Phi 4
by Microsoft · microsoft/phi-4 · #26 cheapest of 325 paid models
Prices updated Jul 22, 2026, 1:41 AM UTC · refreshed hourly
[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...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$0.07
per 1M tokens
Output
$0.14
per 1M tokens
Blended (3:1)
$0.088
3 input : 1 output
Cache read
—
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for Phi 4 (no cache-read rate published — hits billed as normal input).
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $0.088 | $0.00728 | — |
| 50% | $0.088 | $0.00728 | −0% |
| 90% | $0.088 | $0.00728 | −0% |
*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates (available for OpenAI / Anthropic / Google — not flagged for this creator). Confirm on the vendor’s pricing page.
What a request costs
| Workload | Input tokens | Output tokens | Cost / request | Cost / 1K requests |
|---|---|---|---|---|
| Short chat message | 500 | 300 | $7.70e-5 | $0.077 |
| Document summary | 8,000 | 1,000 | $0.0007 | $0.7 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.00238 | $2.38 |
| Long-context analysis | 150,000 | 5,000 | $0.0112 | $11.20 |
Specs
Context window
16K
tokens
Max output
16K
tokens
Input modalities
text
Tokenizer
Other