Baseten vs Nebius
Same workloads, both price lists, refreshed daily. On shared line items today: Baseten is cheaper on 4 of 13 shared models (input or output price), Nebius on 0.
Baseten
Production inference platform with Truss packaging, optimized serving engines and enterprise-grade autoscaling. Strong for teams shipping custom models with SLAs.
- Optimized model serving (TensorRT-LLM)
- Enterprise autoscaling and observability
Nebius
AI cloud from the former Yandex team with H100/H200/B200 clusters in Europe and the US, plus Nebius AI Studio for per-token open-weight inference. Competitive pricing at cluster scale.
- European datacenters
- Both clusters and per-token inference
- Aggressive large-scale pricing
Shared models, priced by both
List prices refreshed 2026-10-08 ยท input $/1M tokens| Model | Baseten in/out | Nebius in/out | Cheaper input |
|---|---|---|---|
| GPT-OSS 120B | $0.100 / $0.500 | $0.150 / $0.600 | Baseten |
| DeepSeek V4 Flash | $0.130 / $0.260 | $0.140 / $0.280 | Baseten |
| GLM 5.3 Flash | $0.150 / $0.500 | $0.150 / $0.500 | tie |
| DeepSeek V4.1 Flash | $0.300 / $1.20 | $0.300 / $1.20 | tie |
| MiniMax M2.5 | $0.300 / $1.20 | $0.300 / $1.20 | tie |
| Nemotron 3 Ultra | $0.600 / $2.40 | $1.00 / $3.00 | Baseten |
| DeepSeek V3 | $0.770 / $0.770 | $0.500 / $1.50 | Nebius |
| Kimi K2.6 | $0.950 / $4.00 | $0.950 / $4.00 | tie |
| Kimi K2.7 Code | $0.950 / $4.00 | $0.950 / $4.00 | tie |
| GLM-5.2 | $1.40 / $4.40 | $1.40 / $4.40 | tie |
| GLM 5.3 | $1.40 / $4.40 | $1.40 / $4.40 | tie |
| DeepSeek V4 Pro | $1.74 / $3.48 | $1.75 / $3.50 | Baseten |
| Kimi K3 | $3.00 / $15.00 | $3.00 / $15.00 | tie |
Cheaper-on-count is a tally of listed prices, not a quality verdict: throughput, reliability and quantization differ between providers. Disclosure.