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 4.7 Original Thinking

GLM-4.7 original with extended thinking capabilities for complex reasoning.

  • Reasoning
  • Tool Calling
  • Structured Output

Added Dec 22, 2025

Pricing

Auto routing · per 1M tokens
Input
$0.40
Output
$1.93
Cache read
$0.0801
Compare provider prices

Specifications

Context window
200K
Max output
65.5K
Parameters
355B / 32B
Total / active

Benchmarks

Sourced from Vectara.

Hallucination Rate

11.7%

Hallucination Rate: 11.7
Better than 31% of models compared

Factual Consistency

88.3%

Factual Consistency: 88.3
Better than 31% of models compared

Answer Rate

99.8%

Answer Rate: 99.8
Better than 64% of models compared

Avg Summary Length

Average generated summary length

70.6

Last updated 2026-10-22 · Matched as zai-org/glm-4p7

Vectara Leaderboard

Leaderboard results

These leaderboards tested GLM 4.7, another version of this model.

BenchmarkScoreRank on NanoGPT
Epoch AI Benchmarking Hub

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

Epoch Capabilities Index

143.4

#87 of 113

GPQA Diamond

83.3%

#73 of 117

SimpleQA Verified

32.2%

#63 of 82

OTIS Mock AIME 2024–2025

83.3%

#80 of 119

Chess Puzzles

21.0%

#60 of 81

EQ-Bench

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

Creative Writing v3

1414

#65 of 91

Longform Writing

66.0

#48 of 93

EQ-Bench 3

1463

#23 of 45

UGI Leaderboard

UGI Leaderboard data, Apache-2.0 · Updated Oct 16, 2026

UGI Score

49.6

#41 of 125

UGI Willingness

4.8

#37 of 125

UGI Writing

47.4

#61 of 125

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)
$0.40$1.93$0.0801N/AN/A
Auto
Auto (Anonymized)
$0.40$1.93$0.0801N/AN/A
MegaNova
MegaNova
FP8
US
$0.263$1.05N/AN/AN/A
DeepInfra
DeepInfra
FP4
US
$0.42$1.84$0.084N/AN/A
Venice
Venice
FP4
US
$0.42$2.03$0.0841N/AN/A
Novita
Novita
FP8
US
$0.63$2.31$0.116N/AN/A
Z.AI
Z.AI
FP4
SG
$0.63$2.31$0.116N/AN/A
Uomi
Uomi
BF16
GLB
$0.662$2.43N/AN/AN/A
Mancer
Mancer
FP4
$0.735$2.63$0.367N/AN/A
Privacy:ZDR, prompts not retainedNo training on promptsMay train on prompts
Batch API
ProviderInputOutputCached input
Auto
Autoz-ai/glm-4.7-original:thinking
$0.40/M$1.93/M$0.0801/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 4.7 Original Thinking with similar models from the same provider or model family.

GLM 5 Original

z-ai/glm-5-original

GLM-5 is a capable open-weight model from Zhipu with advanced reasoning and instruction following. This Original variant uses the model maker's direct endpoint.

GLM 5 Original Thinking

z-ai/glm-5-original:thinking

GLM-5 original with extended thinking capabilities for complex reasoning.

GLM 4.7 Original

z-ai/glm-4.7-original

GLM-4.7 is a next-gen GLM series text model with stronger reasoning, long-context chat, and reliable tool use. Routed directly via Z-AI (Zhipu).

GLM 4.6 Original

z-ai/glm-4.6-original

GLM-4.6, Zhipu's flagship text model with 256K context window and advanced reasoning capabilities. Direct via Z-AI (Zhipu).

GLM 4.6V Original

z-ai/glm-4.6v-original

GLM-4.6V scales its context window to 128k tokens in training, and achieves SoTA performance in visual understanding among models of similar parameter scales. Integrates native Function Calling capabilities, bridging 'visual perception' and 'executable action' for multimodal agents. Direct via Z-AI (Zhipu).

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.