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. All models overview
  2. Text
  3. Z.AI

GLM 4.6 Turbo

Fast variant of GLM 4.6 for general chat, coding, and analysis with improved latency and strong reasoning.

Added Oct 2, 2025

Pricing

Auto routing · per 1M tokens
Input
$0.55
Output
$2.20
Cache read
$0.11
Compare provider prices

Specifications

Context window
200K
Max output
204.8K
Parameters
357B / 32B
Total / active

Benchmarks

Sourced from LMArena.

Arena Score

1424.4

Overall Rank

#128 / 422

Votes

35,641

Confidence Interval

1420.5 - 1428.3

Category Scores

Coding

#150 / 417

7,572 votes

1458.2

Math

#134 / 405

2,135 votes

1417.4

Longer Query

#131 / 400

9,076 votes

1431.6

Creative Writing

#111 / 420

5,091 votes

1400.9

Instruction Following

#133 / 422

10,217 votes

1412.9

Hard Prompts

#134 / 422

19,342 votes

1441.9

Additional Categories
22

Chinese

#100 / 396

2,690 votes

1477.7

Korean

#108 / 289

608 votes

1379.2

German

#111 / 321

681 votes

1426.4

French

#115 / 302

702 votes

1447.4

Polish

#115 / 243

1,300 votes

1419.7

Industry Mathematical

#116 / 403

1,761 votes

1437.6

Industry Medicine And Healthcare

#120 / 392

1,923 votes

1448.5

Japanese

#121 / 288

372 votes

1370.8

Industry Entertainment And Sports And Media

#122 / 420

6,628 votes

1395.3

Industry Legal And Government

#123 / 394

2,438 votes

1435.8

Industry Writing And Literature And Language

#124 / 421

8,017 votes

1405.1

Industry Life And Physical And Social Science

#125 / 420

5,905 votes

1445.9

English

#127 / 422

15,235 votes

1437.0

Exclude Ties

#127 / 422

24,993 votes

1416.1

Non English

#130 / 422

20,370 votes

1407.7

Spanish

#131 / 304

1,008 votes

1413.1

Hard Prompts English

#132 / 420

8,206 votes

1449.4

Multi Turn

#135 / 420

5,601 votes

1421.2

Expert

#140 / 372

2,054 votes

1440.0

Russian

#142 / 386

3,514 votes

1406.8

Industry Software And It Services

#145 / 422

12,558 votes

1453.0

Industry Business And Management And Financial Operations

#148 / 415

6,881 votes

1412.2

Published 2026-11-18 · Matched as GLM-4.6 · CC BY 4.0

LMArena Dataset

Providers

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

Auto
Auto
Recommended
$0.55$2.20$0.11N/AN/A
Batch API
ProviderInputOutputCached input
Auto
Autoz-ai/GLM-4.6-turbo
$0.55/M$2.20/M$0.11/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.

Reliability

Related text models

Compare GLM 4.6 Turbo with similar models from the same provider or model family.

GLM 5V Turbo Thinking

z-ai/glm-5v-turbo:thinking

Thinking-enabled GLM 5V Turbo for image, video, and text inputs. Uses the same multimodal foundation model with more deliberate vision-grounded analysis, planning, and tool use.

GLM 5V Turbo

z-ai/glm-5v-turbo

Z.ai's native multimodal agent model for vision-based coding and agent workflows. This is the standard non-thinking variant for image, video, and text inputs, tuned for perceive-plan-execute loops, complex coding, and tool-driven task execution.

GLM 5 Turbo

z-ai/glm-5-turbo

Fast GLM 5 Turbo variant from Z-AI for general chat, coding, and tool use.

GLM 4.6 Turbo (Thinking)

z-ai/GLM-4.6-turbo:thinking

GLM 4.6 Turbo with thinking mode enabled for enhanced reasoning; shows internal reasoning and supports long context.

GLM 5.3 Abliterated

z-ai/glm-5.3-abliterated

An experimental abliterated (refusal-removed) version of GLM 5.3, hosted by UncensuredAI. It always reasons, with low, high or max effort, and supports tool calling. Text only. Its behavior and response quality may differ from GLM 5.3.

GLM 5.3 Flash Abliterated

z-ai/glm-5.3-flash-abliterated

An experimental abliterated (refusal-removed) version of GLM 5.3 Flash, hosted by UncensuredAI. It always reasons, with low, high or max effort, and supports tool calling. Text only. Its behavior and response quality may differ from GLM 5.3 Flash.