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 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.

  • Vision
Model weights

Pricing

Auto routing · per 1M tokens
Input
$0.30
Output
$1.90
Compare provider prices

Specifications

Context window
131.1K
Max output
32.8K
Parameters
235B / 22B
Total / active
Avg output (7d)
183 tokens
Longer than 12% of models

Benchmarks

Sourced from LMArena.

Arena Score

1413.2

Overall Rank

#150 / 421

Votes

11,288

Confidence Interval

1406.6 - 1419.7

Category Scores

Coding

#139 / 416

2,308 votes

1462.8

Math

#149 / 404

696 votes

1409.3

Longer Query

#146 / 399

2,245 votes

1420.1

Creative Writing

#177 / 419

1,351 votes

1355.4

Instruction Following

#139 / 421

2,941 votes

1408.7

Hard Prompts

#140 / 421

5,695 votes

1437.9

Additional Categories
22

Industry Business And Management And Financial Operations

#109 / 414

2,223 votes

1439.9

Korean

#116 / 289

321 votes

1374.2

French

#117 / 301

261 votes

1445.2

Spanish

#120 / 303

459 votes

1417.7

Japanese

#122 / 288

170 votes

1370.1

German

#126 / 320

279 votes

1412.1

Hard Prompts English

#128 / 419

2,496 votes

1450.1

Industry Life And Physical And Social Science

#129 / 419

1,724 votes

1442.2

Polish

#130 / 244

540 votes

1404.1

Industry Legal And Government

#131 / 393

735 votes

1431.1

Multi Turn

#131 / 419

1,925 votes

1424.4

Expert

#135 / 371

594 votes

1441.5

Chinese

#138 / 395

713 votes

1453.6

Industry Software And It Services

#142 / 421

3,995 votes

1453.7

English

#145 / 421

4,915 votes

1425.6

Industry Medicine And Healthcare

#149 / 390

626 votes

1431.4

Russian

#149 / 385

881 votes

1404.1

Exclude Ties

#152 / 421

7,974 votes

1399.2

Industry Writing And Literature And Language

#153 / 420

2,346 votes

1386.4

Non English

#153 / 421

6,373 votes

1395.1

Industry Mathematical

#170 / 401

595 votes

1406.7

Industry Entertainment And Sports And Media

#175 / 419

1,883 votes

1356.9

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

LMArena Dataset

Providers

Provider information for this model’s automatic routing. These routes cannot be selected individually.

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
Recommended
$0.30$1.90N/AN/AN/A
Parasail
Parasail
US
$0.30$1.90N/AN/AN/A
Privacy:ZDR, prompts not retained
Batch API
ProviderInputOutputCached input
Auto
Autoqwen/qwen3-vl-235b-a22b-instruct
$0.30/M$1.90/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 VL 235B A22B Instruct with similar models from the same provider or model family.

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 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

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 Next 80B A3B (Instruct)

qwen/qwen3-next-80b-a3b-instruct

Based on the new Qwen3‑Next architecture (hybrid attention, highly sparse MoE, training‑stability optimizations, and multi‑token prediction), the Qwen3‑Next‑80B‑A3B‑Instruct model delivers extreme efficiency with only 3B active parameters per pass. It performs comparably to Qwen3‑235B‑A22B‑Instruct‑2507 and shows clear advantages on ultra‑long context tasks (up to 256K 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.

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.