Microsoft Foundry Models — Pricing & Benchmarks

156 models available · Microsoft

Last refreshed 2026-11-10. Next refresh: weekly.

Microsoft Foundry hosts 156 AI models in this catalog. The lowest listed input price is Ministral 3B at $0.04/1M input tokens. LLM Reference compares these models across all 134 providers.

ModelInput (per 1M)Output (per 1M)Per hour of audioContext
Ministral 3B$0.04$0.04—128K
Microsoft-Decision-1$0.042Free—32K
Prompt Guard 86M$0.05$0.05—512
DeciCoder 1B$0.07$0.07—4K
Dolly 2.0 12B$0.07$0.07——
Phi-1.5$0.07$0.07—2K
Phi-2$0.07$0.07—2K
Qwen2-1.5B$0.07$0.07——
Phi-4 Mini$0.075$0.3—128K
Cohere Embed 5 Fast$0.08——128K
Claude Haiku 5.5$0.1$0.5—1M
Cohere Embed English v3.0$0.1——512
Cohere Embed Multilingual v3.0$0.1——512
Mistral Small 2503$0.1$0.3—32K
Cohere Embed 5 Pro$0.12——128K
Cohere Embed v4.0$0.12——128K
Phi 4 Reasoning Plus$0.125$0.5—128K
Mistral 7B v0.1$0.14$0.14—8K
DeepSeek V4 Flash$0.19$0.51—1M
Grok 4.1 Fast$0.2$0.5—128K
Grok Code Fast 1$0.2$1.50—256K
Llama 4 Scout 17B-16E Instruct$0.2$0.78—128K
Grok 3 Mini$0.25$1.27—128K
Mixtral 8x7B$0.27$0.27—32K
Phi-3 Mini 4k$0.28$0.84—4K
Phi-3 Vision$0.28$0.84—128K
Codestral 2501$0.3$0.9—256K
Llama 3.1 8B Instruct$0.3$0.61—128K
Mistral NeMo Instruct (2407)$0.3$0.3—128K
Phi-3 Mini 128K$0.3$0.9—128K
Phi-3 Small 8K$0.32$0.96—8K
Llama 4 Maverick 17B Instruct FP8$0.35$1.41—1M
Phi-3 Small 128K$0.35$1.05—128K
MAI-Transcribe-1$0.36———
Dolphin 2.9 Llama 3 8B$0.37$1.10—8K
Hermes 2 Pro Llama 3 8B$0.37$1.10—8K
Llama 3 8B Gradient 262K$0.37$1.10—262K
Llama 3 8B Instruct$0.37$1.10—8K
Llama 3 ChatQA 8B$0.37$1.10—8K
Llama 3.2 11B Vision Instruct$0.37$0.37—128K
Llama Guard 3 8B$0.37$1.10—8K
Nous Llama 3 8B$0.37$1.10—8K
Phi-3 Medium 4K$0.45$1.35—4K
Command R$0.5$1.50—128K
Jamba-Instruct$0.5$0.7—256K
Phi-3 Medium 128K$0.5$1.50—128K
CodeLlama 7B$0.52$0.67—100K
CodeLlama 7B Python$0.52$0.67—100K
DeciLM 7B$0.52$0.67—8K
Falcon 7B$0.52$0.67——
Llama 2 7B Chat$0.52$0.67—4K
Orca 2 7B$0.52$0.67—4K
SOLAR 10.7B$0.52$0.67—4K
GPT Realtime 2.1 Mini$0.6$2.40—128K
Llama 3.3 70B Instruct$0.71$0.71—128K
MAI-Code-1-Flash$0.75$4.50—256K
Command A+$0.8$3.20—128K
CodeLlama 13B$0.81$0.94—100K
CodeLlama 13B Python$0.81$0.94—100K
Fugaku-LLM 13B$0.81$0.94—4K
Llama 2 13B Chat$0.81$0.94—4K
Orca 2 13B$0.81$0.94—4K
WizardLM 13B V1.1$0.81$0.94—2K
Claude Haiku 4.5$1.00$5.00—200K
Mistral Small$1.00$3.00—32K
Smaug 72B$1.00$2.00—32K
Command R 08-2024$1.50$2.00—128K
Qwen1.5-110B$1.50$2.50—32K
CodeLlama 34B$1.54$1.77—100K
CodeLlama 34B Python$1.54$1.77—100K
Falcon 40B$1.54$1.77——
Llama 2 70B Chat$1.54$1.77—4K
Arctic$2.00$2.00—4K
Claude Sonnet 5.5$2.00$10.00—1M
MAI-Thinking-1$2.00$8.00—256K
Llama 3.2 90B Vision Instruct$2.04$2.04—128K
Command A$2.50$10.00—256K
Command R+ 08-2024$2.50$10.00—128K
Llama 3.1 70B Instruct$2.68$3.54—128K
DBRX Instruct$2.70$2.70—32K
Claude Sonnet 4.5$3.00$15.00—200K
Claude Sonnet 4.6$3.00$15.00—1M
Command R+$3.00$15.00—128K
Grok 4$3.00$15.00—256K
Grok-3$3.00$15.00—128K
Mistral Large 2 (2407)$3.00$9.00—128K
Jais 30B$3.20$9.71—2K
CodeLlama 70B$3.78$11.34—16K
CodeLlama 70B Python$3.78$11.34—16K
Llama 3 70B Instruct$3.78$11.34—8K
Llama 3 ChatQA 70B$3.78$11.34—8K
Llama 3 TenyxChat 70B$3.78$11.34——
Claude Opus 5.5$4.00$20.00—1M
GPT Realtime 2.1$4.00$24.00—128K
Mistral Large$4.00$12.00—32K
Claude Opus 4.5$5.00$25.00—200K
Claude Opus 4.6$5.00$25.00—1M
Claude Opus 4.7$5.00$25.00—1M
MAI-Image-2$5.00$33.00——
MAI-Image-2.6$5.00$38.00——
Llama 3.1 405B Instruct$5.33$16.00—128K
Claude Fable 5$10.00$50.00—1M
Claude Fable 5.1$10.00$50.00—1M
Claude Mythos 5.1$10.00$50.00—1M
Claude Opus 4.1$15.00$75.00—200K
MAI-Voice-1$22.00———
Bria 2.3 Fast————
Claude 3.5 Sonnet———200K
Claude Mythos Preview———1M
Claude Opus 4.8———200K
Claude Opus 5———1M
Claude Sonnet 5———1M
Cohere Rerank v3.5———4K
Cohere Rerank v4.0 Fast———32K
Cohere Rerank v4.0 Pro———32K
DeepSeek R1———128K
DeepSeek R1 0528———160K
DeepSeek V3———64K
DeepSeek V3 0324———128K
DeepSeek V3.1———128K
DeepSeek V3.2———128K
DeepSeek V3.2 Speciale———128K
FLUX.1.1 [pro]————
Grok 4 Fast Non-Reasoning———2M
Grok 4 Fast Reasoning———2M
Grok 4.3———200K
Kimi K2.5———256K
Kimi K2.6———256K
MAI-Code-1————
MAI-Image-2.5————
MAI-Image-2.5-Flash————
MAI-Image-2.6-Flash————
MAI-Image-2e————
MAI-Transcribe-1.5————
MAI-Transcribe-2——$0.10 / hour of audio—
MAI-Transcribe-2-Streaming——$0.54 / hour of audio—
MAI-Voice-2————
MAI-Voice-2.1$22.00/1M chars———
MAI-Voice-2.1-Flash$15.00/1M chars———
Mistral Document AI 2505————
Mistral Document AI 2512————
Mistral Large 2.1 (2411)———128K
Mistral Large 3 675B Instruct———128K
Mistral Medium 3———128K
Mixtral 8x22B v0.1———64K
Phi 4 Multimodal Instruct———128K
Phi 4 Reasoning———32K
Phi-4 14B———16K
Qwen2-72B———128K
Qwen2-7B———128K
Rerank English V3———4K
Rerank Multilingual V3———4K
Stable Diffusion 3.5 Large————
Stable Image Core————
Stable Image Ultra————
TimeGEN-1————

Where else to run this

Pricing Overview

Cheapest$0.04/1M
Most expensive$22.00/1M

About Microsoft Foundry

Microsoft Foundry offers a comprehensive platform-as-a-service for enterprise AI operations. It provides multiple deployment options including Serverless APIs (pay-as-you-go), Global Standard (shared managed capacity), Provisioned Throughput Units (reserved capacity), batch processing, and bring-your-own model deployments. The platform features a unified control plane for models, agents, tools, and observability. Its Agent Service enables building and deploying AI agents with built-in tracing, monitoring, and governance. Evaluation and monitoring tools assess model performance, safety, and groundedness. Foundry supports seamless upgrades from Azure OpenAI with non-destructive migration, maintaining existing deployments while unlocking multi-provider model access and advanced platform capabilities.

Full provider profile →