All models

GLM 5.2

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,...

Modalities
Text
In / Out price
$0.63 / $1.98 per 1M
Context
1.05M
Released
Jun 13, 2026

Providers

Live list prices and uptime across 31 providers serving this model.

ProviderInput /MOutput /MCache read /MContextMax outputUptime 24h
Novitafp8$0.461$1.448$0.0861.05M131K98.08%
Baidufp8$0.462$1.452$0.0861.05M131K95.39%
Sail Researchfp8$0.50$3.15$0.1151.05M131K99.56%
StreamLakefp8$0.56$1.76$0.1041.02M128K99.23%
DigitalOcean$0.70$2.20$0.105262K98.50%
GMICloudfp8$0.742$2.332$0.1381.05M97.58%
DeepInfrafp4$0.75$2.40$0.141.05M164K98.86%
Inceptronfp4$0.75$2.90$0.171.05M1.05M97.23%
CoreWeavefp4$0.76$2.42$0.14262K262K84.22%
Decartfp4$0.768$2.56$0.1281.05M1.05M98.49%
AkashMLfp8$0.77$2.42$0.14397K97K98.95%
Alibabafp8$0.966$3.036$0.1931.05M131K99.75%
Ambientfp8$1.05$4.40$0.20203K203K92.41%
Morphfp4$1.10$4.10$0.221.05M1.05M99.94%
Phalafp8$1.134$3.00$0.2111.05M131K96.46%
SiliconFlowfp8$1.19$3.74$0.2211.05M262K86.85%
Waferfp4$1.26$3.96$0.2341.05M131K95.34%
AtlasCloudfp8$1.26$3.96$0.2341.05M131K99.31%
Z.AIfp8$1.40$4.40$0.261.05M131K99.24%
Fireworks$1.40$4.40$0.141.05M98.96%
Cloudflare$1.40$4.40$0.26262K262K99.94%
Friendli$1.40$4.40$0.261.05M1.05M99.36%
Parasailfp4$1.40$4.40$0.26262K262K99.85%
Venicefp8$1.40$4.40$0.261M131K96.74%
Together$1.40$4.40$0.26512K94.17%
Crusoefp8$1.40$4.40$0.261.05M99.22%
BaseTenfp8$1.40$4.40$0.141.05M262K99.77%
Fireworks$2.10$6.60$0.211.05M95.96%
Cloudflare$2.10$6.60$0.21262K262K99.85%
BaseTenfp8$2.10$6.60$0.211.05M262K99.65%
Alibabafp8$2.31$7.26$0.4621.05M131K99.81%

No implicit prompt caching; cache reads require explicit cache control.

Capabilities

Tool calling
Reasoning
frequency_penalty
include_reasoning
logit_bias
logprobs
max_tokens
min_p
parallel_tool_calls
presence_penalty
reasoning
reasoning_effort
repetition_penalty
response_format
seed
stop
structured_outputs
temperature
tool_choice
top_k
top_logprobs
top_p

Pricing detail

Input
$0.63
Output
$1.98
Cache read
$0.095
Cache write

USD per 1M tokens.