Azure AI Foundry pricing
Microsoft Foundry Models is Azure's catalog of hosted models, including Azure OpenAI, gpt-oss, DeepSeek, Llama and Mistral, with Global, Data Zone, regional and provisioned deployments.
Go to Azure AI Foundry Compare with Amazon Bedrock, Featherless AI, Fireworks AI Request a quote
Every field, sourced
Marker opens the source- Status Whether the provider's public inference API is live.
- Active 1
- Hardware Chips that serve requests: GPUs, the vendor's own custom silicon, or both.
- Not published
- Hardware detail Published chip types (e.g. LPU, wafer-scale engine, RDU, NVIDIA H100/B200).
- Not published
- OpenAI API Accepts OpenAI Chat Completions-style requests, per vendor docs.
- Yes 1
- Serverless Pay-per-use API billed per token or per second, with no GPU to manage.
- Yes 1
- Dedicated Single-tenant deployments or reserved capacity.
- Yes 1
- Fine-tuning Hosted fine-tuning or LoRA adapters offered.
- Yes 1
- Models (published) models Model count as published or counted from the official model list on the verified date.
- Not published
- Flagship models Notable models served, from the official list.
- gpt-oss-120b, gpt-oss-20b, DeepSeek-V4-Pro, Llama 4 Maverick, Mistral Large 3 1
- Serves gpt-oss-120b Offers the reference model gpt-oss-120b pay-per-token.
- Yes 1
- gpt-oss-120b in $/1M tok Standard serverless input price for the reference model gpt-oss-120b, per 1M tokens.
- $0.15 2
- gpt-oss-120b out $/1M tok Standard serverless output price for the reference model gpt-oss-120b, per 1M tokens.
- $0.60 2
- Llama 3.3 70B in $/1M tok Secondary reference: Llama 3.3 70B Instruct input price per 1M tokens, where still listed.
- $0.71 6
- Llama 3.3 70B out $/1M tok Secondary reference: Llama 3.3 70B Instruct output price per 1M tokens, where still listed.
- $0.71 6
- Vendor speed tok/s Vendor-stated output speed on gpt-oss-120b, linked to the vendor’s own page.
- Not published
- Speed source Who published the speed figure and when.
- Not published
- Dedicated H100 $/GPU-hr On-demand price of one H100 for dedicated deployments.
- Not published
- Regions Published serving or data regions.
- Many Azure regions; Global, Data Zone and regional deployments 1
- SOC 2 SOC 2 status as stated by the vendor.
- Type 2 5
- HIPAA Vendor states HIPAA support or offers a BAA.
- Not published
- ZDR Zero data retention: the vendor states prompts and outputs are not stored, by default or as a setting.
- Yes 4
- Free tier Free credits or free rate-limited access, as published.
- Not published
Pricing detail
gpt-oss-120B Global $0.15 / $0.60 (Data Zone $0.165 / $0.66); Llama 3.3 70B $0.71 / $0.71 per 1M (Azure Retail Prices API, East US 2). gpt-oss-120b in Preview. Prompts/completions not stored in the model; abuse monitoring may store flagged prompts.
Sources
- Foundry Models pricing accessed 2026-11-09
- Azure Retail Prices API accessed 2026-11-09
- Foundry Models sold by Azure accessed 2026-11-09
- Data, privacy, and security accessed 2026-11-09
- Azure SOC 2 Type 2 accessed 2026-11-09
- Azure Retail Prices API (Llama 3.3 70B, East US 2) accessed 2026-11-09
Get dedicated or volume pricing from Azure AI Foundry and similar providers
Tell us what you need once. We send it to matching providers and they reply to you directly.