•

Open weights model

•

Released February 2025

Phi-4 Multimodal Instruct API Provider Benchmarking & Analysis

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

Fastest

Output speed

Total 1 provider

Lowest Latency

Time to first token

Total 1 provider

Lowest Price

Azure

$0.10

Blended price (per 1M tokens)

Total 1 provider

Phi-4 Multimodal is available through Azure.

Benchmarks of providers are not available for this model.

Please see the models page for Phi-4 Multimodal Instruct for details of the model and its intelligence compared to other models.

Speed

Output tokens per second · Higher is better

No data available

Latency

Seconds to first answer token received · Lower is better

No data available

Price

USD per 1M tokens (blended) · Lower is better

Update: Default performance benchmarking workload has updated to 10k input tokens to better reflect production use cases. You can still select different workloads above.

Pricing

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

Price (USD per M Tokens) · Lower is better · 10,000 input tokens

Price per token for cached prompts (previously processed), typically offering a significant discount compared to regular input price, represented as USD per million tokens. The values shown here are the cache hit price; cache write and cache storage are billed separately and vary by provider — see "Cache pricing by provider" for detail.

Cost per Intelligence Index Task: Phi-4 Multimodal Providers

Weighted average cost (USD) per Intelligence Index task · Segmented by token type · Lower is better

No data available

Weighted average cost per Intelligence Index task. Each evaluation’s cost is calculated from input, cache hit, cache write, reasoning, and answer token prices, divided by task count, and weighted by its Intelligence Index weight.

Output Speed vs. Price: Phi-4 Multimodal Providers

Blended at 7:2:1 (cache-input-output) · Output speed: output tokens per second · USD per 1M tokens (blended)

Most attractive quadrant

No data available

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Speed

Measured by Output Speed (tokens per second)

Output Speed: Phi-4 Multimodal Instruct

Output speed: output tokens per second · 10,000 input tokens

No data available

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Figures represent performance of the model's first-party API or the median across providers where a first-party API is not available.

Time per Intelligence Index Task: Phi-4 Multimodal Providers

Weighted average decode time (minutes) per Intelligence Index task · Excludes TTFT and overhead time · Lower is better

No data available

The weighted average time (seconds) per Artificial Analysis Intelligence Index task. This is calculated by dividing output tokens per task by output speed, weighted by the relative weights of each benchmark in the Intelligence Index.

Cost per Task vs. Time per Task: Phi-4 Multimodal Providers

Weighted average cost (USD) per Intelligence Index task · Weighted average decode time (minutes) per Intelligence Index task

Most attractive quadrant

No data available

Latency

Measured by Time (seconds) to First Token

Time to First Token: Phi-4 Multimodal Providers

Seconds to first token received · Lower is better · 10,000 input tokens

No data available

Time to first token received, in seconds, after API request sent. For reasoning models which share reasoning tokens, this will be the first reasoning token. For models which do not support streaming, this represents time to receive the completion.

Figures represent median (P50) measurement over the past 72 hours to reflect sustained changes in performance.

End-to-End Response Time

Seconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed

End-to-End Response Time: Phi-4 Multimodal Providers

Seconds to output 500 tokens, including reasoning model 'thinking' time · Lower is better · 10,000 input tokens

No data available

Seconds to receive a 500 token response. Key components:

Input time: Time to receive the first response token
Thinking time (only for reasoning models): Time reasoning models spend outputting tokens to reason prior to providing an answer. Amount of tokens based on the average reasoning tokens across a diverse set of 60 prompts (methodology details).
Answer time: Time to generate 500 output tokens, based on output speed

Key Comparison Metrics & API Features



Microsoft Azure	4.1k			Open	--	--	--	--	--

Frequently Asked Questions

Common questions about Phi-4 Multimodal Instruct providers

Phi-4 Multimodal Instruct is available through 1 API provider: Azure. Each provider offers different performance characteristics and pricing.

Phi-4 Multimodal Instruct is currently available through 1 API provider that we benchmark and track.

The most affordable provider for Phi-4 Multimodal Instruct by blended price is Azure ($0.10 per 1M tokens). Blended price uses a 7:2:1 cache hit/input/output token ratio.

The provider with the lowest input token pricing for Phi-4 Multimodal Instruct is Azure ($0.08 per 1M input tokens).

The provider with the lowest output token pricing for Phi-4 Multimodal Instruct is Azure ($0.32 per 1M output tokens).

The only provider of Phi-4 Multimodal Instruct supports JSON mode for structured output.

When choosing a provider for Phi-4 Multimodal Instruct, consider: output speed (for throughput-intensive tasks), latency (for interactive applications requiring quick first responses), pricing (for cost-sensitive workloads), and API features like JSON mode or function calling.

Yes, provider performance can vary over time due to infrastructure changes, load balancing, and updates. We continuously benchmark all providers and display historical performance trends in the "Over Time" charts.

For information about Phi-4 Multimodal Instruct's intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview

Phi-4 Multimodal Instruct API Provider Benchmarking & Analysis

Fastest

Lowest Latency

Lowest Price

Speed

Latency

Price

Pricing

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

Cache Hit

Cost per Intelligence Index Task: Phi-4 Multimodal Providers

Cost per Intelligence Index Task

Output Speed vs. Price: Phi-4 Multimodal Providers

Output Speed

Speed

Output Speed: Phi-4 Multimodal Instruct

Output Speed

Model Performance Representation

Time per Intelligence Index Task: Phi-4 Multimodal Providers

Time per Intelligence Index Task

Cost per Task vs. Time per Task: Phi-4 Multimodal Providers

Cost per Intelligence Index Task

Latency

Time to First Token: Phi-4 Multimodal Providers

Latency (Time to First Token)

Median

End-to-End Response Time

End-to-End Response Time: Phi-4 Multimodal Providers

End-to-End Response Time

Key Comparison Metrics & API Features

Frequently Asked Questions

Where can I access Phi-4 Multimodal Instruct?

How many API providers offer Phi-4 Multimodal Instruct?

Which provider is cheapest for Phi-4 Multimodal Instruct?

Which provider has the lowest input price for Phi-4 Multimodal Instruct?

Which provider has the lowest output price for Phi-4 Multimodal Instruct?

Which Phi-4 Multimodal Instruct providers support JSON mode?

How do I choose a provider for Phi-4 Multimodal Instruct?

Does provider performance for Phi-4 Multimodal Instruct change over time?

What are the overall capabilities of Phi-4 Multimodal Instruct?