How much does GLM-5.3 Flash cost on Modal?
This checkpoint of GLM-5.3 Flash costs $0.45 per million input tokens, $0.09 per million cached input tokens, and $1.50 per million output tokens. The table compares it with the NVIDIA checkpoint.
The examples below use illustrative token counts for coding agents and assume 95% of input tokens are cache hits.
| Workload | Input / output tokens | Z.ai checkpoint | NVIDIA checkpoint |
|---|---|---|---|
| Live coding agent session | 3M / 75K | $0.44 | $0.15 |
| Background agent from issue to pull request | 30M / 200K | $3.54 | $1.18 |
| Automated review of 100 pull requests | 50M / 1M | $6.90 | $2.30 |
Actual costs depend on token usage and cache hits. Estimates use Modal's current pricing.
Use GLM-5.3 Flash in your coding agent
Modal is supported natively in coding harnesses like Claude Code, Codex, OpenCode, Omp, and Hermes Agent. You can use GLM-5.3 Flash or any other model supported in Model APIs. See the setup steps for each agent.



