Phi-4 Mini Instruct logo
Microsoft
•

Open weights model

•

Released February 2024

Phi-4 Mini Instruct API Provider Benchmarking & Analysis

Model Comparison

Analysis of API providers for Phi-4 Mini Instruct across performance metrics including latency (time to first token), output speed (output tokens per second), price and others. API providers benchmarked include Microsoft Azure, CoreWeave.

Fastest

#1
CoreWeaveCoreWeave
233.6 t/s
#2
AzureAzure
42.9 t/s

Output speed

Total 2 providers

Lowest Latency

#1
AzureAzure
0.64 s
#2
CoreWeaveCoreWeave
0.95 s

Time to first answer token

Total 2 providers

Lowest Price

#1
CoreWeaveCoreWeave
$0.15

Blended price (per 1M tokens, 3:1 Input-Output ratio)

Total 2 providers

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

  • For output speed, the top providers are CoreWeave (233.6 t/s), Azure (42.9 t/s).
  • For latency, Azure (0.64s), CoreWeave (0.95s) offer the lowest time to first token.

Highlights

Speed

Output tokens per second · Higher is better

End-to-End Response Time

Seconds · Lower is better

Price

USD per 1M tokens (3:1 input-output ratio) · 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

USD per 1M 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.

Price per token included in the request/message sent to the API, represented as USD per million Tokens.

The blended bar shown here uses cache hit price only. Other caching costs differ by provider:

  • Anthropic: charges a separate cache write fee, with different rates for 5-minute and 1-hour TTLs (1-hour TTL is more expensive). Blended price charts use Anthropic cache write price for the input leg.
  • Google (Vertex/Gemini): charges a per-hour cache storage fee in addition to cache hit pricing. Some providers also use tiered pricing for prompts above 200K tokens.
  • OpenAI, DeepSeek, others: typically charge only cache hit pricing with no write or storage fee.

See Prompt Caching for the full breakdown.

Price per token generated by the model (received from the API), represented as USD per million Tokens.

Pricing: Blended Price

Blended at 3:1 (Input : Output) · USD per 1M tokens · Lower is better

Price per token, represented as USD per million Tokens. Price is a blend of cache hit, input, and output token prices using the selected ratio.

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.

The blended bar shown here uses cache hit price only. Other caching costs differ by provider:

  • Anthropic: charges a separate cache write fee, with different rates for 5-minute and 1-hour TTLs (1-hour TTL is more expensive). Blended price charts use Anthropic cache write price for the input leg.
  • Google (Vertex/Gemini): charges a per-hour cache storage fee in addition to cache hit pricing. Some providers also use tiered pricing for prompts above 200K tokens.
  • OpenAI, DeepSeek, others: typically charge only cache hit pricing with no write or storage fee.

See Prompt Caching for the full breakdown.

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

Speed vs. Price

Blended at 3:1 (Input : Output) · Output speed: output tokens per second · Price: USD per 1M tokens
Most attractive quadrant
CoreWeave

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).

Price per token, represented as USD per million Tokens. Price is a blend of cache hit, input, and output token prices using the selected ratio.

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.

The blended bar shown here uses cache hit price only. Other caching costs differ by provider:

  • Anthropic: charges a separate cache write fee, with different rates for 5-minute and 1-hour TTLs (1-hour TTL is more expensive). Blended price charts use Anthropic cache write price for the input leg.
  • Google (Vertex/Gemini): charges a per-hour cache storage fee in addition to cache hit pricing. Some providers also use tiered pricing for prompts above 200K tokens.
  • OpenAI, DeepSeek, others: typically charge only cache hit pricing with no write or storage fee.

See Prompt Caching for the full breakdown.

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

Speed

Measured by Output Speed (tokens per second)

Output Speed

Output tokens per second · Higher is better · 10,000 Input Tokens

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

Latency vs. Output Speed

Latency: seconds to first token received · Output speed: output tokens per second · 10,000 Input Tokens
Most attractive quadrant
Size represents Price (USD per M Tokens)
Azure
CoreWeave

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).

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.

Price per token, represented as USD per million Tokens. Price is a blend of cache hit, input, and output token prices using the selected ratio.

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

Latency

Measured by Time (seconds) to First Token

Time to First Token

Seconds to first token received · Lower is better · 10,000 Input Tokens

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

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

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

For fair comparison, the number of reasoning tokens is standardized across all providers for each model based on the model's representative query token counts.

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

API Features

Function (Tool) Calling & JSON Mode

ModelsFunction callingJSON Mode
Azure logoAzure
CoreWeave logoCoreWeave

Indicates whether the provider supports function calling in their API. Function calling is also known as 'Tool Calling'.

Indicates whether the provider supports JSON mode in their API. When JSON mode is enabled, the models will always return a valid JSON object.

Context Window

Context window: tokens limit · Higher is better

Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).

While models have their own context window, in cases this is limited by providers.

Summary Table of Key Comparison Metrics

Frequently Asked Questions

Common questions about Phi-4 Mini Instruct providers

Phi-4 Mini Instruct is available through 2 API providers: Azure and CoreWeave. Each provider offers different performance characteristics and pricing.

Phi-4 Mini Instruct is currently available through 2 API providers that we benchmark and track.

The fastest providers for Phi-4 Mini Instruct by output speed are CoreWeave (233.6 t/s) and Azure (42.9 t/s). Output speed measures how quickly tokens are generated after the model starts responding.

The providers with the lowest time to first token for Phi-4 Mini Instruct are Azure (0.64s) and CoreWeave (0.95s). Lower latency means faster initial response time.

The most affordable provider for Phi-4 Mini Instruct by blended price is CoreWeave ($0.15 per 1M tokens). Blended price uses a 3:1 input to output token ratio.

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

The provider with the lowest output token pricing for Phi-4 Mini Instruct is CoreWeave ($0.35 per 1M output tokens).

Output speed for Phi-4 Mini Instruct varies significantly across providers. CoreWeave is the fastest at 233.6 t/s, which is 5.4x faster than Azure at 42.9 t/s.

1 of 2 providers support JSON mode for Phi-4 Mini Instruct: CoreWeave.

All 2 providers of Phi-4 Mini Instruct support function calling (tool use).

The best provider for Phi-4 Mini Instruct depends on your priorities: CoreWeave offers the highest output speed, Azure has the lowest latency, and CoreWeave provides the most competitive pricing.

When choosing a provider for Phi-4 Mini 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 Mini Instruct's intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview