LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Phi-4-mini

microsoft·microsoft/phi-4-mini·GA·Open weights·phi series
Compact Microsoft instruction model tuned for efficient coding assistance, reasoning, and low-latency agent tasks

Specs & pricing

Input / output per 1M tokens
Official price·Azure
$0.075 / $0.30
Blended $0.13 · Cache read —
Lowest paid·Azure Cognitive ServicesCloud
$0.075 / $0.30
Blended $0.13 · 2.3× spread
Context
128,000
Output limit
4,096
Knowledge cutoff
2024-06
Released / updated
2025-02-26 / 2025-02-26
Capabilities
Reasoning✓ Tool useStructured output✓ TemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
Text
References
Weights

Phi-4-mini by microsoft is offered by 3 providers on this page. Its official list price is $0.075 per 1M input tokens and $0.30 per 1M output tokens. No paid channel is priced below the official list price. Prices vary about 2.3× across the providers that host it.

Median output speed is 45 tokens per second, with 0.88s to the first token.

The context window is 128,000 tokens at the reference host, but hosts report different limits, from 8,192 to 128,000, 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 2024-06.

Quality & performanceArtificial Analysis · Intelligence Index v5

Intelligence—
Value—
Output speed45 tok/s
TTFT0.88 s

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 3 providers3 with public prices

  • ProviderInput / Output
  • Azure Cognitive ServicesOfficialCloud
    $0.075 / $0.30
    Context 128,000Output limit 4,096
  • AzureOfficialCloud
    $0.075 / $0.30
    Context 128,000Output limit 4,096
  • NanoGPTGateway
    phi-4-mini-instruct
    $0.17 / $0.68
    Cache read $0.085Context 8,192 ⚠Output limit 4,096
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Azure Cognitive ServicesOfficialCloud$0.075$0.30——128,0004,096
AzureOfficialCloud$0.075$0.30——128,0004,096
NanoGPT
phi-4-mini-instruct
Gateway$0.17$0.68$0.085—8,192 ⚠4,096

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.

Your usage cost

Common scenarios
1Azure Cognitive Services · Official$30.00
2Azure · Official$30.00
3NanoGPT$57.80
The cheapest paid channel is official.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$0.30$02026-08-082026-08-13
2026-08-13Input list $0.075Output list $0.30Min blended $0.13

Benchmark1 items

NameConditionsScoreMetricSource
MMLU—67.3accuracySource ↗

The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.

Artificial Analysis evaluations11 items

GPQA Diamond33.1%
Humanity's Last Exam4.5%
CritPt0.0%
LiveCodeBench12.6%
Terminal-Bench Hard0.0%
Terminal-Bench 2.10.4%
AIME 20256.7%
τ²-Bench Telecom8.2%
GDPval-AA-401
AA-LCR15.3%
IFBench21.1%

Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and scale (percent correct, points or an index), so rows are not comparable with one another.

Related models

Phi-4-multimodal-instructsame series—Phi-4same series$0.13 / $0.50Phi-4-mini-reasoningsame series$0.075 / $0.30Nova Microcheaper alternative$0.035 / $0.14Command R7Bcheaper alternative$0.038 / $0.15Lyria 3 Clip Previewcheaper alternative$0 / $0Lyria 3 Pro Previewcheaper alternative$0 / $0WizardLM 2 8x22Bsame lab—
Data partly from models.dev (MIT) · Azure official docs ↗