
DeepSeek R1: Intelligence, Performance & Price Analysis
Analysis of DeepSeek's DeepSeek R1 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
Intelligence:
DeepSeek R1 is of higher quality compared to average, with a MMLU score of 0.844 and a Intelligence Index across evaluations of 60.
Price:DeepSeek R1 is cheaper compared to average with a price of $0.96 per 1M Tokens (blended 3:1).
DeepSeek R1 Input token price: $0.55, Output token price: $2.19 per 1M Tokens.
Speed:DeepSeek R1 Input token price: $0.55, Output token price: $2.19 per 1M Tokens.
DeepSeek R1 is slower compared to average, with a output speed of 24.5 tokens per second.
Latency:DeepSeek R1 has a higher latency compared to average, taking 4.55s to receive the first token (TTFT).
Context Window:DeepSeek R1 has a smaller context windows than average, with a context window of 130k tokens.
Highlights
Intelligence
Artificial Analysis Intelligence Index; Higher is better
Estimate (independent evaluation forthcoming)
Speed
Output Tokens per Second; Higher is better
Price
USD per 1M Tokens; Lower is better
Parallel Queries:
Prompt Length:
DeepSeek R1 Model Details
Comparisons to DeepSeek R1
GPT-4o (Nov '24)
GPT-4o mini
o3-mini (high)
o1-pro
GPT-4o (March 2025, chatgpt-4o-latest)
Llama 3.3 Instruct 70B
Llama 3.1 Instruct 8B
Gemini 2.0 Flash (Feb '25)
Gemini 2.5 Pro Experimental (Mar' 25)
Gemma 3 27B Instruct
Claude 3.7 Sonnet (Extended Thinking)
Claude 3.7 Sonnet (Standard)
Mistral Large 2 (Nov '24)
Mistral Small 3.1
DeepSeek V3 0324 (Mar' 25)
Grok 3
Grok 3 Reasoning Beta
Nova Pro
Nova Micro
Command A
QwQ 32B
DeepSeek V3 (Dec '24)
Further details