Last refreshed 2026-06-04. Next refresh: weekly.
Why use Phi 4 Reasoning on Microsoft Foundry?
Microsoft Foundry offers Phi 4 Reasoning with competitive pricing. Microsoft Foundry is a unified Azure platform-as-a-service offering for enterprise AI operations, model builders, and application development.
Compare Phi 4 Reasoning across 2 providers to find the best fit for your use caseSetup recipe
Docs fallbackUse the provider REST API or SDKCreate a provider API keymodel: phi-4-reasoningphi-4-reasoningRequest example
phi-4-reasoning.Gotchas
No curated gotchas have been sourced for this exact provider/model route yet.
Compare Phi 4 Reasoning Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| Fireworks AI | $0.50 | $0.50 |
| Microsoft Foundry | — | — |
Capabilities
About Phi 4 Reasoning
Phi 4 Reasoning is Microsoft Research's Phi-4 model focused on step-by-step reasoning. It offers a 128K-token context window with weights openly available for self-hosting and scores 65.8 on GPQA.
FAQ
What is the context window for Phi 4 Reasoning on Microsoft Foundry?
Phi 4 Reasoning supports a 33k token context window on Microsoft Foundry.
How does Microsoft Foundry compare to other Phi 4 Reasoning providers?
Phi 4 Reasoning is available from 2 providers. The cheapest input pricing is $0.5/1M tokens from Fireworks AI.
What API model ID do I use for Phi 4 Reasoning on Microsoft Foundry?
Use the model ID phi-4-reasoning when calling Microsoft Foundry's API.
Who created Phi 4 Reasoning?
Phi 4 Reasoning was created by Microsoft Research as part of the Phi-4 model family.
Is Phi 4 Reasoning open source?
Phi 4 Reasoning is open source under MIT according to the seed data.