Phi-4: Quality, Performance & Price Analysis
Analysis of Microsoft Azure's Phi-4 and comparison to other AI models across key metrics including quality, price, performance (tokens per second & time to first token), context window & more. Click on any model to compare API providers for that model. For more details including relating to our methodology, see our FAQs.
Comparison Summary
Quality:
Phi-4 is of higher quality compared to average, with Quality Index across evaluations of 77.
Price:Phi-4 is cheaper compared to average with a price of $0.09 per 1M Tokens (blended 3:1).
Phi-4 Input token price: $0.07, Output token price: $0.14 per 1M Tokens.
Speed:Phi-4 Input token price: $0.07, Output token price: $0.14 per 1M Tokens.
Phi-4 is slower compared to average, with a output speed of 85.2 tokens per second.
Latency:Phi-4 has a lower latency compared to average, taking 0.21s to receive the first token (TTFT).
Context Window:Phi-4 has a smaller context windows than average, with a context window of 16k tokens.
Highlights
Quality
Artificial Analysis Quality Index; Higher is better
Speed
Output Tokens per Second; Higher is better
Price
USD per 1M Tokens; Lower is better
Parallel Queries:
Prompt Length:
Further details
o1-preview
Llama 3.3 Instruct 70B
Gemini 2.0 Flash (experimental)
Claude 3.5 Sonnet (Oct '24)
Pixtral Large
Command-R+ (Aug '24)
Sonar 3.1 Small
Nova Pro
Solar Mini
DBRX Instruct
Llama 3.1 Nemotron Instruct 70B
Reka Flash (Sep '24)
Jamba 1.5 Large
DeepSeek V3
Arctic Instruct
Qwen2.5 Instruct 72B
Yi-Large
OpenChat 3.5 (1210)