Azure AI Foundry

Cloud platform · 60 models · 107 priced routes · azure.microsoft.com

Models on Azure AI Foundry

About Azure AI Foundry

Microsoft Corporation is an American multinational technology company headquartered in Redmond, Washington.

Batch: Batch API returns completions within 24 hours for a 50% discount on Global Standard Pricing

Across GlyphCompany profile 18 acquisitions Next earnings 2026-11-04 Paid biweekly 88 releases, latest 2026-09-18 21 conferences

Model	In / out per 1M	Vs headline
Text Embedding 3 Small text-embedding-3-small is OpenAI's improved, more performant version of the ada embedding model.	$0.02 / FreeSame vs headline	Same	text-embedding-3-small is OpenAI's improved, more performant version of the ada embedding model.
Text Embedding 3 Large text-embedding-3-large is OpenAI's most capable embedding model for both english and non-english tasks.	$0.13 / FreeSame vs headline	Same	text-embedding-3-large is OpenAI's most capable embedding model for both english and non-english tasks.
GPT-5 Nano GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments.	$0.05 / $0.4Same vs headline	Same	GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments.
GPT-5 Nano swedencentral · GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments.	$0.055 / $0.44+10% vs headline	+10%	swedencentral · GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments.
GPT-4.1 Nano For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series.	$0.1 / $0.4Same vs headline	Same	For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series.
GPT-4.1 Nano swedencentral · For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series.	$0.11 / $0.44+10% vs headline	+10%	swedencentral · For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series.
GPT-6 Luna Pro GPT-6 Luna Pro is the same underlying model as GPT-6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks.	$0.1 / $0.5Same vs headline	Same	GPT-6 Luna Pro is the same underlying model as GPT-6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks.
GPT-6 Luna GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol.	$0.1 / $0.5Same vs headline	Same	GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol.
Claude Haiku 5.5 global · Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use.	$0.1 / $0.5Same vs headline	Same	global · Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use.
GPT-6 Luna Pro us · GPT-6 Luna Pro is the same underlying model as GPT-6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks.	$0.11 / $0.55+10% vs headline	+10%	us · GPT-6 Luna Pro is the same underlying model as GPT-6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks.
GPT-6 Luna Pro eu · GPT-6 Luna Pro is the same underlying model as GPT-6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks.	$0.11 / $0.55+10% vs headline	+10%	eu · GPT-6 Luna Pro is the same underlying model as GPT-6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks.
GPT-6 Luna us · GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol.	$0.11 / $0.55+10% vs headline	+10%	us · GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol.
GPT-6 Luna eu · GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol.	$0.11 / $0.55+10% vs headline	+10%	eu · GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol.
Claude Haiku 5.5 us · Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use.	$0.11 / $0.55+10% vs headline	+10%	us · Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use.
GPT-4o-mini GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs.	$0.15 / $0.6Same vs headline	Same	GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs.
GPT-4o-mini swedencentral · GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs.	$0.165 / $0.66+10% vs headline	+10%	swedencentral · GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs.
DeepSeek V4 Flash 0423 us · DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window.	$0.21 / $0.56+164% vs headline	+164%	us · DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window.
GPT-5.6 Luna Pro GPT-5.6 Luna Pro is the same underlying model as GPT-5.6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks.	$0.2 / $1.2Same vs headline	Same	GPT-5.6 Luna Pro is the same underlying model as GPT-5.6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks.
GPT-5.6 Luna GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series.	$0.2 / $1.2Same vs headline	Same	GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series.
GPT-5.4 Nano GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks.	$0.2 / $1.25Same vs headline	Same	GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks.