•

Open weights model

•

Released December 2024

Phi-4 API Provider Benchmarking & Analysis

Model Comparison

This analysis is intended to support you in choosing the best API provider of Phi-4 for your use-case.

Lowest Time per Task

Time per Intelligence Index task (minutes)

Total 2 providers

Lowest Cost per Task

Cost per Intelligence Index task

Total 2 providers

Phi-4 is available through 2 API providers, each offering different performance characteristics and pricing. Below is a comparison of the key metrics across providers.

    Inference time (minutes) per Intelligence Index task · Lower is better
    No data available
    Weighted average cost (USD) per Intelligence Index task · Lower is better
    No data available

    Pricing

    Cost per Intelligence Index Task: Phi-4

    Weighted average cost (USD) per Intelligence Index task · Segmented by token type · Lower is better
    No data available

    Pricing: Cache Hit, Input, and Output: Phi-4

    Price (USD per M Tokens) · Lower is better

    Output Speed vs. Cost per Task: Phi-4

    Output speed: output tokens divided by total request time, including time to first token · Weighted average cost (USD) per Intelligence Index task
    Most attractive quadrant
    No data available

    Speed

    Average of the single-request and multi-turn agentic workloads measured

    Output Speed: Phi-4

    Output tokens divided by total request time · Includes time to first token · Average of the single-request and multi-turn agentic workloads measured · Higher is better

    Latency

    Average of the single-request and multi-turn agentic workloads measured

    Time to First Answer Token: Phi-4

    Seconds until the first answer token after any reasoning · Average of the single-request and multi-turn agentic workloads measured · Lower is better

    Reliability

    Share of requests the endpoint failed, across all the single-request and multi-turn agentic workloads measured

    Endpoint Error Rate: Phi-4

    Share of requests the endpoint failed with an error, a rate limit or a timeout · Across all the single-request and multi-turn agentic workloads measured · Lower is better

    Key Comparison Metrics & API Features

    DeepInfra logoDeepInfra
    --
    --
    0.53
    0.0%
    16k
    Open
    Microsoft Azure logoMicrosoft Azure
    --
    --
    3.85
    0.0%
    16k
    Open

    Frequently Asked Questions

    Common questions about Phi-4 providers