Kimi K2.7 Code

Moonshot AIKey kimi-k2.7-codeAlso reported as moonshotai/kimi-k2.7-code, kimi/kimi-k2.7-code, synthetic/hf:moonshotai/kimi-k2.7-code, alibaba/kimi-k2.7-code, @cf/moonshotai/kimi-k2.7-code, pecut/kimi-k2.7-code, neuralwatt/kimi-k2.7-code, opencode-go/kimi-k2.7-code, kimi k2.7 code, olm/kimi-k2.7-code, cf/@cf/moonshotai/kimi-k2.7-code, vova/kimi-k2.7-code, vibeproxy/kimi-k2.7-code, moonshot-cn/kimi-k2.7-code, moonshotai/Kimi-K2.7-Code

Rank
#78
by active users
Active users
17
Down 6 from 23 active users in the previous 30 days. vs previous 30 days
Adoption
1.8%
of 958 accounts
Tokens
112.5M
cache included
Est. cost
$26
at public list prices
First seen
Jan 14, 2026
in any submission

Oct 14 – Nov 12, 2026 (UTC)958 accounts100% of tokens from an identified modelData through Nov 12, 2026, 00:47 UTCHow we count

Daily active users

Distinct accounts that used this model on each UTC day.

0 active users on Nov 12, 2026

Daily active users for Kimi K2.7 Code, Oct 14, 2026 to Nov 12, 2026. Peak 3. Use the left and right arrow keys to read each day.320
Show daily values
Daily active users and tokens for Kimi K2.7 Code
Date (UTC)Active usersTokens
Oct 14, 202600
Oct 15, 2026115.1K
Oct 16, 202600
Oct 17, 202612.5M
Oct 18, 202614.7M
Oct 19, 2026127.4K
Oct 20, 20261314K
Oct 21, 2026288.6K
Oct 22, 2026124
Oct 23, 202600
Oct 24, 202600
Oct 25, 202600
Oct 26, 202600
Oct 27, 202600
Oct 28, 202616M
Oct 29, 2026167.1K
Oct 30, 202611.3M
Oct 31, 2026312.8M
Nov 1, 202625.9M
Nov 2, 202600
Nov 3, 2026167.4M
Nov 4, 2026111.4M
Nov 5, 202600
Nov 6, 202616.6K
Nov 7, 202600
Nov 8, 20261255
Nov 9, 202600
Nov 10, 2026143
Nov 11, 202600
Nov 12, 202600

Token mix

How the 112.5M tokens split. Cache reads are usually most of an agent's tokens and are priced far below input.

  • Input3.2%
  • Output0.4%
  • Cache read96%
  • Cache write0%
  • Reasoning0.2%

Agents that carry Kimi K2.7 Code

Each agent's share of this model's tokens, and how many accounts used the model through it.

  1. OpenCode85% of this model's tokens9active users
  2. Claude Code10% of this model's tokens1active users
  3. OpenClaw4.2% of this model's tokens1active users
  4. Oh My Pi0.3% of this model's tokens1active users
  5. Hermes Agent<0.1% of this model's tokens1active users
  6. Pi<0.1% of this model's tokens1active users
  7. cc-mirror/mozilla<0.1% of this model's tokens1active users
  8. cc-mirror/curl<0.1% of this model's tokens1active users
  9. Cursor<0.1% of this model's tokens1active users
  10. Codex CLI<0.1% of this model's tokens1active users

Benchmarks

The best result for Kimi K2.7 Code in each benchmark Tokscale tracks. Each benchmark has its own unit, run conditions and source, so compare a score only with other models on the same benchmark. Rank is among the models Tokscale matched in that benchmark.

All benchmarks
  • Epoch Capabilities IndexOverall · Epoch AI
    150.1
    Rank #57 of 160 matched modelsNo conditions reportedModel released Jun 12, 2026Source: epoch.ai (opens in a new tab)
  • DeepSWEAgentic coding · Datacurve, collected by Epoch AI
    30.5%
    Rank #24 of 26 matched modelsmini-swe-agentModel released Jun 12, 2026Source: deepswe.datacurve.ai (opens in a new tab)
  • WebDev ArenaWeb development · LMArena
    1,474
    Rank #59 of 110 matched modelsNo conditions reportedPublished Oct 19, 2026Source: huggingface.co (opens in a new tab)
  • GPQA DiamondReasoning · Epoch AI
    87.9%
    Rank #53 of 151 matched modelsNo conditions reportedRun date Aug 7, 2026Source: epoch.ai (opens in a new tab)

    Near its ceiling: the top score is 96.4%, and Epoch AI estimates the reachable maximum at 97%. Differences between top models are small.

  • FrontierMath Tiers 1–3 (v2)Reasoning · Epoch AI
    54.0%
    Rank #49 of 86 matched modelsNo conditions reportedRun date Jun 13, 2026Source: epoch.ai (opens in a new tab)

    Near its ceiling: the top score is 93.7%, and Epoch AI estimates the reachable maximum at 95%. Differences between top models are small.

  • SimpleQA VerifiedKnowledge · Epoch AI
    36.5%
    Rank #50 of 80 matched modelsNo conditions reportedRun date Aug 27, 2026Source: epoch.ai (opens in a new tab)

Not evaluated: Humanity's Last Exam, Terminal-Bench 4.0, CursorBench, FrontierSWE, Agent Arena. A missing result is not a score of zero.

Pricing

List prices from models.dev in US dollars per 1M tokens, retrieved Oct 21, 2026. Moonshot AI is the lab's own API and the reference price for the estimates below.

Price at real agent usageEstimate at list prices

What 1M tokens cost at the reference list price when they split into input, output and cache the way Tokscale users' agents used them. It is not what anyone paid.

At this model's mix
$0.24
Est. per 1M tokens
96% cache reads
At the community mix
$0.23
Est. per 1M tokens
96% cache reads
3:1 input/output blend
$1.71
Per 1M tokens at list prices
No cache

Cache reads were 96% of Kimi K2.7 Code tokens in the last 30 days and 96% of all tokens. The 3:1 blend, (3 × input + output) ÷ 4, is the usual comparison and ignores cache.

Assumptions

  • Moonshot AI list prices per 1M tokens: input $0.95, output $4, cache read $0.19.
  • This model's mix is its own input, output, cache and reasoning tokens in the last 30 days.
  • The community mix is the tokens of every identified model in the last 30 days.
  • This is an estimate at list prices, not what anyone paid.
  • Reasoning tokens are priced as output.
  • Long-context tiers, batch pricing and discounts are not applied.
  • Token mixes come from public Tokscale submissions. Hidden accounts are excluded.
  • No cache-write price is listed, so cache writes are priced as input.

List prices by provider

  • Moonshot AIReferencekimi-k2.7-code
    $0.95 input per 1M tokens$4 output per 1M tokens$0.19 cache read per 1M tokensCache write not listed262K tokens of context
  • Azurekimi-k2.7-code
    $0.95 input per 1M tokens$4 output per 1M tokens$0.19 cache read per 1M tokensCache write not listed262K tokens of context
  • OpenRoutermoonshotai/kimi-k2.7-code
    $0.67 input per 1M tokens$3.35 output per 1M tokens$0.18 cache read per 1M tokensCache write not listed262K tokens of context
  • Vercel AI Gatewaymoonshotai/kimi-k2.7-code
    $0.95 input per 1M tokens$4 output per 1M tokens$0.19 cache read per 1M tokensCache write not listed256K tokens of context
Show 2 more providersShow fewer providers
  • Deep Inframoonshotai/Kimi-K2.7-Code
    $0.68 input per 1M tokens$3.40 output per 1M tokens$0.14 cache read per 1M tokensCache write not listed262K tokens of context
  • Basetenmoonshotai/Kimi-K2.7-Code
    $0.95 input per 1M tokens$4 output per 1M tokens$0.16 cache read per 1M tokensCache write not listed262K tokens of context

Specs

From models.dev (MIT), retrieved Oct 21, 2026, as the lab or the first listed provider reports them. A dash means models.dev does not list the value.

Context window
262K tokens
Max output
262K tokens
Input
Text, Image, Video
Output
Text
Knowledge cutoff
Jan 2025
Release date
Jun 12, 2026
Open weights
Yes
Reasoning
Yes
Tool calling
Yes

Top public profiles

Public profiles that used Kimi K2.7 Code most in this period, by tokens. Hidden accounts are never listed.

  1. 1Hyunsoo Lee@hansLee-it78.8Mtokens$18est. cost2active days$18 est. cost · 2 active days
  2. 2Stark Liu@DimensionPrism11.7Mtokens$3est. cost2active days$3 est. cost · 2 active days
  3. 3Jiko Diga@jiko176.2Mtokens$2est. cost2active days$2 est. cost · 2 active days
  4. 4Michael Burr@CubityFirst6Mtokens$1est. cost1active days$1 est. cost · 1 active days
  5. 5Brandon@cloud-aspect4.7Mtokens$1est. cost1active days$1 est. cost · 1 active days
  6. 6Muhammad Abdullah@iAbdullahMughal2.5Mtokens<$1est. cost1active days<$1 est. cost · 1 active days
  7. 7皓@hpware2.1Mtokens<$1est. cost1active days<$1 est. cost · 1 active days
  8. 8Yuzu Octopus@yuzu-octopus314Ktokens<$1est. cost1active days<$1 est. cost · 1 active days
  9. 9PROTIK MONDAL@MNDL-2773.8Ktokens—est. cost2active daysno price · 2 active days
  10. 10BitmanAlan@BitmanAlan64.3Ktokens<$1est. cost1active days<$1 est. cost · 1 active days

More from Moonshot AI

Other Moonshot AI models in the same period, by active users.

  1. Kimi K35.8% adoption56active users
  2. Kimi K3.1 Pro4.1% adoption39active users
  3. Kimi For Coding1.3% adoption12active users
  4. Kimi K3 10.8% adoption8active users
  5. Kimi K3 Max0.4% adoption4active users
  6. Kimi For Coding Highspeed0.4% adoption4active users
All models

Sources and attribution

Each score keeps its own source, unit and run conditions. Tokscale does not combine benchmarks into one score, and a missing score means the model was not evaluated, not that it scored zero.

  • Epoch AIEpoch Capabilities Index, Epoch's own runs and the external results it collects.CC BY 4.0 · Retrieved Oct 21, 2026 · Data through Oct 15, 2026Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from https://epoch.ai/benchmarks.
  • LMArenaWebDev Arena and Agent Arena leaderboards.CC BY 4.0 · Retrieved Oct 21, 2026 · Data through Oct 19, 2026LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset), Hugging Face.
  • models.devSpecs and list prices per provider.MIT · Retrieved Oct 21, 2026models.dev, an open catalog of AI models (github.com/anomalyco/models.dev).
  • TokscaleActive users, tokens and token mix from public Tokscale submissions. Hidden accounts are excluded.How we count