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

Z.ai: GLM 5.3 Flash

Source description (English)

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...

View source on OpenRouter Hugging Face
Overview

Model specifications

Context
1,310,720 tokens
Maximum output
131,072 tokens
Architecture
text+image+video->text
Tokenizer
Other
Knowledge cutoff
Not provided
Moderated
No
OPENROUTER

Complete pricing

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

Input
$0.075
per 1M tokens
Output
$0.25
per 1M tokens
Cache read
$0.015
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-flash","messages":[{"role":"user","content":"Hello!"}]}'
Capabilities

Input → Output

Input
textimagevideo
Output
text
Reasoning

Yes · max · high · low

API

Supported API parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Available providers

24 providers

Checked: September 7, 2026

Live providers on OpenRouter

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

OpenRouter

Relace

fp4
Context
1.0M
Maximum output
131K
Input
$0.0713
Output
$0.2375
Cache read
$0.0143
Cache write
Not provided

GMICloud

fp8
Context
1.0M
Maximum output
944K
Input
$0.075
Output
$0.25
Cache read
$0.015
Cache write
Not provided

Novita

fp8
Context
1.0M
Maximum output
131K
Input
$0.075
Output
$0.25
Cache read
$0.015
Cache write
Not provided

DeepInfra

fp4
Context
1.0M
Maximum output
131K
Input
$0.075
Output
$0.25
Cache read
$0.015
Cache write
Not provided

Z.AI

fp8
Context
1.0M
Maximum output
131K
Input
$0.075
Output
$0.25
Cache read
$0.015
Cache write
Not provided

Wafer

Not provided
Context
1.0M
Maximum output
944K
Input
$0.1
Output
$0.35
Cache read
$0.02
Cache write
Not provided

StreamLake

fp8
Context
1.0M
Maximum output
128K
Input
$0.135
Output
$0.45
Cache read
$0.027
Cache write
Not provided

Makora

Not provided
Context
1.0M
Maximum output
944K
Input
$0.14
Output
$0.47
Cache read
$0.024
Cache write
Not provided

Modal

fp8
Context
1.0M
Maximum output
944K
Input
$0.15
Output
$0.4999
Cache read
$0.03
Cache write
Not provided

CoreWeave

fp8
Context
1.0M
Maximum output
944K
Input
$0.15
Output
$0.5
Cache read
$0.05
Cache write
Not provided

Sail Research

fp8
Context
1.0M
Maximum output
131K
Input
$0.15
Output
$0.5
Cache read
$0.03
Cache write
Not provided

NextBit

fp8
Context
1.0M
Maximum output
128K
Input
$0.15
Output
$0.5
Cache read
$0.03
Cache write
Not provided

Fireworks

Not provided
Context
1.0M
Maximum output
944K
Input
$0.15
Output
$0.5
Cache read
$0.03
Cache write
Not provided

Friendli

Not provided
Context
1.0M
Maximum output
944K
Input
$0.15
Output
$0.5
Cache read
$0.03
Cache write
Not provided

SiliconFlow

fp8
Context
1.0M
Maximum output
262K
Input
$0.15
Output
$0.5
Cache read
$0.03
Cache write
Not provided

DigitalOcean

Not provided
Context
1.0M
Maximum output
944K
Input
$0.15
Output
$0.5
Cache read
$0.03
Cache write
Not provided

Together

Not provided
Context
1.0M
Maximum output
944K
Input
$0.15
Output
$0.5
Cache read
$0.03
Cache write
Not provided

Reka

fp8
Context
262K
Maximum output
236K
Input
$0.15
Output
$0.5
Cache read
$0.03
Cache write
Not provided

Parasail

fp8
Context
1.0M
Maximum output
944K
Input
$0.15
Output
$0.5
Cache read
$0.03
Cache write
Not provided

BaseTen

fp8
Context
1.0M
Maximum output
131K
Input
$0.15
Output
$0.5
Cache read
$0.03
Cache write
Not provided

Venice

Not provided
Context
1.0M
Maximum output
131K
Input
$0.15
Output
$0.5
Cache read
$0.03
Cache write
Not provided

Io Net

fp8
Context
262K
Maximum output
131K
Input
$0.15
Output
$0.5
Cache read
$0.03
Cache write
Not provided

Cloudflare

Not provided
Context
1.3M
Maximum output
1.2M
Input
$0.15
Output
$0.5
Cache read
$0.03
Cache write
Not provided

Morph

fp8
Context
1.0M
Maximum output
944K
Input
$0.388
Output
$1.358
Cache read
$0.0776
Cache write
Not provided
z-ai

4 models

All models
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: $0.15Output: $0.5per 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: $1.4Output: $4.4per 1M tokens
View model details →
z-ai logoz-ai

Z.ai: GLM 5.2

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,...

Context
1.0M
Input
text
Output
text
Input: $0.966Output: $3.036per 1M tokens
View model details →
z-ai logoz-ai

Z.ai: GLM 5.1

GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on...

Context
205K
Input
text
Output
text
Input: $0.966Output: $3.036per 1M tokens
View model details →