Tenstorrent
- Inference provider
- 5 hosted endpoints
| Model | Endpoint | Context | Input /M | Output /M | Cached input /M | Cache write /M | Uptime 1d |
|---|---|---|---|---|---|---|---|
 GLM 5.3 | tenstorrent/fp8 | 1M | $0.60 | $2.50 | $0.10 | — | 99.85% |
| GLM 5.3 Flash | tenstorrent/fp8 | 262K | $0.075 | $0.25 | $0.015 | — | 99.51% |
 MiMo-V2.6-Flash | tenstorrent/fp8 | 1M | $0.165 | $0.33 | $0.004 | — | 95.28% |
 Qwen3 32B | tenstorrent/fp8 | 20K | $0.14 | $0.40 | $0.09 | — | 98.45% |
| Qwen3.8 27B | tenstorrent/fp8 | 262K | $0.15 | $1.60 | $0.05 | — | 99.86% |