Phi-4 14B
Phi-4 14B is worth evaluating for classification and json / tool use when its provider route and context window match the workload.
Use it for
- Teams evaluating classification and json / tool use
- Workloads that can use a 16k context window
- Buyers comparing 3 tracked provider routes
Do not use it for
- Vision or document-understanding workloads
Advancing the state-of-the-art in AI and computing.
Cheapest of 3 routes · OpenRouter
About
Phi-4 14B is Microsoft Research's Phi-4 model. Weights are openly available for self-hosting and scores 56.1 on GPQA.
Phi-4 14B is an open-source model in the Phi-4 family. The structured metadata tracks a 16k-token context window and structured outputs. This page tracks provider routes through OpenRouter, Fireworks AI, and Microsoft Foundry, with the cheapest tracked route listed at $0.065 input and $0.14 output per 1M tokens. Headline tracked benchmarks include Google-Proof Q&A 56.1 and Massive Multitask Language Understanding 84.8.
Top use-case fit
Classification
Q/$ A1 relevant benchmark in the decision map.
JSON / Tool use
Included by capability and metadata signals in the decision map.
Provider price ladder
Compare all 3Compare API pricing across 3 providers for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| OpenRouter | $0.065 | $0.140 | Serverless |
| Fireworks AI | $0.900 | $0.900 | 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 Classification
Benchmark scores(2)
| Benchmark | Score | Version | Evaluation | Source |
|---|---|---|---|---|
| Google-Proof Q&A | 56.1 | —Observed 2026-04-28 | — | Source |
| Massive Multitask Language Understanding | 84.8 | —Observed 2026-04-28 | — | Source |
Migration checks
No linked migration route is available for this model yet.
Compare Phi-4 14B with other models
Comparison and alternatives
Browse all comparisons →Frequently asked questions
What is the context window of Phi-4 14B?
Phi-4 14B has a context window of 16k tokens.
How much does Phi-4 14B cost?
Phi-4 14B pricing ranges from $0.065/1M to $0.9/1M input tokens depending on the provider.
When was Phi-4 14B released?
Phi-4 14B was released on 2024-12-13.
Which providers offer Phi-4 14B?
Phi-4 14B is available from 3 providers: OpenRouter, Fireworks AI, Microsoft Foundry.
What benchmarks has Phi-4 14B been tested on?
Phi-4 14B has been evaluated on 2 benchmarks, including Google-Proof Q&A, Massive Multitask Language Understanding.
Advancing the state-of-the-art in AI and computing.
Cheapest of 3 routes · OpenRouter