ZMIME
Comparison · 3 models · Updated Nov 2, 2026

Mistral Large 4 vs Kimi K2.7 Code vs Inkling Small

Too close to call on our weighted score (Inkling Small 68, Mistral Large 4 67, Kimi K2.7 Code 63). The right pick depends on what you value most.

  1. Mistral AI

    Mistral Large 4

    Released Oct 6, 2026NewBeta

    67/100
    • ECI150.6
    • Price$0.70 / $2.10
    • Context1.05M
    Full specs Remove Mistral Large 4

  2. Moonshot AI

    Kimi K2.7 Code

    Released Jun 12, 2026

    63/100
    • ECI150.2
    • Price$0.95 / $4.00
    • Context262K
    Full specs Remove Kimi K2.7 Code

  3. Thinking Machines

    Inkling Small

    Released Jul 30, 2026

    68/100
    • ECI150.5
    • Price$0.58 / $1.44
    • Context1.05M
    Full specs Remove Inkling Small
01 — Verdict

Too close to call

It is close. Our weighted score puts them within 1 points (Inkling Small 68/100, Mistral Large 4 67/100, Kimi K2.7 Code 63/100), so choose by what matters most for your work: Mistral Large 4 for raw capability and Inkling Small on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityMistral Large 4Capabilities Index (ECI): Mistral Large 4 150.6 · Inkling Small 150.5 · Kimi K2.7 Code 150.2
  • Lowest priceInkling SmallInkling Small $0.795 · Mistral Large 4 $1.05 · Kimi K2.7 Code $1.71 per 1M tokens (3:1 blend)
  • Longest contextMistral Large 4 and Inkling SmallMistral Large 4 1,048,576 · Inkling Small 1,048,576 · Kimi K2.7 Code 262,144 tokens
  • Widest inputsKimi K2.7 Code and Inkling SmallMistral Large 4: Text, Images · Kimi K2.7 Code: Text, Images, Video · Inkling Small: Text, Images, Audio
  • Self-hostingKimi K2.7 Code and Inkling SmallPublishes downloadable weights (Apache-2.0)
How the score is built
MeasureWeightMistral Large 4Kimi K2.7 CodeInkling Small
CapabilityCapabilities Index (ECI)50%777777
Price25%473752
Inputs & features15%708070
Context window10%613761
Overall100%67/10063/10068/100
02 — Side by side

Every spec in one table

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

Mistral Large 4 vs Kimi K2.7 Code vs Inkling Small specifications side by side
SpecificationMistral Large 4Mistral AIKimi K2.7 CodeMoonshot AIInkling SmallThinking Machines
Capability
Capabilities Index (ECI)150.6 (best)150.2150.5
ECI rank#57 of 165 (best)#59 of 165#58 of 165
GPQA DiamondGraduate-level science questions88.1%87.9%88.5% (best)
FrontierMath Tiers 1–3Research-level mathematics58.6% (best)54.0%46.3%
OTIS Mock AIME 2024–2025Competition mathematics98.3% (best)95.6%90.0%
SimpleQA VerifiedShort factual questions20.0%36.5% (best)19.1%
Price per million tokens
Input$0.70$0.95$0.58 (best)
Output$2.10$4.00$1.44 (best)
Cached input$0.07 (best)$0.19$0.116
Blended (3:1)$1.05$1.71$0.795 (best)
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Mistral APIOfficial Moonshot AI APIOfficial Thinking Machines API
Limits
Context window1,048,576 tokens (best)262,144 tokens1,048,576 tokens (best)
Max output262,144 tokens262,144 tokens1,048,576 tokens (best)
Inputs and features
TextYesYesYes
ImagesYesYesYes
PDFsNoNoNo
AudioNoNoYes
VideoNoYesNo
ReasoningYeslow · medium · highYesYeslow · medium · high · xhigh · max
Tool callingYesYesYes
Structured outputYesYesNo
Availability
WeightsProprietaryOpenOpenApache-2.0
API model IDmistral-large-4kimi-k2.7-codethinkingmachines/Inkling-Small
API providers1549 (best)12
ReleasedOct 6, 2026Jun 12, 2026Jul 30, 2026
Knowledge cutoff—Jan 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.

  • Mistral Large 4$11.20
  • Kimi K2.7 Code$17.50
  • Inkling Small$8.68
04 — Questions

Which should you choose?

Which is better: Mistral Large 4, Kimi K2.7 Code or Inkling Small?

It is close. Our weighted score puts them within 1 points (Inkling Small 68/100, Mistral Large 4 67/100, Kimi K2.7 Code 63/100), so choose by what matters most for your work: Mistral Large 4 for raw capability and Inkling Small on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, Mistral Large 4, Kimi K2.7 Code or Inkling Small?

Inkling Small is cheaper at $0.58 input / $1.44 output per million tokens (official Thinking Machines API price). Mistral Large 4 costs $0.70 input / $2.10 output per million tokens (official Mistral API price); Kimi K2.7 Code costs $0.95 input / $4.00 output per million tokens (official Moonshot AI API price). At a typical mix of three input tokens to one output token, that is $0.795 per million tokens for Inkling Small versus $1.05 for Mistral Large 4 (1.3× as much) and $1.71 for Kimi K2.7 Code (2.2× as much).

Which scores higher on benchmarks?

Mistral Large 4 scores higher on the Capabilities Index (ECI): Mistral Large 4 150.6 (#57 of 165), Inkling Small 150.5 (#58 of 165) and Kimi K2.7 Code 150.2 (#59 of 165). The confidence ranges of the top two overlap (147.4–153.5 vs 147.7–152.4), so treat the gap as small. On individual benchmarks: GPQA Diamond — Inkling Small 88.5%, Mistral Large 4 88.1%, Kimi K2.7 Code 87.9%; FrontierMath Tiers 1–3 — Mistral Large 4 58.6%, Kimi K2.7 Code 54.0%, Inkling Small 46.3%; OTIS Mock AIME 2024–2025 — Mistral Large 4 98.3%, Kimi K2.7 Code 95.6%, Inkling Small 90.0%; SimpleQA Verified — Kimi K2.7 Code 36.5%, Mistral Large 4 20.0%, Inkling Small 19.1%.

Which is better for coding?

There are no published SWE-bench Verified results for Mistral Large 4, Kimi K2.7 Code and Inkling Small yet, so there is no like-for-like coding score. On overall capability, Mistral Large 4 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?

Mistral Large 4 and Inkling Small have the largest context windows (1,048,576 and 1,048,576 tokens), against 262,144 for Kimi K2.7 Code. Maximum output per response: Mistral Large 4 up to 262,144, Kimi K2.7 Code up to 262,144, Inkling Small up to 1,048,576 tokens.

Which can read images, PDFs, audio or video?

Mistral Large 4 accepts text and images; Kimi K2.7 Code accepts text, images and video; Inkling Small accepts text, images and audio. Kimi K2.7 Code handles the widest range of inputs.

Are any of these open source?

Kimi K2.7 Code and Inkling Small publishes its weights (Apache-2.0) and can be self-hosted; Mistral Large 4 is proprietary.

Which is newer?

Mistral Large 4 is the newest, released Oct 6, 2026. Inkling Small came out Jul 30, 2026; Kimi K2.7 Code came out Jun 12, 2026. Knowledge cutoff: Kimi K2.7 Code Jan 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 Nov 2, 2026.

05 — Keep comparing

Related comparisons