Skip to content
LLMs
Z.ai logo

Z.ai: GLM 5.2

by Z.ai

Z.ai: GLM 5.2 is a large language model from Z.ai. It costs $0.683 per million input tokens and $2.15 per million output tokens. Its context window is 1.0M tokens.

ReasoningTool callingStructured outputPrompt cachingBatch tierOpen weights
Input / 1M tokens
$0.683
Output / 1M tokens
$2.15
Cached input / 1M
$0.127

On repeated prefixes

Context window
1.0M

tokens

Who serves it cheapest

23 hosts serve GLM 5.2. Same weights, same API - the price difference is pure margin and routing.

Providers serving Z.ai: GLM 5.2, cheapest first
ProviderInput / 1MOutput / 1MContextThroughputUptime 24h
BaiduCheapestfp8$0.487$1.531.0M-99.9%
DeepInfrafp4$0.487$1.561.0M-98.5%
StreamLakefp8$0.560$1.761.0M-99.0%
Ambientfp8$0.600$2.00203K-97.4%
Novitafp8$0.683$2.151.0M-100.0%
DigitalOcean$0.700$2.20262K-98.9%
CoreWeavefp4$0.760$2.421.0M-99.8%
AtlasCloudfp8$0.938$2.951.0M-99.9%
Alibabafp8$0.966$3.041M-99.9%
Inceptronfp4$1.10$2.941.0M-98.5%
Phalafp8$1.26$3.001.0M-99.9%
SiliconFlowfp8$1.19$3.741.0M-97.8%
Mistral$1.40$4.401.0M-99.9%
BaseTenfp8$1.40$4.401.0M-100.0%
Together$1.40$4.40512K-93.9%
Fireworks$1.40$4.401.0M-99.6%
Venicefp8$1.40$4.401M-99.8%
GMICloudfp8$1.40$4.401.0M-99.2%
Parasailfp4$1.40$4.40262K-99.5%
Friendli$1.40$4.401.0M-99.9%
Cloudflare$1.40$4.40262K-100.0%
Z.AIfp8$1.40$4.401.0M-99.9%
Decartfp4$2.10$6.601.0M-99.8%

The spread between Baidu and Decart is 4.3× for identical weights. Quantization and context limits differ, so check both columns before switching.

Benchmarks

Independent scores published alongside the catalogue.

Coding index
68.8
Agentic index
39.4

About 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,...

Specifications

Z.ai: GLM 5.2 specifications
Model IDz-ai/glm-5.2
ProviderZ.ai
Context window1.0M tokens
Max output131K tokens
Input modalitiestext
Output modalitiestext
Knowledge cutoff-
Open weightsYes - zai-org/GLM-5.2
ReleasedJune 16, 2026

Cheaper alternatives

Models that cost less than GLM 5.2 while keeping at least half its context window and every input modality it supports.

MiniMax M1

$0.550 in · $2.20 out

1.1× cheaper

Gemini 3.5 Flash Lite

$0.300 in · $2.50 out

1.2× cheaper

Nova 2 Lite

$0.300 in · $2.50 out

1.2× cheaper

Gemini 2.5 Flash

$0.300 in · $2.50 out

1.2× cheaper

Qwen3.8 27B

$0.214 in · $2.55 out

1.3× cheaper

Frequently asked

How much does Z.ai: GLM 5.2 cost?

$0.683 per million input tokens and $2.15 per million output tokens. Cached input reads cost $0.127 per million tokens.

What is the context window of Z.ai: GLM 5.2?

1.0M tokens, with up to 131K tokens of output per request.

Which provider serves Z.ai: GLM 5.2 cheapest?

Baidu at $0.487 per million input tokens - 4.3× cheaper than Decart, the most expensive of the 23 hosts serving it.

Confirm against the source: Z.ai official pricing.