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

Z.ai: GLM 5.3

Source description (English)

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...

View source on OpenRouter Hugging Face
Overview

Model specifications

Context
1,310,720 tokens
Maximum output
943,717 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
$1.4
per 1M tokens
Output
$4.4
per 1M tokens
Cache read
$0.26
per 1M tokens
API

Model configuration

Default parameters

temperature
1
top_p
0.95

Reasoning

Reasoning required
Yes
Default parameters
max
Capabilities
max, high, low
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-5.3","messages":[{"role":"user","content":"Hello!"}]}'
Capabilities

Input → Output

Input
text
Output
text
Reasoning

Yes · max · high · low

API

Supported API parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_pparallel_tool_callspresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Available providers

40 providers

Checked: September 28, 2026

Live providers on OpenRouter

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

OpenRouter

Reka

Not provided
Context
262K
Maximum output
236K
Input
$0.3556
Output
$2.574
Cache read
$0.066
Cache write
Not provided

Inceptron

fp4
Context
1.0M
Maximum output
944K
Input
$0.4204
Output
$2.7392
Cache read
$0.0967
Cache write
Not provided

Morph

fp8
Context
1.0M
Maximum output
944K
Input
$0.4522
Output
$2.805
Cache read
$0.1466
Cache write
Not provided

Io Net

fp8
Context
262K
Maximum output
66K
Input
$0.5005
Output
$1.898
Cache read
$0.091
Cache write
Not provided

Relace

Not provided
Context
1.0M
Maximum output
131K
Input
$0.55
Output
$1.7
Cache read
$0.1
Cache write
Not provided

DeepInfra

fp4
Context
1.0M
Maximum output
131K
Input
$0.5625
Output
$2.5
Cache read
$0.125
Cache write
Not provided

InferenceNet

Not provided
Context
1.0M
Maximum output
131K
Input
$0.684
Output
$2.28
Cache read
$0.114
Cache write
Not provided

Sail Research

fp8
Context
1.0M
Maximum output
944K
Input
$0.77
Output
$4
Cache read
$0.19
Cache write
Not provided

Sail Research

fp8
Context
1.0M
Maximum output
944K
Input
$0.77
Output
$4
Cache read
$0.19
Cache write
Not provided

Novita

fp8
Context
1.0M
Maximum output
131K
Input
$0.7826
Output
$2.4596
Cache read
$0.1453
Cache write
Not provided

DigitalOcean

Not provided
Context
1.0M
Maximum output
128K
Input
$0.91
Output
$2.86
Cache read
$0.169
Cache write
Not provided

Phala

Not provided
Context
1.0M
Maximum output
131K
Input
$0.98
Output
$3.08
Cache read
$0.182
Cache write
Not provided

GMICloud

fp8
Context
1.0M
Maximum output
944K
Input
$0.98
Output
$3.08
Cache read
$0.182
Cache write
Not provided

Makora

fp4
Context
980K
Maximum output
128K
Input
$1.05
Output
$4.2
Cache read
$0.19
Cache write
Not provided

SiliconFlow

fp8
Context
1.0M
Maximum output
262K
Input
$1.12
Output
$3.52
Cache read
$0.208
Cache write
Not provided

Alibaba

Not provided
Context
1M
Maximum output
131K
Input
$1.19
Output
$3.74
Cache read
$0.238
Cache write
Not provided

Decart

fp4
Context
1.0M
Maximum output
944K
Input
$1.19
Output
$3.74
Cache read
$0.1955
Cache write
Not provided

Friendli

Not provided
Context
1.0M
Maximum output
944K
Input
$1.26
Output
$3.96
Cache read
$0.234
Cache write
Not provided

AkashML

fp8
Context
1.0M
Maximum output
131K
Input
$1.3
Output
$4.4
Cache read
$0.26
Cache write
Not provided

Mistral

nvfp4
Context
1.0M
Maximum output
131K
Input
$1.4
Output
$4.4
Cache read
$0.14
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

Baidu

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

BaseTen

fp4
Context
1.0M
Maximum output
262K
Input
$1.4
Output
$4.4
Cache read
$0.14
Cache write
Not provided

Mistral

nvfp4
Context
1.0M
Maximum output
131K
Input
$1.4
Output
$4.4
Cache read
$0.14
Cache write
Not provided

Crusoe

fp4
Context
1.0M
Maximum output
944K
Input
$1.4
Output
$4.4
Cache read
$0.26
Cache write
Not provided

PrimeIntellect

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

Venice

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

Together

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

Parasail

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

Modal

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

BaseTen

fp4
Context
1.0M
Maximum output
262K
Input
$1.4
Output
$4.4
Cache read
$0.14
Cache write
Not provided

Fireworks

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
1.3M
Maximum output
1.2M
Input
$1.4
Output
$4.4
Cache read
$0.26
Cache write
Not provided

AtlasCloud

fp8
Context
1.0M
Maximum output
131K
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

Mistral

nvfp4
Context
1.0M
Maximum output
131K
Input
$1.54
Output
$4.84
Cache read
$0.154
Cache write
Not provided

Wafer

Not provided
Context
1.0M
Maximum output
944K
Input
$1.82
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

BaseTen

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

Alibaba

Not provided
Context
1M
Maximum output
131K
Input
$2.8
Output
$8.8
Cache read
$0.56
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
1.3M
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 →