from the same provider or model family.

Qwen3.7 Plus

qwen/qwen3.7-plus

Qwen3.7 Plus is Alibaba's cost-effective Qwen 3.7 multimodal agent model for coding, tool use, productivity workflows, visual understanding, screen reading, and GUI interaction.

Qwen3.5 Omni Plus

qwen/qwen3.5-omni-plus

Qwen3.5 Omni Plus is Qwen's stronger general multimodal model. We verified live support for text prompts, images, audio files, and direct video URLs on Alibaba's chat-completions-compatible API. Alibaba describes Plus as a comprehensive evolution of Qwen3 Omni with support for over 10 hours of audio input.

Qwen3.5 Plus

qwen/qwen3.5-plus

Qwen 3.5 Plus is a commercial model with hybrid linear attention and sparse MoE architecture. Supports text, image, and video input with a 1M context window.

Qwen3.5 Plus Thinking

qwen/qwen3.5-plus:thinking

Qwen 3.5 Plus with extended reasoning. A commercial model with hybrid linear attention and sparse MoE architecture. Supports text, image, and video input with a 1M context window.

DeepSeek V4 Pro Qwen3.5 9B Uncensored Heretic

xtools-at/deepseek-v4-pro-qwen3.5-9b-uncensored-heretic

xtools-at's uncensored Heretic version of Jackrong's DeepSeek V4 Pro Qwen3.5 9B, a Qwen3.5 9B model distilled from DeepSeek V4 Pro on about 250,000 math and STEM samples. It answers directly without a thinking phase. It accepts and returns text, with a 32,768-token context window shared by input and output and up to 8,192 output tokens.

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.