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. Z.AI

GLM 5.3 Thinking

GLM-5.3 with higher reasoning enabled for harder long-horizon coding, autonomous agent workflows, and complex engineering tasks.

  • Reasoning
  • Tool Calling
  • Structured Output

Added Aug 14, 2026

Model weights

Pricing

Auto routing · per 1M tokens
Input
$0.60
Output
$1.10
Cache read
$0.20
Compare provider prices

Specifications

Context window
1M
Max output
131.1K

Benchmarks

Sourced from LMArena.

Arena Score

1481.6

Overall Rank

#28 / 421

Votes

31,604

Confidence Interval

1476.9 - 1486.3

Category Scores

Coding

#33 / 416

7,348 votes

1522.0

Math

#16 / 404

1,338 votes

1501.4

Longer Query

#32 / 399

14,146 votes

1488.3

Creative Writing

#33 / 419

7,185 votes

1455.8

Instruction Following

#24 / 421

10,480 votes

1480.6

Hard Prompts

#23 / 421

19,800 votes

1507.1

Additional Categories
22

German

#7 / 320

482 votes

1510.1

French

#9 / 301

1,094 votes

1512.6

Chinese

#16 / 395

2,406 votes

1540.2

Hard Prompts English

#17 / 419

7,816 votes

1514.5

Expert

#20 / 371

2,900 votes

1522.3

Industry Life And Physical And Social Science

#20 / 419

5,254 votes

1508.2

Industry Mathematical

#20 / 402

1,645 votes

1501.8

Japanese

#22 / 288

536 votes

1479.7

English

#23 / 421

12,382 votes

1490.8

Industry Medicine And Healthcare

#24 / 391

2,345 votes

1500.3

Industry Software And It Services

#27 / 421

11,352 votes

1514.8

Exclude Ties

#30 / 421

23,528 votes

1491.3

Korean

#30 / 289

480 votes

1443.2

Industry Writing And Literature And Language

#31 / 420

9,215 votes

1466.8

Spanish

#34 / 304

1,053 votes

1471.2

Industry Business And Management And Financial Operations

#35 / 414

5,722 votes

1475.6

Non English

#35 / 421

19,221 votes

1467.3

Russian

#36 / 385

4,289 votes

1479.6

Industry Entertainment And Sports And Media

#37 / 419

8,307 votes

1448.3

Multi Turn

#37 / 419

4,682 votes

1482.1

Industry Legal And Government

#39 / 393

2,654 votes

1481.7

Polish

#44 / 243

467 votes

1474.7

Published 2026-11-11 · Matched as GLM-5.3 (Max) · CC BY 4.0

LMArena Dataset

Leaderboard results

BenchmarkScoreRank on NanoGPT
Epoch AI Benchmarking Hub

Epoch AI data, CC BY 4.0 · Updated Nov 18, 2026

Epoch Capabilities Index

Tested as GLM 5.3

157.1

#30 of 113

FrontierMath v2 (Tiers 1–3)

68.8%

#30 of 82

GPQA Diamond

90.9%

#33 of 117

SimpleQA Verified

41.0%

#48 of 82

FrontierMath v2 (Tier 4)

29.3%

#36 of 66

OTIS Mock AIME 2024–2025

91.1%

#56 of 119

Chess Puzzles

37.0%

#38 of 81

Mystery Game Puzzles

33.0%

#31 of 78

EQ-Bench

EQ-Bench data, MIT · Updated Nov 18, 2026

Creative Writing v3

Tested as GLM 5.3

2076

#7 of 91

Longform Writing

Tested as GLM 5.3

81.8

#11 of 93

Filtered and ranked to models on NanoGPT.

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)
$0.60$1.10$0.20N/AN/A
Auto
Auto (Anonymized)
$0.60$1.10$0.20N/AN/A
Wafer US
Wafer US
FP4
US
$0.0734$1.47$0.0723N/AN/A
Relace
Relace
FP4
UNK
$0.0738$4.60$0.0738N/AN/A
Wafer
Wafer
FP4
US
$0.188$1.47$0.187N/AN/A
Akash
Akash
FP4
GLB
$0.20$4.62$0.20N/AN/A
DeepInfra
DeepInfra
FP4
US
$0.591$2.63$0.131N/AN/A
Novita
Novita
55% off
FP8
US
$1.47$0.662$4.62$2.08$0.273$0.123N/AN/A
Nube
Nube
$0.662$2.08$0.123N/AN/A
Cloudflare
Cloudflare
50% off
US
$1.47$0.735$4.62$2.31$0.273$0.136N/AN/A
GMICloud
GMICloud
50% off
FP8
US
$1.47$0.735$4.62$2.31$0.273$0.136N/AN/A
SiliconFlow
SiliconFlow
FP8
SG
$0.735$2.00$0.136N/AN/A
SCX (Global)
SCX (Global)
BF16
GLB
$0.759$2.38$0.141N/AN/A
CoreWeave
CoreWeave
NVFP4
US
$0.787$3.15$0.20N/AN/A
Sail Research (Standard)
Sail Research (Standard)
FP8
GLB
$0.787$3.15$0.126N/AN/A
Decart
Decart
FP4
US
$0.872$2.77$0.147N/AN/A
EngyAI
EngyAI
GLB
$1.03$3.23$0.189N/AN/A
Inceptron
Inceptron
FP4
EU
$1.10$4.41$0.145N/AN/A
Runware
Runware
10% off
UNK
$1.26$1.13$4.20$3.78$0.21$0.189N/AN/A
Morph
Morph
FP8
US
$1.14$5.30$0.23N/AN/A
Mixlayer
Mixlayer
FP8
GLB
$1.21$4.09$0.242N/AN/A
Alibaba
Alibaba
SG
$1.25$3.93$0.25N/AN/A
Uomi
Uomi
BF16
GLB
$1.28$4.34N/AN/AN/A
Friendli
Friendli
10% off
US
$1.47$1.32$4.62$4.16$0.273$0.246N/AN/A
Kitani
Kitani
GLB
$1.36$4.46$0.273N/AN/A
AtlasCloud
AtlasCloud
FP8
US
$1.47$4.62$0.273N/AN/A
Baidu
Baidu
FP8
CN
$1.47$4.62$0.273N/AN/A
BaseTen
BaseTen
FP4
US
$1.47$4.62$0.147N/AN/A
Crusoe
Crusoe
FP4
US
$1.47$4.62$0.273N/AN/A
Fireworks
Fireworks
US
$1.47$4.62$0.273N/AN/A
Modal
Modal
US
$1.47$4.62$0.273N/AN/A
Nebius
Nebius
FP4
GLB
$1.47$4.62$0.273N/AN/A
Ollama
Ollama
UNK
$1.47$4.62$0.273N/AN/A
Parasail
Parasail
FP4
US
$1.47$4.62$0.273N/AN/A
RunAnywhere Fast (Wally)
RunAnywhere Fast (Wally)
33% off
FP8
US
$2.21$1.47$6.93$4.62$0.41$0.273N/AN/A
RunInfra
RunInfra
NVFP4
$1.47$4.62$0.147N/AN/A
SambaNova
SambaNova
US
$1.47$4.62$0.0735N/AN/A
Together
Together
US
$1.47$4.62$0.273N/AN/A
Venice
Venice
20% off
US
$1.84$1.47$5.77$4.62$0.341$0.273N/AN/A
Z.AI
Z.AI
FP8
SG
$1.47$4.62$0.273N/AN/A
NeuralWatt
NeuralWatt
US
$1.52$4.72$0.152N/AN/A
TensorX
TensorX
EU
$1.84$4.72$0.459N/AN/A
SCX Fast
SCX Fast
BF16
GLB
$2.94$9.24$0.588N/AN/A
Privacy:ZDR, prompts not retainedNo training on promptsRetention and training unclear
Batch API
ProviderInputOutputCached input
Auto
Autoz-ai/glm-5.3:thinking
$0.60/M$1.10/M$0.20/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 GLM 5.3 Thinking with similar models from the same provider or model family.

GLM 5.3 FlashX Legal

z-ai/glm-5.3-flashx-legal

GLM 5.3 FlashX Legal is Z.AI's model trained for legal document analysis, contract review, legal reasoning and initial drafts. It accepts text and images and returns text, with always-on reasoning, tool calling, JSON output, a 1M-token context window and up to 131,072 output tokens. External legal databases and document-editing tools require your own integrations.

Apex Flash 1

z-ai/glm-5.3-flash-apex

Apex Flash 1 is Cantina Security and Yeta's cybersecurity-focused post-train of GLM 5.3 Flash for code investigation and tool use.

Apex Flash 1 Abliterated

z-ai/glm-5.3-flash-apex-abliterated

Apex Flash 1 Abliterated is an experimental derivative of Cantina Security and Yeta's Apex Flash 1 with modified refusal behavior.

GLM 5.3 Uncensored

z-ai/glm-5.3-uncensored

An experimental uncensored version of the full GLM 5.3 reasoning model for chat, creative writing, coding, and tool use. It may show unusual behavior or inconsistent response quality.

GLM 5.3 Flash Cybersecurity

z-ai/glm-5.3-flash-cybersecurity

GLM 5.3 Flash Cybersecurity is a cybersecurity-focused variant based on the uncensored model, with provider moderation for illegal activities. It supports always-on reasoning, image understanding, tool calling, and a 1,048,576-token context window.

GLM 5.3 Flash

z-ai/glm-5.3-flash

ox-alpha out of stealth! GLM-5.3 Flash is Z.ai's first natively multimodal GLM-5 model, with 320B total parameters and just 18B active parameters for efficient coding, agentic work, and precise 1M-token context. Its hybrid sparse-and-linear attention architecture helps it outperform GLM-5.2 at one-tenth the price while approaching Claude Opus 4.8 on coding and agentic benchmarks.