GPU cloud
Baseten
/baseten · San Francisco, USA · est. 2019
Data: mediumVisit provider ↗
Key facts
- Baseten is a gpu cloud headquartered in San Francisco, USA, founded 2019.
- Exposes an OpenAI-compatible API, so existing OpenAI SDK code can target it by changing the base URL.
- Blended reference price is $0.80 per 1M tokens (in $0.70 / out $0.90).
- Reference latency 280 ms TTFT at 140 tok/s throughput, with 99.6% reference uptime.
- Editorial reputation index 84/100 from 260 weighted signals; 90-day trend improving.
Specification
- Category
- GPU cloud
- Headquarters
- San Francisco, USA
- Founded
- 2019
- Model access
- Open weights
- Flagship / served
- Dedicated + Model APIs
- Reference open model
- Llama 3.3 70B
- OpenAI-compatible API
- Yes
- Blended $/1M
- $0.80 seed
Strengths & trade-offs
Strength
Production dedicated deployments with strong autoscaling.
Trade-off
Dedicated capacity costs more than shared per-token tiers.
Profile reviewed 2026-07-10. Confidence for this listing:medium — Figure based on public sources but not re-confirmed on the exact review date; may drift.Not affiliated with Baseten. ← Back to directory