Phi 4 Reasoning
Phi 4 Reasoning is worth evaluating for long context when its provider route and context window match the workload.
Use it for
- Teams evaluating long context
- Workloads that can use a 128k context window
- Buyers comparing 2 tracked provider routes
Do not use it for
- Vision or document-understanding workloads
- Strict JSON or tool-calling flows
Advancing the state-of-the-art in AI and computing.
Cheapest of 2 routes · Fireworks AI
About
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.
Phi 4 Reasoning is an open-source model in the Phi-4 family. The structured metadata tracks a 128k-token context window and reasoning. This page tracks provider routes through Fireworks AI and Microsoft Foundry, with the cheapest tracked route listed at $0.5 input and $0.5 output per 1M tokens. Headline tracked benchmarks include Google-Proof Q&A 65.8.
Top use-case fit
Long context
Included by capability and metadata signals in the decision map.
Provider price ladder
Compare all 2Compare API pricing across 2 providers for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| Fireworks AI | $0.500 | $0.500 | Serverless |
| Microsoft Foundry | - | - | ServerlessPartial |
Available via routers & gateways(6)
LiteLLM
GatewayOpen-source Python SDK and proxy server that unifies 100+ LLM APIs behind a single OpenAI-compatible interface, with load balancing, cost tracking, and configurable failover.
OpenRouter
HybridUnified hybrid gateway to 400+ models from 60+ providers via a single OpenAI-compatible API, with optional auto-routing that selects the best model per prompt.
Portkey
GatewayProduction AI gateway routing to 1,600+ LLMs with failover, load balancing, semantic caching, and guardrails; Apache 2.0 core is fully self-hostable with the complete feature set.
Azure AI Foundry Model Router
RouterMicrosoft Azure AI Foundry's native model router that uses a trained ML model to route each prompt in real time to the optimal Azure-hosted model, with Balanced/Cost/Quality mode selection and automatic failover.
Helicone
GatewayObservability-first AI gateway with routing, caching, rate limiting, and request tracing; Apache 2.0 open-source core with a managed hosted tier for logging and analytics.
Kong AI Gateway
GatewayMulti-LLM AI gateway built on Kong Gateway 3.x, adding semantic routing, load balancing, guardrails, and MCP traffic analytics as plugins over Kong's existing API management platform.
Capabilities
Benchmark peer barsfor Long context
No task-mapped benchmark peers are available for this model yet.
Benchmark scores(1)
| Benchmark | Score | Version | Source |
|---|---|---|---|
| Google-Proof Q&A | 65.8 | diamond | https://huggingface.co/microsoft/Phi-4-reasoning-plus |
Migration checks
No linked migration route is available for this model yet.
Frequently asked questions
What is the context window of Phi 4 Reasoning?
Phi 4 Reasoning has a context window of 128k tokens.
How much does Phi 4 Reasoning cost?
Phi 4 Reasoning is available at $0.5/1M input tokens through Fireworks AI.
When was Phi 4 Reasoning released?
Phi 4 Reasoning was released on 2025-01-01.
Which providers offer Phi 4 Reasoning?
Phi 4 Reasoning is available from 2 providers: Fireworks AI, Microsoft Foundry.
What benchmarks has Phi 4 Reasoning been tested on?
Phi 4 Reasoning has been evaluated on 1 benchmark, including Google-Proof Q&A.
Advancing the state-of-the-art in AI and computing.
Cheapest of 2 routes · Fireworks AI