Skip to content
Metered.
Z.ai model

GLM 5.3 Flash

API pricing per million tokens

glm-5-3-flash Open weightsChecked 7h ago
Cost calculator Compare Benchmarks
Input
$0.045
per 1M, InferenceNet (fp4)
Output
$0.14
per 1M tokens
Cached input
$0.01
no batch tier listed
Context
1.31M
944K max output

Where to buy it (30)

  • InferenceNetfp4, fp4$0.045 / $0.14cached $0.01
  • DeepInfrafp4, fp4$0.075 / $0.25cached $0.015
  • Relacedefault region$0.07 / $0.28cached $0.02
  • Inceptronfp8, fp8$0.09 / $0.28cached $0.07
  • GMICloudfp8, fp8$0.09 / $0.3cached $0.018
  • Morphdefault region$0.088 / $0.308cached $0.018
  • Waferdefault region$0.089 / $0.35cached $0.03
  • Io Netfp8, fp8$0.125 / $0.42cached $0.025
  • OpenInferencefp4, fp4$0.1 / $0.5cached $0.025
  • Phalafp8, fp8$0.128 / $0.425cached $0.025
  • Novita AIfp8, fp8$0.132 / $0.44cached $0.026
  • StreamLakefp8, fp8$0.141 / $0.47cached $0.028
  • Sail Researchus, fp8$0.143 / $0.475cached $0.029
  • AtlasCloudfp8, fp8$0.15 / $0.5cached $0.03
  • Basetenfp8, fp8$0.15 / $0.5cached $0.03
  • CoreWeavenvfp4, nvfp4$0.15 / $0.5cached $0.05
  • Crusoefp4, fp4$0.15 / $0.5cached $0.03
  • DigitalOceandefault region$0.15 / $0.5cached $0.03
  • Fireworks AIdefault region$0.15 / $0.5cached $0.03
  • Friendlidefault region$0.15 / $0.5cached $0.03
  • Near AIfp8, fp8$0.15 / $0.5cached $0.035
  • Parasailfp8, fp8$0.15 / $0.5cached $0.03
  • Rekafp8, fp8$0.15 / $0.5cached $0.03
  • SiliconFlowfp8, fp8$0.15 / $0.5cached $0.03
  • Together AIdefault region$0.15 / $0.5cached $0.03
  • Venicedefault region$0.15 / $0.5cached $0.03
  • Z.aifp8, fp8$0.15 / $0.5cached $0.03
  • NextBitfp8, fp8$0.165 / $0.55cached $0.033
  • Cloudflare Workers AIdefault region$0.3 / $1cached $0.03
  • Modalfp8, fp8$0.45 / $1.5cached $0.09

Through a gateway

Your own numbers

100M input and 20M output tokens a month: $7.30 direct.

Related models

About GLM 5.3 Flash

GLM-5.3-Flash is a native multimodal model from Z.ai.

Takes text, image, video in and returns text. First listed Sep 23, 2026. Blended price $0.069 per 1M tokens at 3 input to 1 output.

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

Questions

How much does GLM 5.3 Flash cost?

$0.045 per million input tokens and $0.14 per million output tokens, with cached input at $0.01.

What is the context window of GLM 5.3 Flash?

1.31M tokens, with up to 944K tokens of output.

Where is GLM 5.3 Flash cheapest?

Of 30 routes tracked, InferenceNet is cheapest at $0.045 input and $0.14 output per million tokens.

Has GLM 5.3 Flash's price changed?

Yes. The output price went from $0.5 to $0.36, 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.