ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Mistral Medium 3 vs Mistral Medium 3.1 vs GPT-4.1 mini

No independent capability benchmark covers every model here yet. The score uses price, inputs & features and context window.

Price in rating: Included · Exclude price

  1. Mistral AI

    Mistral Medium 3

    Released May 7, 2025Deprecated

    48/100
    • ECI132.8
    • Price$0.40 / $2.00
    • Context131K
  2. Mistral AI

    Mistral Medium 3.1

    Released Aug 12, 2025

    50/100
    • ECI—
    • Price$0.44 / $2.20
    • Context131K
  3. OpenAI

    GPT-4.1 mini

    Released Apr 14, 2025

    61/100
    • ECI134.3
    • Price$0.40 / $1.60
    • Context1.05M
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (GPT-4.1 mini 61/100, Mistral Medium 3.1 50/100, Mistral Medium 3 48/100) compare the available specifications and price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

  • CapabilityNot enough dataNo independent benchmark covers every model here yet
  • Lowest priceGPT-4.1 miniGPT-4.1 mini $0.70 · Mistral Medium 3 $0.80 · Mistral Medium 3.1 $0.88 per 1M tokens (3:1 blend)
  • Longest contextGPT-4.1 miniGPT-4.1 mini 1,047,576 · Mistral Medium 3 131,072 · Mistral Medium 3.1 131,072 tokens
  • Widest inputsMistral Medium 3.1 and GPT-4.1 miniMistral Medium 3: Text, Images · Mistral Medium 3.1: Text, Images, PDFs · GPT-4.1 mini: Text, Images, PDFs
  • Self-hostingNo confirmed open weightsAll three are available only through APIs
How the score is built
MeasureWeightMistral Medium 3Mistral Medium 3.1GPT-4.1 mini
Price50%525055
Inputs & features30%506070
Context window20%323265
Specs & price only100%48/10050/10061/100

Left out because at least one model lacks the data: capability. The remaining weights were rescaled.

02 — Side by side

Every spec in one table

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

Mistral Medium 3 vs Mistral Medium 3.1 vs GPT-4.1 mini specifications side by side
SpecificationMistral Medium 3Mistral AIMistral Medium 3.1Mistral AIGPT-4.1 miniOpenAI
Capability
Capabilities Index (ECI)132.8—134.3 (best)
ECI rank#133 of 158—#128 of 158 (best)
GPQA DiamondGraduate-level science questions59.5%—65.9% (best)
FrontierMath Tiers 1–3Research-level mathematics——6.7%
OTIS Mock AIME 2024–2025Competition mathematics32.2%—44.7% (best)
SimpleQA VerifiedShort factual questions——12.7%
Price per million tokens
Input$0.40 (best)$0.44$0.40 (best)
Output$2.00$2.20$1.60 (best)
Cached input——$0.10
Blended (3:1)$0.80$0.88$0.70 (best)
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Mistral APIMedian of 4 providersOfficial OpenAI API
Limits
Context window131,072 tokens131,072 tokens1,047,576 tokens (best)
Max output131,072 tokens (best)104,857 tokens32,768 tokens
Inputs and features
TextYesYesYes
ImagesYesYesYes
PDFsNoYesYes
AudioNoNoNo
VideoNoNoNo
ReasoningNoNoNo
Tool callingYesYesYes
Structured outputNoNoYes
Availability
WeightsProprietaryProprietaryProprietary
API model IDmistral-medium-2505—gpt-4.1-mini
API providers10430 (best)
ReleasedMay 7, 2025Aug 12, 2025Apr 14, 2025
Knowledge cutoffMay 2025Jun 30, 2025Apr 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.

  • Mistral Medium 3$8.00
  • Mistral Medium 3.1$8.80
  • GPT-4.1 mini$7.20
04 — Questions

Which should you choose?

Which is better: Mistral Medium 3, Mistral Medium 3.1 or GPT-4.1 mini?

There is not enough shared capability evidence to name an overall winner. The scores (GPT-4.1 mini 61/100, Mistral Medium 3.1 50/100, Mistral Medium 3 48/100) compare the available specifications and price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

Which is cheaper, Mistral Medium 3, Mistral Medium 3.1 or GPT-4.1 mini?

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); Mistral Medium 3.1 costs $0.44 input / $2.20 output per million tokens (median across 4 API providers). 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 $0.88 for Mistral Medium 3.1 (1.3× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Mistral Medium 3 has an ECI of 132.8, Mistral Medium 3.1 has not been scored yet and GPT-4.1 mini has an ECI of 134.3.

Which is better for coding?

There are no published SWE-bench Verified results for Mistral Medium 3, Mistral Medium 3.1 and GPT-4.1 mini yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.

Which has the bigger context window?

GPT-4.1 mini has the largest context window at 1,047,576 tokens, against 131,072 for Mistral Medium 3 and 131,072 for Mistral Medium 3.1. Maximum output per response: Mistral Medium 3 up to 131,072, Mistral Medium 3.1 up to 104,857, GPT-4.1 mini up to 32,768 tokens.

Which can read images, PDFs, audio or video?

Mistral Medium 3 accepts text and images; Mistral Medium 3.1 accepts text, images and PDFs; GPT-4.1 mini accepts text, images and PDFs. Mistral Medium 3.1 handles the widest range of inputs.

Are any of these open source?

No. Mistral Medium 3, Mistral Medium 3.1 and GPT-4.1 mini are proprietary and only available through APIs and apps.

Which is newer?

Mistral Medium 3.1 is the newest, released Aug 12, 2025. Mistral Medium 3 came out May 7, 2025; GPT-4.1 mini came out Apr 14, 2025. Knowledge cutoff: Mistral Medium 3 May 2025, Mistral Medium 3.1 Jun 30, 2025, GPT-4.1 mini Apr 2024.

How do you decide the winner?

This rating uses price (50%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (30%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (20%, 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.