ZMIME
Comparison · 3 models · Updated Oct 4, 2026

Kimi K2.7 Code vs DeepSeek-R1 vs Grok 4.3

Too close to call on our weighted score (Grok 4.3 67, Kimi K2.7 Code 64, DeepSeek-R1 51). The right pick depends on what you value most.

  1. Moonshot AI

    Kimi K2.7 Code

    Released Jun 12, 2026

    64/100
    • ECI150.0
    • Price$0.95 / $4.00
    • Context262K
    Full specs Remove Kimi K2.7 Code

  2. DeepSeek

    DeepSeek-R1

    Released Jan 20, 2025

    51/100
    • ECI139.0
    • Price$0.70 / $2.60
    • Context128K
    Full specs Remove DeepSeek-R1

  3. xAI

    Grok 4.3

    Released Apr 17, 2026

    67/100
    • ECI149.2
    • Price$1.25 / $2.50
    • Context1M
    Full specs Remove Grok 4.3
01 — Verdict

Too close to call

It is close. Our weighted score puts them within 2 points (Grok 4.3 67/100, Kimi K2.7 Code 64/100, DeepSeek-R1 51/100), so choose by what matters most for your work: Kimi K2.7 Code for raw capability, DeepSeek-R1 on price and Grok 4.3 for long inputs. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityKimi K2.7 CodeCapabilities Index (ECI): Kimi K2.7 Code 150.0 · Grok 4.3 149.2 · DeepSeek-R1 139.0
  • Lowest priceDeepSeek-R1DeepSeek-R1 $1.18 · Grok 4.3 $1.56 · Kimi K2.7 Code $1.71 per 1M tokens (3:1 blend)
  • Longest contextGrok 4.3Grok 4.3 1,000,000 · Kimi K2.7 Code 262,144 · DeepSeek-R1 128,000 tokens
  • Widest inputsKimi K2.7 Code and Grok 4.3Kimi K2.7 Code: Text, Images, Video · DeepSeek-R1: Text · Grok 4.3: Text, Images, PDFs
  • Self-hostingKimi K2.7 Code and DeepSeek-R1Publishes downloadable weights
How the score is built
MeasureWeightKimi K2.7 CodeDeepSeek-R1Grok 4.3
CapabilityCapabilities Index (ECI)50%786477
Price25%394741
Inputs & features15%803580
Context window10%372460
Overall100%64/10051/10067/100
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 DeepSeek-R1 vs Grok 4.3 specifications side by side
SpecificationKimi K2.7 CodeMoonshot AIDeepSeek-R1DeepSeekGrok 4.3xAI
Capability
Capabilities Index (ECI)150.0 (best)139.0149.2
ECI rank#49 of 148 (best)#104 of 148#55 of 148
GPQA DiamondGraduate-level science questions87.9%71.7%88.8% (best)
FrontierMath Tiers 1–3Research-level mathematics54.0% (best)—42.8%
OTIS Mock AIME 2024–2025Competition mathematics95.6% (best)53.3%93.3%
SimpleQA VerifiedShort factual questions36.5% (best)—33.2%
Price per million tokens
Input$0.95$0.70 (best)$1.25
Output$4.00$2.60$2.50 (best)
Cached input$0.19 (best)—$0.20
Blended (3:1)$1.71$1.18 (best)$1.56
Long-context rateSame rateSame rateOver 200K: $2.50 / $5.00
Price sourceOfficial Moonshot AI APIMedian of 11 providersOfficial xAI API
Limits
Context window262,144 tokens128,000 tokens1,000,000 tokens (best)
Max output262,144 tokens (best)32,768 tokens30,000 tokens
Inputs and features
TextYesYesYes
ImagesYesNoYes
PDFsNoNoYes
AudioNoNoNo
VideoYesNoNo
ReasoningYesYesYeslow · medium · high
Tool callingYesYesYes
Structured outputYesNoYes
Availability
WeightsOpenOpenProprietary
API model IDkimi-k2.7-code—grok-4.3
API providers51 (best)1227
ReleasedJun 12, 2026Jan 20, 2025Apr 17, 2026
Knowledge cutoffJan 2025Jul 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.

  • Kimi K2.7 Code$17.50
  • DeepSeek-R1$12.20
  • Grok 4.3$17.50
04 — Questions

Which should you choose?

Which is better: Kimi K2.7 Code, DeepSeek-R1 or Grok 4.3?

It is close. Our weighted score puts them within 2 points (Grok 4.3 67/100, Kimi K2.7 Code 64/100, DeepSeek-R1 51/100), so choose by what matters most for your work: Kimi K2.7 Code for raw capability, DeepSeek-R1 on price and Grok 4.3 for long inputs. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, Kimi K2.7 Code, DeepSeek-R1 or Grok 4.3?

DeepSeek-R1 is cheaper at $0.70 input / $2.60 output per million tokens (median across 11 API providers). Grok 4.3 costs $1.25 input / $2.50 output per million tokens (official xAI 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 $1.18 per million tokens for DeepSeek-R1 versus $1.56 for Grok 4.3 (1.3× as much) and $1.71 for Kimi K2.7 Code (1.5× as much).

Which scores higher on benchmarks?

Kimi K2.7 Code scores higher on the Capabilities Index (ECI): Kimi K2.7 Code 150.0 (#49 of 148), Grok 4.3 149.2 (#55 of 148) and DeepSeek-R1 139.0 (#104 of 148). The confidence ranges of the top two overlap (148.1–151.8 vs 147.6–150.8), so treat the gap as small. On individual benchmarks: GPQA Diamond — Grok 4.3 88.8%, Kimi K2.7 Code 87.9%, DeepSeek-R1 71.7%; OTIS Mock AIME 2024–2025 — Kimi K2.7 Code 95.6%, Grok 4.3 93.3%, DeepSeek-R1 53.3%.

Which is better for coding?

There are no published SWE-bench Verified results for Kimi K2.7 Code, DeepSeek-R1 and Grok 4.3 yet, so there is no like-for-like coding score. On overall capability, Kimi K2.7 Code 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?

Grok 4.3 has the largest context window at 1,000,000 tokens, against 262,144 for Kimi K2.7 Code and 128,000 for DeepSeek-R1. Maximum output per response: Kimi K2.7 Code up to 262,144, DeepSeek-R1 up to 32,768, Grok 4.3 up to 30,000 tokens.

Which can read images, PDFs, audio or video?

Kimi K2.7 Code accepts text, images and video; DeepSeek-R1 accepts text; Grok 4.3 accepts text, images and PDFs. Kimi K2.7 Code handles the widest range of inputs.

Are any of these open source?

Kimi K2.7 Code and DeepSeek-R1 publishes its weights and can be self-hosted; Grok 4.3 is proprietary.

Which is newer?

Kimi K2.7 Code is the newest, released Jun 12, 2026. Grok 4.3 came out Apr 17, 2026; DeepSeek-R1 came out Jan 20, 2025. Knowledge cutoff: Kimi K2.7 Code Jan 2025, DeepSeek-R1 Jul 2024.

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