Compare/DeepSeek R1 (Jan '25) vs o4-mini (high)

DeepSeek R1 (Jan '25)vso4-mini (high)

Side-by-side comparison of pricing, 12 benchmarks, and generation speed.

DeepSeek

DeepSeek R1 (Jan '25)

Input
$1.35/M
Output
$4/M
Speed
TTFT
OpenAI

o4-mini (high)

Input
$1.1/M
Output
$4.4/M
Speed
145 tok/s
TTFT
26.75s

Winner by Category

Cheaper
o4-mini (high)
Faster (tok/s)
o4-mini (high)
Lower Latency
DeepSeek R1 (Jan '25)
Benchmarks (1-11)
o4-mini (high)

Pricing Comparison

MetricDeepSeek R1 (Jan '25)o4-mini (high)
Input ($/M tokens)$1.35$1.1
Output ($/M tokens)$4$4.4
Cost for 1M input + 100K output tokens:
DeepSeek R1 (Jan '25)$1.75
o4-mini (high)$1.54

Speed Comparison

Output Speed (tokens/s) — higher is better
DeepSeek R1 (Jan '25)
o4-mini (high)
145 tok/s
Time to First Token (seconds) — lower is better
DeepSeek R1 (Jan '25)
o4-mini (high)
26.75s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
18.833.1
Coding Index
15.925.6
Math Index
68.090.7
GPQA Diamond
70.8%78.4%
MMLU-Pro
84.4%83.2%
LiveCodeBench
61.7%85.9%
AIME 2025
68.0%90.7%
MATH-500
96.6%98.9%
Humanity's Last Exam
9.3%17.5%
SciCode
35.7%46.5%
IFBench
39.0%68.7%
TerminalBench
6.1%15.2%
DeepSeek R1 (Jan '25)1 wins
11 winso4-mini (high)

Frequently Asked Questions

Which is cheaper, DeepSeek R1 (Jan '25) or o4-mini (high)?

o4-mini (high) is cheaper overall. Its blended price (3:1 input/output ratio) is $1.93/M tokens vs $2.36/M for DeepSeek R1 (Jan '25).

Which model performs better on benchmarks?

o4-mini (high) wins 11 out of 12 benchmarks compared to 1 for DeepSeek R1 (Jan '25). See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

o4-mini (high) generates tokens faster at 145 tok/s vs 0 tok/s. DeepSeek R1 (Jan '25) also has lower time-to-first-token (0.00s vs 26.75s).

When should I use DeepSeek R1 (Jan '25) vs o4-mini (high)?

Choose based on your priorities: o4-mini (high) for lower cost, o4-mini (high) for stronger benchmark performance, and o4-mini (high) for faster generation. For latency-sensitive apps, check the TTFT comparison above.