ZMIME
Comparison · 3 models · Updated Nov 2, 2026

Kimi K2.7 Code vs Mistral Large 4 vs Inkling

Mistral Large 4 comes out ahead, 67 to 63 and 63 on our weighted score, and it is the cheaper option too.

  1. 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
  2. Our pick

    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

  3. Thinking Machines

    Inkling

    Released Jul 15, 2026

    63/100
    • ECI148.5
    • Price$1.00 / $4.05
    • Context1.05M
    Full specs Remove Inkling
01 — Verdict

Mistral Large 4 is our pick

Mistral Large 4 is the better all-round choice, scoring 67/100 against Kimi K2.7 Code (63) and Inkling (63). It leads on price. Kimi K2.7 Code wins on inputs & features. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityMistral Large 4Capabilities Index (ECI): Mistral Large 4 150.6 · Kimi K2.7 Code 150.2 · Inkling 148.5
  • Lowest priceMistral Large 4Mistral Large 4 $1.05 · Kimi K2.7 Code $1.71 · Inkling $1.76 per 1M tokens (3:1 blend)
  • Longest contextMistral Large 4 and InklingMistral Large 4 1,048,576 · Inkling 1,048,576 · Kimi K2.7 Code 262,144 tokens
  • Widest inputsKimi K2.7 Code and InklingKimi K2.7 Code: Text, Images, Video · Mistral Large 4: Text, Images · Inkling: Text, Images, Audio
  • Self-hostingKimi K2.7 Code and InklingPublishes downloadable weights (Apache-2.0)
How the score is built
MeasureWeightKimi K2.7 CodeMistral Large 4Inkling
CapabilityCapabilities Index (ECI)50%777775
Price25%374737
Inputs & features15%807070
Context window10%376161
Overall100%63/10067/10063/100
02 — Side by side

Every spec in one table

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

Kimi K2.7 Code vs Mistral Large 4 vs Inkling specifications side by side
SpecificationKimi K2.7 CodeMoonshot AIMistral Large 4Mistral AIInklingThinking Machines
Capability
Capabilities Index (ECI)150.2150.6 (best)148.5
ECI rank#59 of 165#57 of 165 (best)#67 of 165
GPQA DiamondGraduate-level science questions87.9%88.1%88.3% (best)
FrontierMath Tiers 1–3Research-level mathematics54.0%58.6% (best)33.3%
OTIS Mock AIME 2024–2025Competition mathematics95.6%98.3% (best)88.9%
SimpleQA VerifiedShort factual questions36.5%20.0%40.3% (best)
Price per million tokens
Input$0.95$0.70 (best)$1.00
Output$4.00$2.10 (best)$4.05
Cached input$0.19$0.07 (best)$0.17
Blended (3:1)$1.71$1.05 (best)$1.76
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Moonshot AI APIOfficial Mistral APIOfficial Thinking Machines API
Limits
Context window262,144 tokens1,048,576 tokens (best)1,048,576 tokens (best)
Max output262,144 tokens262,144 tokens1,048,576 tokens (best)
Inputs and features
TextYesYesYes
ImagesYesYesYes
PDFsNoNoNo
AudioNoNoYes
VideoYesNoNo
ReasoningYesYeslow · medium · highYeslow · medium · high · xhigh · max
Tool callingYesYesYes
Structured outputYesYesNo
Availability
WeightsOpenProprietaryOpenApache-2.0
API model IDkimi-k2.7-codemistral-large-4thinkingmachines/Inkling:peft:262144:sampling-nvfp4
API providers49 (best)1520
ReleasedJun 12, 2026Oct 6, 2026Jul 15, 2026
Knowledge cutoffJan 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.

  • Kimi K2.7 Code$17.50
  • Mistral Large 4$11.20
  • Inkling$18.10
04 — Questions

Which should you choose?

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

Mistral Large 4 is the better all-round choice, scoring 67/100 against Kimi K2.7 Code (63) and Inkling (63). It leads on price. Kimi K2.7 Code wins on inputs & features. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

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

Mistral Large 4 is cheaper at $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); Inkling costs $1.00 input / $4.05 output per million tokens (official Thinking Machines API price). At a typical mix of three input tokens to one output token, that is $1.05 per million tokens for Mistral Large 4 versus $1.71 for Kimi K2.7 Code (1.6× as much) and $1.76 for Inkling (1.7× 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), Kimi K2.7 Code 150.2 (#59 of 165) and Inkling 148.5 (#67 of 165). The confidence ranges of the top two overlap (147.4–153.5 vs 148.1–151.9), so treat the gap as small. On individual benchmarks: GPQA Diamond — Inkling 88.3%, 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 33.3%; OTIS Mock AIME 2024–2025 — Mistral Large 4 98.3%, Kimi K2.7 Code 95.6%, Inkling 88.9%; SimpleQA Verified — Inkling 40.3%, Kimi K2.7 Code 36.5%, Mistral Large 4 20.0%.

Which is better for coding?

There are no published SWE-bench Verified results for Kimi K2.7 Code, Mistral Large 4 and Inkling 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 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: Kimi K2.7 Code up to 262,144, Mistral Large 4 up to 262,144, Inkling up to 1,048,576 tokens.

Which can read images, PDFs, audio or video?

Kimi K2.7 Code accepts text, images and video; Mistral Large 4 accepts text and images; Inkling 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 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 came out Jul 15, 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