Baseten pricing & review
Production inference platform with Truss packaging, optimized serving engines and enterprise-grade autoscaling. Strong for teams shipping custom models with SLAs.
Where Baseten wins
- Optimized model serving (TensorRT-LLM)
- Enterprise autoscaling and observability
Baseten model pricing
List prices refreshed 2026-08-23 ยท cheapest 25 shown| Model | Input $/1M | Output $/1M | Market floor in |
|---|---|---|---|
| GPT-OSS 120B | $0.100 | $0.500 | $0.050at DeepInfra |
| MiniMax M2.5 | $0.300 | $1.20 | $0.300at AWS Bedrock |
| DeepSeek-V3.1 | $0.500 | $1.50 | $0.270at DeepInfra |
| Kimi K2 | $0.600 | $2.50 | $0.500at DeepInfra |
| GLM-4.7 | $0.600 | $2.20 | $0.400at GMI Cloud |
| Kimi K2 Thinking | $0.600 | $2.50 | $0.600at AWS Bedrock |
| Kimi K2.5 | $0.600 | $3.00 | $0.500at Together AI |
| GLM-4.6 | $0.600 | $2.20 | $0.400at OpenRouter |
| DeepSeek V3 | $0.770 | $0.770 | $0.200at Hyperbolic |
| GLM-5 | $0.950 | $3.15 | $0.800at OpenRouter |