LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Phi-4

microsoft·microsoft/phi-4·GA·Open weights·phi series
Open-weight instruction model for adaptable chat and self-hosted production workloads

Specs & pricing

Input / output per 1M tokens
Official price·Azure
$0.13 / $0.50
Blended $0.22 · Cache read —
Lowest paid·Kilo GatewayGateway
$0.056 / $0.11
Blended $0.07 · 2.2× spread
Context
128,000
Output limit
4,096
Knowledge cutoff
2023-10
Released / updated
2024-12-11 / 2025-01-10
Capabilities
ReasoningTool use✓ Structured output✓ TemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
Text

Phi-4 by microsoft is offered by 4 providers on this page. Its official list price is $0.125 per 1M input tokens and $0.50 per 1M output tokens. The lowest paid channel is Kilo Gateway at $0.056 / $0.112 per 1M, about 3.1× below the list price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it.

Median output speed is 37 tokens per second, with 2.6s to the first token.

The context window is 128,000 tokens at the reference host, but hosts report different limits, from 16,384 to 128,000, so the usable window depends on the provider you pick. It supports structured output. 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 & performanceArtificial Analysis · Intelligence Index v5

Intelligence—
Value—
Output speed37 tok/s
TTFT2.6 s

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

Available at 4 providers4 with public prices

  • ProviderInput / Output
  • Kilo GatewayGateway
    $0.056 / $0.11
    Context 16,384 ⚠Output limit 14,745
  • OpenRouterGateway
    $0.07 / $0.14
    Context 16,384 ⚠Output limit 14,745
  • Azure Cognitive ServicesOfficialCloud
    $0.13 / $0.50
    Context 128,000Output limit 4,096
  • AzureOfficialCloud
    $0.13 / $0.50
    Context 128,000Output limit 4,096
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Kilo GatewayGateway$0.056$0.11——16,384 ⚠14,745
OpenRouterGateway$0.07$0.14——16,384 ⚠14,745
Azure Cognitive ServicesOfficialCloud$0.13$0.50——128,0004,096
AzureOfficialCloud$0.13$0.50——128,0004,096

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
1Kilo Gateway$16.80
2OpenRouter$21.00
3Azure Cognitive Services · Official$50.00
4Azure · Official$50.00
Switch to Kilo Gateway to save $33.20/mo (66%)
Note: this is a gateway; verify availability and rate limits yourself.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$0.50$02026-08-052026-10-16
2026-10-16Input list $0.13Output list $0.50Min blended $0.07

Artificial Analysis evaluations9 items

GPQA Diamond57.5%
Humanity's Last Exam3.8%
CritPt0.0%
LiveCodeBench23.1%
Terminal-Bench Hard3.8%
AIME 202518.0%
τ²-Bench Telecom0.0%
AA-LCR0.0%
IFBench23.5%

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-minisame series$0.075 / $0.30Phi-4-multimodal-instructsame series—Phi-4-mini-reasoningsame series$0.075 / $0.30Nova Litecheaper alternative$0.06 / $0.24Nova Microcheaper alternative$0.035 / $0.14Command R7Bcheaper alternative$0.038 / $0.15Lyria 3 Clip Previewcheaper alternative$0 / $0Decision-1same lab—
Data partly from models.dev (MIT) · Azure official docs ↗