LLM Reference
Microsoft Foundry

Microsoft Foundry

Researched todayHyperscalerTier 1

Microsoft

CodingRAGAgentsLong contextVisionClassificationJSON / Tool useHyperscaler

Microsoft Foundry offers 134 tracked models (87 with output token pricing). This catalog covers coding, rag, and agents; open any model detail page for benchmarks, batch tiers, and migration prompts.

Covers 7 workload areas across 134 tracked models; last verified 2026-06-27.

Use it for

  • Teams comparing token and batch pricing across this provider's models
  • Operators routing coding, rag, and agents workloads through this API

Do not use it for

  • Final benchmark picks without opening the relevant model detail page

Tracked models

134

Models available through this provider

Priced output routes

87

Models with output token pricing tracked

Cheapest output

$0.040

Mistral Ministral 3B on this route

Batch-ready models

0

No batch pricing tracked

Latest model release

2026-06-09

18d since newest release

Freshness

2026-06-27

Researched today

fresh

Routes available via routers & gateways

These routers list Microsoft Foundry as a target provider, so they can sit in front of this catalog for fallback, routing, or unified API access.

Browse routers ->

Information

TypeHyperscaler
TierTier 1
Models134
CompanyMicrosoft
Founded2025
Redmond, Washington, United States

Microsoft Foundry is a unified Azure platform-as-a-service offering for enterprise AI operations, model builders, and application development. It provides access to over 1,900 models from Microsoft, OpenAI, Anthropic, Mistral, xAI, Meta, DeepSeek, Hugging Face, and more. Foundry unifies agents, models, and tools under a single management grouping with built-in enterprise-readiness capabilities including tracing, monitoring, evaluations, and customizable enterprise setup configurations.

Catalog freshness

The newest model tracked on this provider was released 2026-06-09 (18d ago).

Where this host wins

  • Coding: 45 tracked models with SWE-bench / HumanEval-style scores.
  • RAG: 34 tracked models with ruler / needle retrieval benchmarks.
  • Agentic: 29 tracked models with BFCL, tau-bench, and SWE-bench tool-use coverage.
  • Long-context: 48 tracked models with context-token or InfiniteBench-class signal.

Getting started

Official product, docs, and pricing links — confirm quotas and regions in the vendor docs.

Compliance notes

No verified compliance claims (SOC 2, ISO, HIPAA) tracked for this provider yet — check the vendor's trust center for current certifications.

Platform Overview

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.

Compare per-model pricing, input and output token costs, batch availability, and benchmark coverage.

Available Models(134)

View all →
ModelInput (per 1M)Output (per 1M)Image (medium)Type
Claude Fable 5$10$50
Serverless
MAI-Code-1
Serverless
MAI-Code-1-Flash$0.75$4.50
Serverless
MAI-Image-2.5
Serverless
MAI-Image-2.5-Flash
Serverless
MAI-Thinking-1
Serverless
MAI-Transcribe-1.5
Serverless
MAI-Voice-2
Serverless
Claude Opus 4.8
Serverless
Grok 4.3
Serverless
View full catalog →