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 12 shared models (input or output price), DeepInfra on 11.

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

Visit Azure AI Foundry

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

Visit DeepInfra

Shared models, priced by both

List prices refreshed 2026-08-23 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 $0.050 / $0.450 DeepInfra
Mistral Nemo $0.150 / $0.150 $0.020 / $0.040 DeepInfra
Llama 4 Scout $0.200 / $0.780 $0.080 / $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
Llama 3.3 70B $0.710 / $0.710 $0.230 / $0.400 DeepInfra
DeepSeek V3 $1.14 / $4.56 $0.380 / $0.890 DeepInfra
DeepSeek-V3.1 $1.23 / $4.94 $0.270 / $1.00 DeepInfra
DeepSeek R1 $1.35 / $5.40 $0.700 / $2.40 DeepInfra
Llama 4 Maverick $1.41 / $0.350 $0.150 / $0.600 DeepInfra
Llama 3.1 70B Instruct $2.68 / $3.54 $0.400 / $0.400 DeepInfra

Cheaper-on-count is a tally of listed prices, not a quality verdict: throughput, reliability and quantization differ between providers. Disclosure.