GLM 5.3 Flash pricing
GLM 5.3 Flash from Z.ai runs on 12 providers. The lowest price is $0.084 input and $0.28 output per 1M tokens, on Novita AI. On Z.ai it costs 1.8× as much.
Updated
- Lab
- Z.ai
- Context
- 1.05M
- Input
- Text and images
- Providers
- 12
Novita AI$0.133Lowest
DigitalOcean$0.1781.3×- CoreWeave$0.1851.4×
Mistral$0.2371.8×
Cohere$0.2371.8×
Nebius$0.2371.8×
Baseten$0.2371.8×
Crusoe$0.2371.8×
Fireworks AI$0.2371.8×
Together AI$0.2371.8×
DeepInfra$0.2371.8×
Z.ai$0.2371.8×
Every price, by provider
| Provider | Input | Output | Cached | Cache write | Batch in | Batch out | Context | Max output |
|---|---|---|---|---|---|---|---|---|
| Novita AIfp8 | $0.084 | $0.28 | $0.0168 | – | – | – | 1.05M | 131K |
| DigitalOcean | $0.1125 | $0.375 | $0.03 | – | – | – | 1.05M | 131K |
| CoreWeavenvfp4 | $0.12 | $0.38 | $0.02 | – | – | – | 1.05M | 944K |
| Z.aifp8 | $0.15 | $0.50 | $0.03 | Free | – | – | 1.05M | 131K |
| Mistral | $0.15 | $0.50 | $0.03 | – | – | – | 1.05M | 131K |
| Coherenvfp4 | $0.15 | $0.50 | $0.03 | – | – | – | 1.05M | 131K |
| Nebiusfp4 | $0.15 | $0.50 | $0.03 | – | – | – | 1.05M | 944K |
| Basetenfp8 | $0.15 | $0.50 | $0.03 | – | – | – | 1.05M | 131K |
| Crusoefp4 | $0.15 | $0.50 | $0.03 | – | – | – | 1.05M | 944K |
| Fireworks AI | $0.15 | $0.50 | $0.03 | – | $0.075 | $0.25 | 1.05M | 944K |
| Together AI | $0.15 | $0.50 | $0.03 | – | – | – | 1.05M | 944K |
| DeepInfrafp4 | $0.15 | $0.50 | $0.03 | – | $0.12 | $0.40 | 1.05M | 944K |
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).