Phi-4 vs o4-mini
Phi-4 is cheaper than o4-mini by about 96% on a blended (75% input / 25% output) basis. Phi-4 charges $0.0560 / $0.11 per 1M input/output tokens; o4-mini charges $1.10 / $4.40.
| Field | Phi-4 | o4-mini |
|---|---|---|
| Input $/Mtok | $0.0560 | $1.10 |
| Output $/Mtok | $0.11 | $4.40 |
| Cache read $/Mtok | – | $0.28 |
| Cache write $/Mtok | – | – |
| Input $/Mchar | n/a | 0.31 |
| Output $/Mchar | n/a | 1.24 |
| Context window | 16384 | 200000 |
| Tokenizer | – | o200k |
| Confidence? | api | api |
| Source | openrouter | openrouter |
Confidence: official = vendor pricing page · api = OpenRouter per-host · aggregator = community list, may lag · unreviewed = automatic extraction awaiting review. When sources disagree the most authoritative wins. Details: /methodology#confidence
Price history
No price changes recorded yet for either model.
Same workload, monthly cost
Illustrative monthly cost at 10M tokens/month, split per workload preset. Not a substitute for the calculator, which uses your own volume, cache and batch assumptions.
| Workload | Phi-4 | o4-mini |
|---|---|---|
| Coding agent | $0.59 | $12.65 |
| RAG chat | $0.64 | $15.95 |
| Summarisation (batch) | $0.62 | $14.30 |
| Classification | $0.57 | $11.66 |
| Chat assistant | $0.78 | $24.20 |
| Content generation | $1.01 | $37.40 |
Batch pricing not published for Phi-4; standard rate used for the batch share of a workload.
Batch pricing not published for o4-mini; standard rate used for the batch share of a workload.
Cite this page
Phi-4 vs o4-mini: $0.0560/$0.11 vs $1.10/$4.40 per 1M tokens as of 2026-11-19. Token Barometer by Dejan Strbad, https://tokenbarometer.com, data CC BY 4.0. https://tokenbarometer.com/compare/microsoft_phi-4-vs-openai_o4-mini
Phi-4 page | o4-mini page | Open Phi-4 in calculator | Open o4-mini in calculator