ZMIME
Comparison · 3 models · Updated Oct 4, 2026

GPT-4.1 mini vs GPT-4.1 vs Mistral Medium 3

GPT-4.1 mini comes out ahead, 60 to 53 and 53 on our weighted score, and it is the cheaper option too.

  1. Our pick

    OpenAI

    GPT-4.1 mini

    Released Apr 14, 2025

    60/100
    • ECI135.0
    • Price$0.40 / $1.60
    • Context1.05M
    Full specs Remove GPT-4.1 mini

  2. OpenAI

    GPT-4.1

    Released Apr 14, 2025

    53/100
    • ECI136.8
    • Price$2.00 / $8.00
    • Context1.05M
    Full specs Remove GPT-4.1

  3. Mistral AI

    Mistral Medium 3

    Released May 7, 2025

    53/100
    • ECI134.1
    • Price$0.40 / $2.00
    • Context131K
    Full specs Remove Mistral Medium 3
01 — Verdict

GPT-4.1 mini is our pick

GPT-4.1 mini is the better all-round choice, scoring 60/100 against GPT-4.1 (53) and Mistral Medium 3 (53). It leads on price. GPT-4.1 wins on capability. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityGPT-4.1Capabilities Index (ECI): GPT-4.1 136.8 · GPT-4.1 mini 135.0 · Mistral Medium 3 134.1
  • Lowest priceGPT-4.1 miniGPT-4.1 mini $0.70 · Mistral Medium 3 $0.80 · GPT-4.1 $3.50 per 1M tokens (3:1 blend)
  • Longest contextGPT-4.1 mini and GPT-4.1GPT-4.1 mini 1,047,576 · GPT-4.1 1,047,576 · Mistral Medium 3 131,072 tokens
  • Widest inputsGPT-4.1 mini and GPT-4.1GPT-4.1 mini: Text, Images, PDFs · GPT-4.1: Text, Images, PDFs · Mistral Medium 3: Text, Images
  • Self-hostingNo open weightsAll three are available only through APIs
How the score is built
MeasureWeightGPT-4.1 miniGPT-4.1Mistral Medium 3
CapabilityCapabilities Index (ECI)50%596158
Price25%572454
Inputs & features15%707050
Context window10%616124
Overall100%60/10053/10053/100
02 — Side by side

Every spec in one table

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

GPT-4.1 mini vs GPT-4.1 vs Mistral Medium 3 specifications side by side
SpecificationGPT-4.1 miniOpenAIGPT-4.1OpenAIMistral Medium 3Mistral AI
Capability
Capabilities Index (ECI)135.0136.8 (best)134.1
ECI rank#115 of 148#111 of 148 (best)#117 of 148
GPQA DiamondGraduate-level science questions65.9%66.9% (best)59.5%
FrontierMath Tiers 1–3Research-level mathematics6.7% (best)6.0%—
OTIS Mock AIME 2024–2025Competition mathematics44.7% (best)38.3%32.2%
SWE-bench VerifiedFixing real GitHub issues—48.5%—
SimpleQA VerifiedShort factual questions12.7%31.1% (best)—
Price per million tokens
Input$0.40 (best)$2.00$0.40 (best)
Output$1.60 (best)$8.00$2.00
Cached input$0.10 (best)$0.50—
Blended (3:1)$0.70 (best)$3.50$0.80
Long-context rateSame rateSame rateSame rate
Price sourceOfficial OpenAI APIOfficial OpenAI APIOfficial Mistral API
Limits
Context window1,047,576 tokens (best)1,047,576 tokens (best)131,072 tokens
Max output32,768 tokens32,768 tokens131,072 tokens (best)
Inputs and features
TextYesYesYes
ImagesYesYesYes
PDFsYesYesNo
AudioNoNoNo
VideoNoNoNo
ReasoningNoNoNo
Tool callingYesYesYes
Structured outputYesYesNo
Availability
WeightsProprietaryProprietaryProprietary
API model IDgpt-4.1-minigpt-4.1mistral-medium-2505
API providers2425 (best)5
ReleasedApr 14, 2025Apr 14, 2025May 7, 2025
Knowledge cutoffApr 2024Apr 2024May 2025
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 mini$7.20
  • GPT-4.1$36.00
  • Mistral Medium 3$8.00
04 — Questions

Which should you choose?

Which is better: GPT-4.1 mini, GPT-4.1 or Mistral Medium 3?

GPT-4.1 mini is the better all-round choice, scoring 60/100 against GPT-4.1 (53) and Mistral Medium 3 (53). It leads on price. GPT-4.1 wins on capability. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, GPT-4.1 mini, GPT-4.1 or Mistral Medium 3?

GPT-4.1 mini is cheaper at $0.40 input / $1.60 output per million tokens (official OpenAI API price). Mistral Medium 3 costs $0.40 input / $2.00 output per million tokens (official Mistral API price); 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 $0.70 per million tokens for GPT-4.1 mini versus $0.80 for Mistral Medium 3 (1.1× as much) and $3.50 for GPT-4.1 (5× as much).

Which scores higher on benchmarks?

GPT-4.1 scores higher on the Capabilities Index (ECI): GPT-4.1 136.8 (#111 of 148), GPT-4.1 mini 135.0 (#115 of 148) and Mistral Medium 3 134.1 (#117 of 148). The confidence ranges of the top two overlap (133.6–138.4 vs 131.2–136.6), so treat the gap as small. On individual benchmarks: GPQA Diamond — GPT-4.1 66.9%, GPT-4.1 mini 65.9%, Mistral Medium 3 59.5%; OTIS Mock AIME 2024–2025 — GPT-4.1 mini 44.7%, GPT-4.1 38.3%, Mistral Medium 3 32.2%.

Which is better for coding?

There are no published SWE-bench Verified results for GPT-4.1 mini and Mistral Medium 3 yet, so there is no like-for-like coding score. On overall capability, GPT-4.1 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 mini and GPT-4.1 have the largest context windows (1,047,576 and 1,047,576 tokens), against 131,072 for Mistral Medium 3. Maximum output per response: GPT-4.1 mini up to 32,768, GPT-4.1 up to 32,768, Mistral Medium 3 up to 131,072 tokens.

Which can read images, PDFs, audio or video?

GPT-4.1 mini accepts text, images and PDFs; GPT-4.1 accepts text, images and PDFs; Mistral Medium 3 accepts text and images. GPT-4.1 mini handles the widest range of inputs.

Are any of these open source?

No. GPT-4.1 mini, GPT-4.1 and Mistral Medium 3 are proprietary and only available through APIs and apps.

Which is newer?

Mistral Medium 3 is the newest, released May 7, 2025. GPT-4.1 mini came out Apr 14, 2025; GPT-4.1 came out Apr 14, 2025. Knowledge cutoff: GPT-4.1 mini Apr 2024, GPT-4.1 Apr 2024, Mistral Medium 3 May 2025.

How do you decide the winner?

Each model gets a 0–100 score on 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 Oct 4, 2026.

05 — Keep comparing

Related comparisons