DeepInfra vs OVHcloud
Same workloads, both price lists, refreshed daily. On shared line items today: DeepInfra is cheaper on 7 of 10 shared models (input or output price), OVHcloud on 1.
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
OVHcloud
European cloud giant with budget GPU instances (V100, L4, L40S, H100) and strong data-sovereignty guarantees. Pricing sits well below US hyperscalers for equivalent hardware.
- EU sovereignty
- Budget hourly pricing
- Anti-DDoS included
Shared models, priced by both
List prices refreshed 2026-08-23 ยท input $/1M tokens| Model | DeepInfra in/out | OVHcloud in/out | Cheaper input |
|---|---|---|---|
| Mistral Nemo | $0.020 / $0.040 | $0.130 / $0.130 | DeepInfra |
| Llama 3.1 8B | $0.030 / $0.050 | $0.100 / $0.100 | DeepInfra |
| GPT-OSS 20B | $0.040 / $0.150 | $0.040 / $0.150 | tie |
| GPT-OSS 120B | $0.050 / $0.450 | $0.080 / $0.400 | DeepInfra |
| Mistral Small 3.2 24B | $0.075 / $0.200 | $0.090 / $0.280 | DeepInfra |
| Qwen3 32B | $0.100 / $0.280 | $0.080 / $0.230 | OVHcloud |
| DeepSeek R1 Distill Llama 70B | $0.200 / $0.600 | $0.670 / $0.670 | DeepInfra |
| Llama 3.3 70B | $0.230 / $0.400 | $0.670 / $0.670 | DeepInfra |
| Llama 3.1 70B Instruct | $0.400 / $0.400 | $0.670 / $0.670 | DeepInfra |
| Mixtral-8x7B-Instruct-V0.1 | $0.400 / $0.400 | $0.630 / $0.630 | DeepInfra |
Cheaper-on-count is a tally of listed prices, not a quality verdict: throughput, reliability and quantization differ between providers. Disclosure.