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 122B A10B

Qwen3.5 122B A10B is a large open Qwen 3.5 MoE model served through Gerra with tool calling and structured output support.

  • Tool Calling
  • Structured Output

Added Feb 24, 2026

Model weights

Pricing

Auto routing · per 1M tokens
Input
$0.26
Output
$2.08
Compare provider prices

Specifications

Context window
131.1K
Max output
32.8K
Parameters
122B / 10B
Total / active
Avg output (7d)
127 tokens
Longer than 6% of models

Benchmarks

Sourced from LMArena.

Arena Score

1416.3

Overall Rank

#140 / 421

Votes

29,496

Confidence Interval

1412.0 - 1420.6

Category Scores

Coding

#148 / 416

8,117 votes

1458.2

Math

#120 / 404

1,824 votes

1424.9

Longer Query

#151 / 399

11,622 votes

1417.7

Creative Writing

#165 / 419

4,472 votes

1365.1

Instruction Following

#142 / 421

9,486 votes

1405.6

Hard Prompts

#148 / 421

18,636 votes

1432.5

Additional Categories
22

French

#110 / 301

914 votes

1448.6

German

#118 / 320

424 votes

1419.2

Spanish

#119 / 303

961 votes

1418.0

Industry Business And Management And Financial Operations

#128 / 414

5,705 votes

1421.9

Industry Mathematical

#128 / 401

1,700 votes

1429.8

Chinese

#129 / 395

2,098 votes

1457.3

Expert

#134 / 371

2,691 votes

1441.6

Japanese

#134 / 288

253 votes

1358.3

English

#135 / 421

13,046 votes

1430.5

Industry Life And Physical And Social Science

#138 / 419

4,863 votes

1436.1

Multi Turn

#140 / 419

5,181 votes

1419.4

Hard Prompts English

#141 / 419

8,583 votes

1444.0

Exclude Ties

#142 / 421

21,594 votes

1403.4

Industry Legal And Government

#142 / 393

2,322 votes

1423.8

Korean

#147 / 289

470 votes

1347.9

Industry Software And It Services

#148 / 421

11,607 votes

1449.4

Industry Writing And Literature And Language

#151 / 420

6,745 votes

1387.0

Non English

#151 / 421

16,450 votes

1396.7

Polish

#152 / 244

600 votes

1386.2

Industry Medicine And Healthcare

#153 / 390

2,169 votes

1429.1

Russian

#158 / 385

3,456 votes

1398.5

Industry Entertainment And Sports And Media

#167 / 419

5,693 votes

1365.0

Published 2026-11-09 · Matched as Qwen3.5-122B-A10B

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)

Auto
Auto (ZDR)
$0.40$3.20N/AN/AN/A
Auto
Auto (Anonymized)
$0.26$2.08N/AN/AN/A
SiliconFlow
SiliconFlow
FP8
SG
$0.273$2.18N/A1.1s40 tps
AtlasCloud
AtlasCloud
FP8
US
$0.315$2.52$0.3151.4s63 tps
Alibaba
Alibaba
SG
$0.42$3.36N/A0.5s122 tps
Novita
Novita
BF16
US
$0.42$3.36N/A1.4s60 tps
Privacy:ZDR, prompts not retainedNo training on promptsRetention and training unclearBest latency and throughput are highlighted.
Batch API
ProviderInputOutputCached input
Auto
Autoqwen/qwen3.5-122b-a10b
$0.26/M$2.08/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 122B A10B with similar models from the same provider or model family.

Qwen3.5 122B A10B Thinking

qwen/qwen3.5-122b-a10b:thinking

Qwen3.5 122B A10B with extended reasoning enabled, served through Gerra with tool calling and structured output support.

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.

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.