ZMIME
Comparison · 3 models · Updated Nov 18, 2026

GPT-4.1 vs o4-mini vs DeepSeek-R1

o4-mini comes out ahead, 59 to 55 and 50 on our weighted score, and it is the cheaper option too.

Price in rating: Included · Exclude price

  1. OpenAI

    GPT-4.1

    Released Apr 14, 2025

    55/100
    • ECI136.2
    • Price$2.00 / $8.00
    • Context1.05M
  2. Our pick

    OpenAI

    o4-mini

    Released Apr 16, 2025Deprecated

    59/100
    • ECI145.2
    • Price$1.10 / $4.40
    • Context200K
  3. DeepSeek

    DeepSeek-R1

    Released Jan 20, 2025

    50/100
    • ECI138.6
    • Price$1.02 / $5.14
    • Context128K
01 — Verdict

o4-mini is our pick

o4-mini is the better all-round choice, scoring 59/100 against GPT-4.1 (55) and DeepSeek-R1 (50). It leads on capability. GPT-4.1 wins on context window. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • Capabilityo4-miniCapabilities Index (ECI): o4-mini 145.2 · DeepSeek-R1 138.6 · GPT-4.1 136.2
  • Lowest priceo4-minio4-mini $1.93 · DeepSeek-R1 $2.05 · GPT-4.1 $3.50 per 1M tokens (3:1 blend)
  • Longest contextGPT-4.1GPT-4.1 1,047,576 · o4-mini 200,000 · DeepSeek-R1 128,000 tokens
  • Widest inputsGPT-4.1GPT-4.1: Text, Images, PDFs · o4-mini: Text, Images · DeepSeek-R1: Text
  • Self-hostingDeepSeek-R1Publishes downloadable weights
How the score is built
MeasureWeightGPT-4.1o4-miniDeepSeek-R1
CapabilityCapabilities Index (ECI)50%647367
Price25%233534
Inputs & features15%707035
Context window10%653932
Overall100%55/10059/10050/100
02 — Side by side

Every spec in one table

Highlighted cells lead their row. Dashes mean the data is not published.

GPT-4.1 vs o4-mini vs DeepSeek-R1 specifications side by side
SpecificationGPT-4.1OpenAIo4-miniOpenAIDeepSeek-R1DeepSeek
Capability
Capabilities Index (ECI)136.2145.2 (best)138.6
ECI rank#123 of 158#91 of 158 (best)#118 of 158
GPQA DiamondGraduate-level science questions66.9%79.6% (best)71.7%
FrontierMath Tiers 1–3Research-level mathematics6.0%36.1% (best)—
OTIS Mock AIME 2024–2025Competition mathematics38.3%81.7% (best)53.3%
SWE-bench VerifiedFixing real GitHub issues48.5%——
SimpleQA VerifiedShort factual questions31.1% (best)19.6%—
Price per million tokens
Input$2.00$1.10$1.02 (best)
Output$8.00$4.40 (best)$5.14
Cached input$0.50$0.275 (best)—
Blended (3:1)$3.50$1.93 (best)$2.05
Long-context rateSame rateSame rateSame rate
Price sourceOfficial OpenAI APIOfficial OpenAI APIMedian of 12 providers
Limits
Context window1,047,576 tokens (best)200,000 tokens128,000 tokens
Max output32,768 tokens100,000 tokens (best)32,768 tokens
Inputs and features
TextYesYesYes
ImagesYesYesNo
PDFsYesNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningNoYeslow · medium · highYes
Tool callingYesYesYes
Structured outputYesYesNo
Availability
WeightsProprietaryProprietaryOpen
API model IDgpt-4.1o4-mini—
API providers32 (best)1713
ReleasedApr 14, 2025Apr 16, 2025Jan 20, 2025
Knowledge cutoffApr 2024May 2024Jul 2024
03 — Cost

What would a month cost?

Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.

  • GPT-4.1$36.00
  • o4-mini$19.80
  • DeepSeek-R1$20.53
04 — Questions

Which should you choose?

Which is better: GPT-4.1, o4-mini or DeepSeek-R1?

o4-mini is the better all-round choice, scoring 59/100 against GPT-4.1 (55) and DeepSeek-R1 (50). It leads on capability. GPT-4.1 wins on context window. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, GPT-4.1, o4-mini or DeepSeek-R1?

o4-mini is cheaper at $1.10 input / $4.40 output per million tokens (official OpenAI API price). DeepSeek-R1 costs $1.02 input / $5.14 output per million tokens (median across 12 API providers); GPT-4.1 costs $2.00 input / $8.00 output per million tokens (official OpenAI API price). At a typical mix of three input tokens to one output token, that is $1.93 per million tokens for o4-mini versus $2.05 for DeepSeek-R1 (1.1× as much) and $3.50 for GPT-4.1 (1.8× as much).

Which scores higher on benchmarks?

o4-mini scores higher on the Capabilities Index (ECI): o4-mini 145.2 (#91 of 158), DeepSeek-R1 138.6 (#118 of 158) and GPT-4.1 136.2 (#123 of 158). Their confidence ranges do not overlap (143.7–146.7 vs 136.7–140.4), so the gap is a real one. On individual benchmarks: GPQA Diamond — o4-mini 79.6%, DeepSeek-R1 71.7%, GPT-4.1 66.9%; OTIS Mock AIME 2024–2025 — o4-mini 81.7%, DeepSeek-R1 53.3%, GPT-4.1 38.3%.

Which is better for coding?

There are no published SWE-bench Verified results for o4-mini and DeepSeek-R1 yet, so there is no like-for-like coding score. On overall capability, o4-mini leads, which tends to carry over to coding, but test on your own codebase. All three support tool calling for agent workflows.

Which has the bigger context window?

GPT-4.1 has the largest context window at 1,047,576 tokens, against 200,000 for o4-mini and 128,000 for DeepSeek-R1. Maximum output per response: GPT-4.1 up to 32,768, o4-mini up to 100,000, DeepSeek-R1 up to 32,768 tokens.

Which can read images, PDFs, audio or video?

GPT-4.1 accepts text, images and PDFs; o4-mini accepts text and images; DeepSeek-R1 accepts text. GPT-4.1 handles the widest range of inputs.

Are any of these open source?

DeepSeek-R1 publishes its weights and can be self-hosted; GPT-4.1 and o4-mini is proprietary.

Which is newer?

o4-mini is the newest, released Apr 16, 2025. GPT-4.1 came out Apr 14, 2025; DeepSeek-R1 came out Jan 20, 2025. Knowledge cutoff: GPT-4.1 Apr 2024, o4-mini May 2024, DeepSeek-R1 Jul 2024.

How do you decide the winner?

This rating uses capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Nov 18, 2026.