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 VL 235B A22B Thinking

Qwen3 Vision‑Language model built on a 235B MoE backbone (≈22B active per token). Strong at OCR, charts/tables, multi‑image reasoning, and complex document understanding. The Thinking variant enables long‑form, chain‑of‑thought style reasoning.

  • Reasoning
  • Vision

Added Aug 26, 2025

Pricing

Auto routing · per 1M tokens
Input
$0.50
Output
$6.00
Compare provider prices

Specifications

Context window
N/A
Max output
32.8K
Parameters
235B / 22B
Total / active

Benchmarks

Sourced from LMArena.

Arena Score

1394.7

Overall Rank

#173 / 421

Votes

7,835

Confidence Interval

1387.8 - 1401.5

Category Scores

Coding

#160 / 416

1,635 votes

1452.1

Math

#165 / 404

422 votes

1398.2

Longer Query

#171 / 399

1,767 votes

1403.8

Creative Writing

#196 / 419

1,014 votes

1338.1

Instruction Following

#177 / 421

2,152 votes

1382.1

Hard Prompts

#174 / 421

4,035 votes

1417.6

Additional Categories
20

German

#121 / 320

178 votes

1417.7

Industry Mathematical

#132 / 401

383 votes

1428.8

Korean

#137 / 289

231 votes

1355.0

Expert

#138 / 371

411 votes

1440.6

Spanish

#152 / 303

380 votes

1401.1

Industry Legal And Government

#166 / 393

493 votes

1404.8

Industry Software And It Services

#167 / 421

2,781 votes

1435.6

Industry Entertainment And Sports And Media

#169 / 419

1,437 votes

1361.4

Industry Medicine And Healthcare

#169 / 390

437 votes

1415.1

Non English

#171 / 421

4,354 votes

1379.7

Chinese

#172 / 395

442 votes

1424.1

Russian

#172 / 385

615 votes

1385.5

Industry Business And Management And Financial Operations

#175 / 414

1,566 votes

1393.2

Polish

#175 / 244

398 votes

1364.6

Exclude Ties

#177 / 421

5,520 votes

1371.5

Industry Life And Physical And Social Science

#179 / 419

1,235 votes

1407.6

English

#183 / 421

3,481 votes

1403.4

Industry Writing And Literature And Language

#184 / 420

1,744 votes

1364.6

Hard Prompts English

#187 / 419

1,827 votes

1418.7

Multi Turn

#191 / 419

1,254 votes

1384.6

Published 2026-11-09 · Matched as Qwen3-VL-235B-A22B-Thinking

LMArena Dataset

Providers

Auto routing is available for this model. Explicit provider selection is not available.

Auto
Auto
Recommended
$0.50$6.00N/AN/AN/A
Batch API
ProviderInputOutputCached input
Auto
Autoqwen/qwen3-vl-235b-a22b-thinking
$0.50/M$6.00/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.

Reliability

Related text models

Compare Qwen3 VL 235B A22B Thinking with similar models from the same provider or model family.

Qwen3 VL 235B A22B Instruct Original

qwen3-vl-235b-a22b-instruct-original

Routed across multiple providers, which may include Alibaba, a Chinese entity; provider-specific privacy and logging guarantees may vary. Qwen3 Vision‑Language model (235B MoE, ≈22B active) tuned for instruction following and grounded visual QA. Excels at image understanding, dense OCR, charts and diagrams, and multi‑image context. Use this variant when you want concise, direct answers grounded in the visuals.

Qwen 3 235b A22B 2507 Thinking

qwen/qwen3-235b-a22b-thinking-2507

The thinking version of Qwen 3 235b A22B 2507, with enhanced reasoning capabilities and step-by-step problem solving.

Qwen 3 235b A22B 2507

qwen/qwen3-235b-a22b-instruct-2507

Qwen 3 235b A22B Instruct 2507 the updated version of Qwen3 235B A22B, with significant improvements in performance. This model is non-thinking.

Qwen 3 235b A22B

qwen/qwen3-235b-a22b

Qwen 3 235b is a 235b model with 22B active parameters. Supports switching between thinking and non thinking: trigger thinking with /think and /no_think anywhere in a prompt or system message to toggle chain-of-thought reasoning.

Qwen3 VL 235B A22B Instruct

qwen/qwen3-vl-235b-a22b-instruct

Routed across multiple providers, which may include Alibaba, a Chinese entity; provider-specific privacy and logging guarantees may vary. Qwen3 Vision‑Language model (235B MoE, ≈22B active) tuned for instruction following and grounded visual QA. Excels at image understanding, dense OCR, charts/diagrams, and multi‑image context.

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.