GLM 5.2 pricing

GLM 5.2 from Z.ai runs on 11 providers. The lowest price is $0.45 input and $1.44 output per 1M tokens, on DeepInfra. On Mistral it costs 3.4× as much.

Updated

Lab
Z.ai
Context
1.05M
Input
Text
Providers
11
What each provider chargesBlended price per 1M tokens, 3 parts input to 1 part output. The highest is 3.4× the lowest.
  1. DeepInfra$0.698Lowest
  2. Novita AI$0.9981.4×
  3. CoreWeave$1.071.5×
  4. DigitalOcean$1.071.5×
  5. Alibaba Cloud$1.482.1×
  6. Cloudflare Workers AI$2.143.1×
  7. Nebius$2.153.1×
  8. Baseten$2.153.1×
  9. Together AI$2.153.1×
  10. Z.ai$2.153.1×
  11. Mistral$2.373.4×

Every price, by provider

GLM 5.2 prices by provider, in US dollars per 1 million tokens
ProviderInputOutputCachedCache writeBatch inBatch outContextMax output
DeepInfrafp4$0.45$1.44$0.084–––1.05M164K
Novita AIfp8$0.6496$2.0416$0.1206–––1.05M131K
CoreWeavefp4$0.62$2.42$0.14–––1.05M944K
DigitalOcean$0.70$2.20$0.105–––1.05M131K
Alibaba Cloudfp8$0.966$3.036$0.1932–––1M131K
FastTier$2.31$7.26$0.462
Cloudflare Workers AI$0.19$8.00$0.19–––262K236K
Z.aifp8$1.40$4.40$0.26Free––1.05M131K
Nebiusfp4$1.40$4.40$0.14–––1.05M944K
Basetenfp8$1.40$4.40$0.14–––1.05M262K
USRegion$2.10$6.60$0.21
FastTier$2.10$6.60$0.21
Together AI$1.40$4.40$0.26–––1.05M944K
Mistral$1.54$4.84$0.154–––1.05M128K
Zero data retentionTier$1.40$4.40$0.14

Prices in US dollars. Token prices are per 1 million tokens. abracadabra compiles them from each provider’s listing on OpenRouter, the LiteLLM price list and the providers’ own pricing pages, and refreshes them daily. The dataset is free to use: /api/ai-pricing.

See which tasks your agent finishes.

A price says what a call costs. abracadabra reads every conversation your agent has and shows the topics people bring, the tasks that get done and the turn where the rest stop.

Free to start, no card. Or open the playground (opens in a new tab).