Baseten is a San Francisco company, founded in 2019, that provides infrastructure for deploying and serving machine learning models in production. It also publishes a small number of in-house models on its platform.
- Founded
- 2019
- Type
- Private company
- Founders
- Tuhin Srivastava, Amir Haghighat, Philip Howes and Pankaj Gupta
- AI lab
- Inference provider
- 31 hosted endpoints
| Model | Endpoint | Context | Input /M | Output /M | Cached input /M | Cache write /M | Uptime 1d |
|---|---|---|---|---|---|---|---|
| baseten/fp4 | 1M | $0.40 | $1.20 | $0.04 | — | 97.75% | |
| baseten/fp32 | 1M | $0.13 | $0.26 | $0.028 | — | 98.15% | |
| baseten/fp8 | 1M | $0.13 | $0.26 | $0.028 | — | 98.39% | |
| baseten/fp4 | 1M | $1.32 | $3.96 | $0.132 | — | 98.51% | |
| baseten | 1M | $0.30 | $1.20 | $0.007 | — | 97.29% | |
| baseten/us | 1M | $0.30 | $1.20 | $0.007 | — | 94.55% | |
| baseten | 1M | $0.30 | $1.20 | $0.007 | — | 98.54% | |
| baseten/fast | 1M | $0.60 | $2.40 | $0.014 | — | 98.19% | |
| baseten | 16K | $0.035 | $0.00 | — | — | 98.44% | |
| baseten/fast | 1M | $2.10 | $6.60 | $0.21 | — | 97.67% | |
| baseten/fp8 | 1M | $1.40 | $4.40 | $0.14 | — | 95.48% | |
| baseten/fp8/us | 1M | $1.40 | $4.40 | $0.14 | — | 98.87% | |
| baseten/us/fast | 1M | $2.10 | $6.60 | $0.21 | — | 97.70% | |
| baseten/fast | 1M | $2.10 | $6.60 | $0.21 | — | 98.92% | |
| baseten/fp4 | 1M | $1.40 | $4.40 | $0.14 | — | 98.54% | |
| baseten/fp4/us | 1M | $1.40 | $4.40 | $0.14 | — | 98.27% | |
| baseten/us/fast | 1M | $2.10 | $6.60 | $0.21 | — | 97.87% | |
| baseten/fp8 | 1M | $0.15 | $0.50 | $0.03 | — | 98.47% | |
| baseten/fp8/us | 1M | $0.15 | $0.50 | $0.03 | — | 0.00% | |
| baseten | 16K | $0.01 | $0.00 | — | — | 97.87% | |
| baseten/fp8 | 1M | $3.00 | $15.00 | $0.30 | — | 97.00% | |
| baseten | 16K | $0.10 | $0.00 | — | — | 98.89% | |
| baseten/fp4 | 1M | $1.25 | $4.25 | $0.15 | — | 98.22% | |
| baseten/fp4 | 203K | $0.60 | $2.40 | $0.12 | — | 96.92% | |
| baseten/fp4/us | 203K | $0.60 | $2.40 | $0.12 | — | 97.65% | |
| baseten/fp4 | 1M | $0.20 | $0.50 | $0.04 | — | 95.90% | |
| baseten/fp4 | 128K | $0.10 | $0.50 | $0.10 | — | 97.07% | |
| baseten/fp4/us | 128K | $0.10 | $0.50 | $0.10 | — | 98.47% |
