MicrosoftReasoningReleased 10 January 2025
Phi 4 pricing, context and benchmark
[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed.
16K
Input context
15K
Output context
$0.07
Official input
$0.14
Official output
n/a
AA index
01 · Model Overview
Everything that matters, in one table
Context, pricing, cache, modalities and tooling, from the model registry and Artificial Analysis.
| Model | Phi 4 |
| Model ID | microsoft/phi-4 |
| Provider | Microsoft |
| Release date | 10 January 2025 |
| Status | Generally available |
| Input context | 16,384 tokens |
| Output context | 14,745 tokens |
| Official input pricing | $0.07 per 1M tokens |
| Official output pricing | $0.14 per 1M tokens |
| Cache read pricing | Not published |
| Market input pricing | $0.056 per 1M (cheapest route) |
| Market output pricing | $0.112 per 1M (cheapest route) |
| Input modalities | text |
| Output modalities | text |
| Reasoning control | Not exposed |
| Tool support | Text generation only |
| Tokenizer | Other |
| Provider routes | 2 endpoints |
| Artificial Analysis index | Not published |
| Speed | Not published |
| Knowledge cutoff | Not publicly stated |
Input and output support
| Modality | Input | Output | Billed at |
|---|---|---|---|
| Text | ✓ yes | ✓ yes | $0.07 in |
| Image | no | no | not supported |
| Audio | no | no | not supported |
| Video | no | no | not supported |
| File (PDF) | no | no | not supported |
02 · Overview
What is Phi 4?
[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed.
At 14 billion...
Phi 4 carries a 16K token window, uses the Other tokenizer and is served by Microsoft. On Hoodgen it sits in the Reasoning tier of the model menu next to its siblings, so you can switch mid conversation without losing the thread.
03 · Release
Release and what changed from the previous version
Released10 January 2025
This is the only release of Phi 4 on OpenRouter, released 10 January 2025. The provider has not published a knowledge cutoff, so treat training data as recent but unconfirmed for very new events.
04 · Capabilities
Features and capabilities
{ }
Structured outputs
Schema constrained JSON with response_format, so no parse and retry loop in your code.
⌁
Seeds
A seed can be pinned so the same prompt is reproducible across test runs.
07 · Use cases
What can you do with Phi 4?
Debugging and root cause
Multi file failures where the model has to hold a causal chain before answering.
Architecture and planning
Design docs, migration plans and trade off analysis over long context.
Data analysis
Spreadsheets and logs read in one pass, then summarised with the numbers quoted back.
Agentic coding
Repo wide changes that need plan, edit and verify loops.
09 · Pricing
Phi 4 pricing
Official pricing
List price
$0.07 / 1M in
$0.14 / 1M out
- 16K context
- text input
Cheapest route
$0.056 / 1M in
$0.112 / 1M out
- 2 routes on OpenRouter
- What Hoodgen routes to first
- Same model, lower bill
Market pricing, every route
| Provider | Tier | Input | Output | Cache read | Uptime 24h |
|---|---|---|---|---|---|
| DeepInfra | standard | $0.056 | $0.112 | n/a | n/a |
| DeepInfra | standard | $0.07 | $0.14 | n/a | 100.0% |
API pricing and cost calculator
| Rate | Per call | Total | Credits |
|---|---|---|---|
| Cheapest route | $0.0013 | $0.64 | 612 |
| List price | $0.0016 | $0.81 | 765 |
10 · Developers
API and developer information
| Model ID | microsoft/phi-4 |
| Endpoint | https://openrouter.ai/api/v1/chat/completions |
| Parameters | frequency_penalty · logit_bias · max_tokens · min_p · presence_penalty · repetition_penalty · response_format · seed · stop · structured_outputs · temperature · top_k · top_p |
| Streaming | Yes, server sent events |
| Modality string | text->text |
| Max prompt tokens | 16,384 |
| Max completion tokens | 14,745 |
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "microsoft/phi-4",
"messages": [{ "role": "user", "content": "Summarise this document." }],
"max_tokens": 1024
}'11 · Limitations
Model limitations
| Text only output | It cannot generate images, audio or video. Pair it with an image model on Hoodgen when you need visuals. |
| Output cap | 14,745 tokens per request. Long deliverables have to be chunked. |
| Benchmarks not published | Artificial Analysis does not publish an Intelligence Index for this release, so no benchmark score is claimed here. |
| Knowledge cutoff | The provider does not state a fixed cutoff for every release. Verify very recent events against search. |
12 · Comparison
Phi 4 vs other Microsoft models
| Model | Context | Input /1M | Output /1M | AA index | Released |
|---|---|---|---|---|---|
| Phi 4 | 16K | $0.07 | $0.14 | n/a | 2025 |
13 · Privacy
Privacy and data policy
- On Hoodgen, prompts and attachments answer that request and stay in your conversation history so you can reopen it. They are not used to train models.
- Requests route through OpenRouter to Microsoft and are covered by that provider's API terms.
- Do not paste secrets or personal data you would not send to any hosted model.
14 · FAQ
Phi 4 questions, answered
Phi 4 is a reasoning model from Microsoft, released 10 January 2025. [Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed.
✦
Start chatting with Phi 4
Free to try on Hoodgen AI, with a live credit estimate before every send. No API key, no setup.