Phi-4 Mini Instruct API Pricing
Microsoft · released 2024-02-26
Pricing
Pricing not published by Artificial Analysis yet.
Benchmarks
6.3
Intelligence
#425 of 533
#425 of 533
3.8
Coding
#191 of 197
#191 of 197
6.7
Math
#221 of 249
#221 of 249
45
Tokens/sec
0.35s
Time to first token
Leaderboard neighbours
| Model | Intelligence | Blended $/1M |
|---|---|---|
| Celeris-1 | 6.3 | $0.325 |
| EXAONE 4.0 32B (Non-reasoning) | 6.3 | — |
| Grok-1 | 6.3 | — |
| Phi-4 Mini Instruct | 6.3 | — |
| Qwen2 Instruct 72B | 6.3 | — |
| Gemini 1.5 Flash-8B | 6.2 | — |
| DeepHermes 3 - Mistral 24B Preview (Non-reasoning) | 6.1 | — |
More from Microsoft
| Model | Intelligence | Blended $/1M |
|---|---|---|
| Phi-4 | 5.9 | $0.219 |
| Phi-3 Mini Instruct 3.8B | 5.8 | — |
| Phi-4 Multimodal Instruct | 5.8 | — |
See Phi-4 Mini Instruct on the leaderboard
Source: Artificial Analysis · last synced 2026-09-22
FAQ
Who develops Phi-4 Mini Instruct?
Phi-4 Mini Instruct is developed by Microsoft, released 2024-02-26.
Is Phi-4 Mini Instruct's API pricing published?
No — as of the last data sync (2026-09-22), Artificial Analysis has not published official API pricing for Phi-4 Mini Instruct. This page updates automatically once pricing is available.
How does Phi-4 Mini Instruct rank on benchmarks?
Phi-4 Mini Instruct scores 6.3 on the Artificial Analysis Intelligence Index, ranking #425 of 533 models we track.
Where does this data come from?
Pricing and benchmark data for Phi-4 Mini Instruct comes from Artificial Analysis (artificialanalysis.ai), synced daily. Last synced 2026-09-22.