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

Z.ai: GLM 5.1

Source description (English)

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...

View source on OpenRouter Hugging Face
Overview

Model specifications

Context
204,800 tokens
Maximum output
128,000 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
$0.966
per 1M tokens
Output
$3.036
per 1M tokens
Cache read
$0.1794
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-5.1","messages":[{"role":"user","content":"Hello!"}]}'
Capabilities

Input → Output

Input
text
Output
text
Reasoning

Yes

API

Supported API parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Available providers

16 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

StreamLake

fp8
Context
200K
Maximum output
128K
Input
$0.966
Output
$3.036
Cache read
$0.1794
Cache write
Not provided

Chutes

fp8
Context
203K
Maximum output
66K
Input
$0.98
Output
$3.08
Cache read
$0.098
Cache write
Not provided

DeepInfra

fp4
Context
203K
Maximum output
66K
Input
$1.05
Output
$3.5
Cache read
$0.205
Cache write
Not provided

SiliconFlow

fp8
Context
205K
Maximum output
131K
Input
$1.19
Output
$3.74
Cache read
$0.6
Cache write
Not provided

Crusoe

fp8
Context
203K
Maximum output
182K
Input
$1.2
Output
$4.4
Cache read
$0.25
Cache write
Not provided

Phala

Not provided
Context
203K
Maximum output
128K
Input
$1.21
Output
$4.2
Cache read
$0.6
Cache write
Not provided

AtlasCloud

fp8
Context
203K
Maximum output
182K
Input
$1.26
Output
$3.96
Cache read
$0.234
Cache write
Not provided

DigitalOcean

Not provided
Context
164K
Maximum output
147K
Input
$1.3
Output
$4.3
Cache read
$0.26
Cache write
Not provided

Alibaba

fp8
Context
203K
Maximum output
131K
Input
$1.33
Output
$4.18
Cache read
$0.247
Cache write
Not provided

Novita

fp8
Context
205K
Maximum output
131K
Input
$1.38
Output
$4.4
Cache read
$0.26
Cache write
Not provided

Nebius

fp8
Context
203K
Maximum output
182K
Input
$1.4
Output
$4.4
Cache read
Not provided
Cache write
Not provided

Baidu

fp8
Context
203K
Maximum output
131K
Input
$1.4
Output
$4.4
Cache read
$0.26
Cache write
Not provided

GMICloud

fp8
Context
203K
Maximum output
182K
Input
$1.4
Output
$4.4
Cache read
$0.26
Cache write
Not provided

Friendli

Not provided
Context
203K
Maximum output
182K
Input
$1.4
Output
$4.4
Cache read
$0.26
Cache write
Not provided

Z.AI

fp8
Context
203K
Maximum output
131K
Input
$1.4
Output
$4.4
Cache read
$0.26
Cache write
Not provided

Venice

fp8
Context
200K
Maximum output
80K
Input
$1.54
Output
$4.84
Cache read
$0.286
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 →