AI TOOLS RADAR
All models / Z-AI
z-ai logo
z-ai

Z.ai: GLM 4.7

Source description (English)

GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while...

View source on OpenRouter Hugging Face
Overview

Model specifications

Context
204,800 tokens
Maximum output
131,072 tokens
Architecture
text->text
Tokenizer
Other
Knowledge cutoff
Not provided
Moderated
No
OPENROUTER

Complete pricing

Synchronized OpenRouter rates. Token prices are shown per one million tokens.

Input
$0.54
per 1M tokens
Output
$1.98
per 1M tokens
Cache read
$0.099
per 1M tokens
API

Model configuration

Default parameters

temperature
1
top_p
0.95

Reasoning

Reasoning required
No
Default parameters
Yes
API

Quick start

Set OPENROUTER_API_KEY locally. Python requires requests; JavaScript runs in Node.js. Keep the key on the server.

API documentation

curl --fail-with-body https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"z-ai/glm-4.7","messages":[{"role":"user","content":"Hello!"}]}'
Capabilities

Input → Output

Input
text
Output
text
Reasoning

Yes

API

Supported API parameters

frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_atop_ktop_p
Available providers

7 providers

Checked: October 19, 2026

Live providers on OpenRouter

Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.

OpenRouter

DeepInfra

fp4
Context
203K
Maximum output
131K
Input
$0.32
Output
$1.4
Cache read
$0.064
Cache write
Not provided

DeepInfra

fp4
Context
203K
Maximum output
131K
Input
$0.4
Output
$1.75
Cache read
$0.08
Cache write
Not provided

Venice

fp4
Context
198K
Maximum output
16K
Input
$0.4004
Output
$1.9292
Cache read
$0.0801
Cache write
Not provided

Novita

fp8
Context
205K
Maximum output
131K
Input
$0.54
Output
$1.98
Cache read
$0.099
Cache write
Not provided

Google

Not provided
Context
200K
Maximum output
128K
Input
$0.6
Output
$2.2
Cache read
Not provided
Cache write
Not provided

Z.AI

fp4
Context
203K
Maximum output
131K
Input
$0.6
Output
$2.2
Cache read
$0.11
Cache write
Not provided

Mancer 2

fp4
Context
131K
Maximum output
118K
Input
$0.7
Output
$2.5
Cache read
Not provided
Cache write
Not provided
z-ai

4 models

All models
z-ai logoz-ai

Z.ai: GLM 5.3 Prime

GLM-5.3-Prime is the high-speed variant of Z.ai's GLM-5.3, inheriting its full capabilities while delivering 1.5–2× the output throughput through inference acceleration. It supports text input and output with a 1M-token...

Context
1M
Input
text
Output
text
Input: $2.8Output: $8.8per 1M tokens
View model details →
z-ai logoz-ai

Z.ai: GLM 5.3 FlashX

GLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens/s. Built on the same hybrid sparse and linear attention architecture...

Context
1.0M
Input
text · image · video
Output
text
Input: $0.37Output: $1.25per 1M tokens
View model details →
z-ai logoz-ai

Z.ai: GLM 5.3 Flash

GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...

Context
1.0M
Input
text · image · video
Output
text
Input: $0.15Output: $0.5per 1M tokens
View model details →
z-ai logoz-ai

Z.ai: GLM 5.3 Flash (batch)

GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...

Context
1.0M
Input
text · image · video
Output
text
Input: $0.05Output: $0.18per 1M tokens
View model details →