# GLM 5.2 Fast API prices

GLM 5.2 Fast (glm) — 1.0M context, 1.0M max output.
6 metered per-token offers from 6 provider(s), in USD per 1M tokens.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Neuralwatt | $1.45 | $4.5 | $0.145 | 1.0M |
| Baseten | $2.1 | $6.6 | $0.21 | 1.0M |
| Fireworks AI | $2.1 | $6.6 | $0.21 | 1.0M |
| Requesty | $2.1 | $6.6 | $0.21 | 1.0M |
| Vercel AI Gateway | $2.1 | $6.6 | $0.21 | 1.0M |
| above.dev | $2.31 | $7.26 | $0.231 | 1.0M |

## Summary

- Cheapest input: $1.45 per 1M tokens (Neuralwatt)
- Cheapest output: $4.5 per 1M tokens (Neuralwatt)
- First-party: not listed separately
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2026-06-13
- Inputs: image, text

HTML page: https://llmprice.gitlab.io/models/glm-5-2-fast/
Full dataset: https://llmprice.gitlab.io/data/catalog.json