Compact Microsoft instruction model tuned for efficient coding assistance, reasoning, and low-latency agent tasks
Phi-4-mini by microsoft is offered by 4 providers on this page. Public prices are shown for 3 of them. Its official list price is $0.075 per 1M input tokens and $0.30 per 1M output tokens. The lowest paid channel is Azure at $0.075 / $0.30 per 1M, about 2.3× below the list price. It also has 1 free ($0) channel; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.
Artificial Analysis rates it 6.3 on the Intelligence Index, with 3.8 for coding. Against its lowest blended price of $0.131 per 1M, that is roughly 48 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 45 tokens per second, with 0.83s to the first token.
The context window is 128,000 tokens at the reference host, but hosts report different limits, from 128,000 to 131,072, so the usable window depends on the provider you pick. It supports tool use. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2023-10.
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Nvidia microsoft/phi-4-mini-instruct | Cloud | Free | — | — | 131,072 ⚠ | 8,192 | deprecated | |
| AzureOfficial | Cloud | $0.075 | $0.30 | — | — | 128,000 | 4,096 | |
| Azure Cognitive ServicesOfficial | Cloud | $0.075 | $0.30 | — | — | 128,000 | 4,096 | |
| NanoGPT phi-4-mini-instruct | Gateway | $0.17 | $0.68 | $0.085 | — | 128,000 | 16,384 |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
1 more channels offer $0 (Nvidia); free tiers usually have rate limits and no SLA, excluded from ranking.
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| MMLU | — | 67.3 | accuracy | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.
Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and harness, so rows are not comparable with one another. The Intelligence Index above draws on a different, newer set of evaluations.