Azure AI Foundry vs DeepInfra
Same workloads, both price lists, refreshed daily. On shared line items today: Azure AI Foundry is cheaper on 0 of 24 shared models (input or output price), DeepInfra on 16.
Azure AI Foundry
OpenAI models with Azure enterprise controls plus a broad third-party model catalog. The compliance-friendly way to run GPT-class models.
- Azure compliance/enterprise controls
- OpenAI models with SLAs
- Provisioned throughput
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
Shared models, priced by both
List prices refreshed 2026-08-28 ยท input $/1M tokens| Model | Azure AI Foundry in/out | DeepInfra in/out | Cheaper input |
|---|---|---|---|
| Phi-4 | $0.125 / $0.500 | $0.070 / $0.140 | DeepInfra |
| GPT-OSS 120B | $0.150 / $0.600 | $0.037 / $0.170 | DeepInfra |
| Mistral Nemo | $0.150 / $0.150 | $0.019 / $0.030 | DeepInfra |
| DeepSeek V4 Flash | $0.190 / $0.510 | $0.090 / $0.180 | DeepInfra |
| Llama 4 Scout | $0.200 / $0.780 | $0.100 / $0.300 | DeepInfra |
| Llama 3.1 8B | $0.300 / $0.610 | $0.030 / $0.050 | DeepInfra |
| Llama-3.2-11b-Vision-Instruct | $0.370 / $0.370 | $0.049 / $0.049 | DeepInfra |
| DeepSeek V3.2 | $0.580 / $1.68 | $0.260 / $0.380 | DeepInfra |
| Kimi K2.5 | $0.600 / $3.00 | $0.450 / $2.25 | DeepInfra |
| Llama 3.3 70B | $0.710 / $0.710 | $0.230 / $0.400 | DeepInfra |
| Kimi K2.6 | $0.950 / $4.00 | $0.750 / $3.50 | DeepInfra |
| Claude Haiku 4.5 | $1.00 / $5.00 | $1.00 / $5.00 | tie |
| DeepSeek V3 | $1.14 / $4.56 | $0.320 / $0.890 | DeepInfra |
| DeepSeek-V3.1 | $1.23 / $4.94 | $0.250 / $0.950 | DeepInfra |
| DeepSeek R1 | $1.35 / $5.40 | $0.700 / $2.40 | DeepInfra |
| Llama 4 Maverick | $1.41 / $0.350 | $0.200 / $0.800 | DeepInfra |
| DeepSeek V4 Pro | $1.74 / $3.48 | $1.30 / $2.60 | DeepInfra |
| Claude Sonnet 5 | $2.00 / $10.00 | $2.00 / $10.00 | tie |
| Llama 3.1 70B Instruct | $2.68 / $3.54 | $0.400 / $0.400 | DeepInfra |
| Claude Sonnet 4.6 | $3.00 / $15.00 | $3.00 / $15.00 | tie |
| Claude Opus 4.7 | $5.00 / $25.00 | $5.00 / $25.00 | tie |
| Claude Opus 5 | $5.00 / $25.00 | $5.00 / $25.00 | tie |
| Claude Opus 4.8 | $5.00 / $25.00 | $5.00 / $25.00 | tie |
| Claude Fable 5 | $10.00 / $50.00 | $10.00 / $50.00 | tie |
Cheaper-on-count is a tally of listed prices, not a quality verdict: throughput, reliability and quantization differ between providers. Disclosure.