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

Z.ai: GLM 4.6

Source description (English)

Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex...

View source on OpenRouter Hugging Face
Overview

Model specifications

Context
204,800 tokens
Maximum output
16,384 tokens
Architecture
text->text
Tokenizer
Other
Knowledge cutoff
2025-03-31
Moderated
No
OPENROUTER

Complete pricing

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

Input
$0.43
per 1M tokens
Output
$1.75
per 1M tokens
Cache read
$0.08
per 1M tokens
API

Model configuration

Default parameters

temperature
0.6

Reasoning

Reasoning required
No
Default parameters
No
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-4.6","messages":[{"role":"user","content":"Hello!"}]}'
Capabilities

Input → Output

Input
text
Output
text
Reasoning

No

API

Supported API parameters

frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Available providers

4 providers

Checked: September 20, 2026

Live providers on OpenRouter

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

OpenRouter

Venice

fp4
Context
198K
Maximum output
16K
Input
$0.43
Output
$1.75
Cache read
$0.08
Cache write
Not provided

DeepInfra

fp4
Context
203K
Maximum output
131K
Input
$0.5
Output
$2
Cache read
$0.1
Cache write
Not provided

Novita

bf16
Context
205K
Maximum output
131K
Input
$0.55
Output
$2.2
Cache read
$0.11
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
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 →