DeepInfra vs Nebius
Same workloads, both price lists, refreshed daily. On shared line items today: DeepInfra is cheaper on 21 of 30 shared models (input or output price), Nebius on 5.
DeepInfra
Consistently the price floor for open-weight models: Llama, Qwen, DeepSeek at rock-bottom per-token rates with an OpenAI-compatible API and per-request GPU billing options..
- Among the cheapest open-model tokens anywhere
- OpenAI-compatible API
- Dedicated GPU deployments
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 | DeepInfra in/out | Nebius in/out | Cheaper input |
|---|---|---|---|
| Mistral Nemo | $0.019 / $0.030 | $0.040 / $0.120 | DeepInfra |
| Llama 3.1 8B | $0.030 / $0.050 | $0.020 / $0.060 | Nebius |
| GPT-OSS 120B | $0.037 / $0.170 | $0.150 / $0.600 | DeepInfra |
| Nemotron 3 Nano | $0.050 / $0.200 | $0.060 / $0.240 | DeepInfra |
| Llama-Guard-3-8B | $0.055 / $0.055 | $0.020 / $0.060 | Nebius |
| Qwen3 32B | $0.080 / $0.280 | $0.100 / $0.300 | DeepInfra |
| Gemma 3 27B | $0.080 / $0.160 | $0.100 / $0.300 | DeepInfra |
| Nemotron 3.5 Lightning | $0.080 / $0.200 | $0.060 / $0.240 | Nebius |
| Nemotron 3 Super | $0.085 / $0.400 | $0.300 / $0.900 | DeepInfra |
| DeepSeek V4 Flash | $0.090 / $0.180 | $0.140 / $0.280 | DeepInfra |
| Qwen3 30B A3B | $0.120 / $0.500 | $0.100 / $0.300 | Nebius |
| Qwen3 14B | $0.120 / $0.240 | $0.080 / $0.240 | Nebius |
| Qwen3 Next 80B A3B Thinking | $0.140 / $1.40 | $0.150 / $1.20 | DeepInfra |
| QwQ-32B | $0.150 / $0.400 | $0.150 / $0.450 | tie |
| Qwen3 235B A22B | $0.180 / $0.540 | $0.200 / $0.600 | DeepInfra |
| DeepSeek R1 Distill Llama 70B | $0.200 / $0.600 | $0.250 / $0.750 | DeepInfra |
| Llama 3.3 70B | $0.230 / $0.400 | $0.130 / $0.400 | Nebius |
| MiniMax M3 | $0.280 / $1.10 | $0.300 / $1.20 | DeepInfra |
| DeepSeek V3 | $0.320 / $0.890 | $0.500 / $1.50 | DeepInfra |
| Qwen2p5-72b | $0.360 / $0.400 | $0.130 / $0.400 | Nebius |
| Llama 3.1 70B Instruct | $0.400 / $0.400 | $0.130 / $0.400 | Nebius |
| Qwen3.8 27B | $0.400 / $3.00 | $0.450 / $3.00 | DeepInfra |
| Qwen3.5 397B A17B | $0.450 / $3.00 | $0.600 / $3.60 | DeepInfra |
| Nemotron 3 Ultra | $0.500 / $2.20 | $1.00 / $3.00 | DeepInfra |
| Kimi K2.7 Code | $0.680 / $3.40 | $0.950 / $4.00 | DeepInfra |
| DeepSeek R1 | $0.700 / $2.40 | $0.800 / $2.40 | DeepInfra |
| GLM-5.2 | $0.750 / $2.40 | $1.40 / $4.40 | DeepInfra |
| Kimi K2.6 | $0.750 / $3.50 | $0.950 / $4.00 | DeepInfra |
| Hermes 3 405B Instruct | $1.00 / $1.00 | $1.00 / $3.00 | tie |
| GLM-5.1 | $1.05 / $3.50 | $1.40 / $4.40 | DeepInfra |
Cheaper-on-count is a tally of listed prices, not a quality verdict: throughput, reliability and quantization differ between providers. Disclosure.