Skip to content
Metered.
Z.ai model

GLM 5.2

API pricing per million tokens

glm-5-2 Open weightsChecked 5h ago
Cost calculator Compare
Input
$0.563
per 1M, DeepInfra (fp4)
Output
$1.8
per 1M tokens
Cached input
$0.105
no batch tier listed
Context
1M
131K max output

Where to buy it (27)

  • DeepInfrafp4, fp4$0.563 / $1.8cached $0.105
  • StreamLakefp8, fp8$0.643 / $2.02cached $0.119
  • Novita AIfp8, fp8$0.65 / $2.04cached $0.121
  • DigitalOceandefault region$0.7 / $2.2cached $0.105
  • CoreWeavefp4, fp4$0.76 / $2.42cached $0.14
  • AtlasCloudfp8, fp8$0.938 / $2.95cached $0.174
  • Qwen (Alibaba)fp8, fp8$0.966 / $3.04cached $0.193
  • Inceptronfp4, fp4$1.01 / $3.24cached $0.194
  • Phalafp8, fp8$1.26 / $3cached $0.22
  • SiliconFlowfp8, fp8$1.19 / $3.74cached $0.221
  • Baidufp8, fp8$1.4 / $4.4cached $0.26
  • Basetenfp8, fp8$1.4 / $4.4cached $0.14
  • Cloudflare Workers AIdefault region$1.4 / $4.4cached $0.26
  • Fireworks AIdefault region$1.4 / $4.4cached $0.14
  • Friendlidefault region$1.4 / $4.4cached $0.26
  • GMICloudfp8, fp8$1.4 / $4.4cached $0.26
  • Parasailfp4, fp4$1.4 / $4.4cached $0.26
  • Together AIdefault region$1.4 / $4.4cached $0.26
  • Venicefp8, fp8$1.4 / $4.4cached $0.26
  • Waferdefault region$1.4 / $4.4cached $0.26
  • Z.aifp8, fp8$1.4 / $4.4cached $0.26
  • Basetenfast, fp8$2.1 / $6.6cached $0.21
  • Fireworks AIfast$2.1 / $6.6cached $0.21
  • Fireworks AIfast-us$2.1 / $6.6cached $0.21
  • Qwen (Alibaba)fast, fp8$2.31 / $7.26cached $0.462
  • Baidufast, fp4$2.25 / $7.88cached $0.56
  • Decartfast, fp4$2.25 / $8cached $0.48

Through a gateway

Your own numbers

100M input and 20M output tokens a month: $92.25 direct.

Related models

About GLM 5.2

GLM 5.2 is a large-scale reasoning model from Z.ai.

Takes text in and returns text. First listed Sep 23, 2026. Blended price $0.872 per 1M tokens at 3 input to 1 output.

OpenRouter listing Z.ai pricing page
Across fru.devCompany profile

Questions

How much does GLM 5.2 cost?

$0.563 per million input tokens and $1.8 per million output tokens, with cached input at $0.105.

What is the context window of GLM 5.2?

1M tokens, with up to 131K tokens of output.

Where is GLM 5.2 cheapest?

Of 27 routes tracked, DeepInfra is cheapest at $0.563 input and $1.8 output per million tokens.

Has GLM 5.2's price changed?

Yes. The output price went from $2.27 to $7.88, first seen Sep 24, 2026.

List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.

Weekly: LLM API list prices that changed, Thursday mornings.