Phi-3 Mini Instruct 3.8B API Pricing
Microsoft · released 2024-04-23
Pricing
Pricing not published by Artificial Analysis yet.
Benchmarks
5.8
Intelligence
#451 of 533
#451 of 533
—
Coding
0.3
Math
#244 of 249
#244 of 249
—
Tokens/sec
—
Time to first token
Leaderboard neighbours
| Model | Intelligence | Blended $/1M |
|---|---|---|
| Mistral Large (Feb '24) | 5.8 | $6.00 |
| Mistral Small (Sep '24) | 5.8 | $0.30 |
| NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) | 5.8 | $0.30 |
| Phi-3 Mini Instruct 3.8B | 5.8 | — |
| Phi-4 Multimodal Instruct | 5.8 | — |
| Qwen2.5 Coder Instruct 7B | 5.8 | — |
| Jamba Reasoning 3B | 5.7 | — |
More from Microsoft
| Model | Intelligence | Blended $/1M |
|---|---|---|
| Phi-4 Mini Instruct | 6.3 | — |
| Phi-4 | 5.9 | $0.219 |
| Phi-4 Multimodal Instruct | 5.8 | — |
See Phi-3 Mini Instruct 3.8B on the leaderboard
Source: Artificial Analysis · last synced 2026-09-22
FAQ
Who develops Phi-3 Mini Instruct 3.8B?
Phi-3 Mini Instruct 3.8B is developed by Microsoft, released 2024-04-23.
Is Phi-3 Mini Instruct 3.8B's API pricing published?
No — as of the last data sync (2026-09-22), Artificial Analysis has not published official API pricing for Phi-3 Mini Instruct 3.8B. This page updates automatically once pricing is available.
How does Phi-3 Mini Instruct 3.8B rank on benchmarks?
Phi-3 Mini Instruct 3.8B scores 5.8 on the Artificial Analysis Intelligence Index, ranking #451 of 533 models we track.
Where does this data come from?
Pricing and benchmark data for Phi-3 Mini Instruct 3.8B comes from Artificial Analysis (artificialanalysis.ai), synced daily. Last synced 2026-09-22.