Microsoft model
Phi 4 API cost calculator
Phi 4 costs $0.07 per 1M input tokens and $0.14 per 1M output tokens on the Microsoft API, with a 16K-token context window. A typical request (2K input, 500 output tokens) costs $0.0002 — about $6.30/month at 1,000 requests per day. Use the calculator below to model your exact workload.
Find me a cheaper modelWhat real workloads cost on Phi 4
| Workload | Tokens (in / out) | Per request | Per 1K requests |
|---|---|---|---|
| Chatbot message | 500 / 300 | <$0.0001 | $0.08 |
| RAG query with context | 4,000 / 500 | $0.0003 | $0.35 |
| Document summarization | 20,000 / 1,000 | $0.0015 | $1.54 |
| Agent coding session | 100,000 / 5,000 | $0.0077 | $7.70 |
Phi 4 vs other Microsoft models
| Model | Input /1M | Output /1M | Context |
|---|---|---|---|
| Phi 4 | $0.07 | $0.14 | 16K |
| WizardLM-2 8x22B | $0.62 | $0.62 | 66K |
Frequently asked questions
How much does Phi 4 cost per 1M tokens?
According to current pricing data, Phi 4 costs $0.07 per 1M input tokens and $0.14 per 1M output tokens. Processing 1M tokens each way costs $0.21.
What does a typical API request to Phi 4 cost?
A typical request with 2,000 input tokens and 500 output tokens costs $0.0002. At 1,000 requests per day that is $0.21 daily, or about $6.30 per month.
What is Phi 4's context window?
Phi 4 supports a 16K-token context window (16,384 tokens).
Does Phi 4 support prompt caching?
No cache-read pricing is published for Phi 4, so every input token is billed at the full $0.07 per 1M rate.
What is a cheaper alternative to Phi 4?
Ling-2.6-flash from Inclusionai is currently the cheapest comparable option at $0.01 per 1M input tokens versus $0.07 for Phi 4 — roughly 7x cheaper on input.
Compare all current prices on the live model pricing dashboard, see Phi 4 vs Ling-2.6-flash pricing, or run Phi 4 head-to-head against other models in the side-by-side comparison playground.
Pricing data via the OpenRouter models API.