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

Z.ai: GLM 5.2

Source description (English)

GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...

View source on OpenRouter Hugging Face
Overview

Model specifications

Context
1,048,576 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
$0.6496
per 1M tokens
Output
$2.0416
per 1M tokens
Cache read
$0.1206
per 1M tokens
API

Model configuration

Default parameters

temperature
1
top_p
0.95

Reasoning

Reasoning required
No
Default parameters
high
Capabilities
xhigh, high
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-5.2","messages":[{"role":"user","content":"Hello!"}]}'
Capabilities

Input → Output

Input
text
Output
text
Reasoning

Yes · xhigh · high

API

Supported API parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_pparallel_tool_callspresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Available providers

30 providers

Checked: September 21, 2026

Live providers on OpenRouter

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

OpenRouter

StreamLake

fp8
Context
1.0M
Maximum output
128K
Input
$0.5555
Output
$1.7459
Cache read
$0.1032
Cache write
Not provided

DeepInfra

fp4
Context
1.0M
Maximum output
164K
Input
$0.5625
Output
$1.8
Cache read
$0.105
Cache write
Not provided

Ambient

fp8
Context
203K
Maximum output
182K
Input
$0.6
Output
$2
Cache read
$0.15
Cache write
Not provided

Novita

fp8
Context
1.0M
Maximum output
131K
Input
$0.6496
Output
$2.0416
Cache read
$0.1206
Cache write
Not provided

DigitalOcean

Not provided
Context
262K
Maximum output
236K
Input
$0.7
Output
$2.2
Cache read
$0.105
Cache write
Not provided

CoreWeave

fp4
Context
1.0M
Maximum output
944K
Input
$0.76
Output
$2.42
Cache read
$0.14
Cache write
Not provided

AtlasCloud

fp8
Context
1.0M
Maximum output
131K
Input
$0.938
Output
$2.948
Cache read
$0.1742
Cache write
Not provided

Alibaba

fp8
Context
1M
Maximum output
131K
Input
$0.966
Output
$3.036
Cache read
$0.1932
Cache write
Not provided

SiliconFlow

fp8
Context
1.0M
Maximum output
262K
Input
$1.19
Output
$3.74
Cache read
$0.221
Cache write
Not provided

Inceptron

fp4
Context
1.0M
Maximum output
944K
Input
$1.2533
Output
$3.3469
Cache read
$0.2041
Cache write
Not provided

Phala

fp8
Context
1.0M
Maximum output
131K
Input
$1.26
Output
$3
Cache read
$0.22
Cache write
Not provided

BaseTen

fp8
Context
1.0M
Maximum output
262K
Input
$1.4
Output
$4.4
Cache read
$0.14
Cache write
Not provided

Together

Not provided
Context
512K
Maximum output
461K
Input
$1.4
Output
$4.4
Cache read
$0.26
Cache write
Not provided

Baidu

fp8
Context
1.0M
Maximum output
131K
Input
$1.4
Output
$4.4
Cache read
$0.26
Cache write
Not provided

Wafer

Not provided
Context
1.0M
Maximum output
944K
Input
$1.4
Output
$4.4
Cache read
$0.26
Cache write
Not provided

Fireworks

Not provided
Context
1.0M
Maximum output
944K
Input
$1.4
Output
$4.4
Cache read
$0.14
Cache write
Not provided

BaseTen

fp8
Context
1.0M
Maximum output
262K
Input
$1.4
Output
$4.4
Cache read
$0.14
Cache write
Not provided

Venice

fp8
Context
1M
Maximum output
131K
Input
$1.4
Output
$4.4
Cache read
$0.26
Cache write
Not provided

GMICloud

fp8
Context
1.0M
Maximum output
944K
Input
$1.4
Output
$4.4
Cache read
$0.26
Cache write
Not provided

Parasail

fp4
Context
262K
Maximum output
236K
Input
$1.4
Output
$4.4
Cache read
$0.26
Cache write
Not provided

Friendli

Not provided
Context
1.0M
Maximum output
944K
Input
$1.4
Output
$4.4
Cache read
$0.26
Cache write
Not provided

Cloudflare

Not provided
Context
262K
Maximum output
236K
Input
$1.4
Output
$4.4
Cache read
$0.26
Cache write
Not provided

Z.AI

fp8
Context
1.0M
Maximum output
131K
Input
$1.4
Output
$4.4
Cache read
$0.26
Cache write
Not provided

BaseTen

fp8
Context
1.0M
Maximum output
262K
Input
$2.1
Output
$6.6
Cache read
$0.21
Cache write
Not provided

Fireworks

Not provided
Context
1.0M
Maximum output
944K
Input
$2.1
Output
$6.6
Cache read
$0.21
Cache write
Not provided

BaseTen

fp8
Context
1.0M
Maximum output
262K
Input
$2.1
Output
$6.6
Cache read
$0.21
Cache write
Not provided

Fireworks

Not provided
Context
1.0M
Maximum output
944K
Input
$2.1
Output
$6.6
Cache read
$0.21
Cache write
Not provided

Baidu

fp4
Context
1.0M
Maximum output
131K
Input
$2.25
Output
$7.88
Cache read
$0.56
Cache write
Not provided

Decart

fp4
Context
1.0M
Maximum output
944K
Input
$2.25
Output
$8
Cache read
$0.48
Cache write
Not provided

Alibaba

fp8
Context
1M
Maximum output
131K
Input
$2.31
Output
$7.26
Cache read
$0.462
Cache write
Not provided
z-ai

4 models

All models
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
1.3M
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: $0.06Output: $0.2per 1M tokens
View model details →
z-ai logoz-ai

Z.ai: GLM 5.3

GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...

Context
1.3M
Input
text
Output
text
Input: $0.5614Output: $1.7644per 1M tokens
View model details →