Kimi K2.6

Moonshot AIKey kimi-k2.6Also reported as moonshotai/kimi-k2.6, cr/kimi-k2.6, hf:moonshotai/kimi-k2.6, ocg/kimi-k2.6, moonshot-cn/kimi-k2.6, opencode-go/kimi-k2.6, neuralwatt/moonshotai/kimi-k2.6, workers-ai/@cf/moonshotai/kimi-k2.6, @cf/moonshotai/kimi-k2.6, pro/moonshotai/kimi-k2.6, bbg/moonshotai/kimi-k2.6, gnk24/kimi-k2.6, cmc/moonshotai/kimi-k2.6, dahl/moonshotai/kimi-k2.6, wsf/kimi-k2.6, crof/kimi-k2.6, synthetic/kimi-k2.6, gnkrtr/moonshotai/kimi-k2.6, synthetic/hf:moonshotai/kimi-k2.6, Pro/moonshotai/Kimi-K2.6

Rank
#265
by active users
Active users
3
Down 7 from 10 active users in the previous 30 days. vs previous 30 days
Adoption
0.3%
of 956 accounts
Tokens
11.4M
cache included
Est. cost
$11
at public list prices
First seen
Apr 15, 2026
in any submission

Oct 15 – Nov 13, 2026 (UTC)956 accounts100% of tokens from an identified modelData through Nov 13, 2026, 01:06 UTCHow we count

Daily active users

Distinct accounts that used this model on each UTC day.

0 active users on Nov 13, 2026

Daily active users for Kimi K2.6, Oct 15, 2026 to Nov 13, 2026. Peak 1. Use the left and right arrow keys to read each day.110
Show daily values
Daily active users and tokens for Kimi K2.6
Date (UTC)Active usersTokens
Oct 15, 202600
Oct 16, 202600
Oct 17, 202600
Oct 18, 202600
Oct 19, 202600
Oct 20, 202600
Oct 21, 202600
Oct 22, 2026124
Oct 23, 202600
Oct 24, 202600
Oct 25, 202600
Oct 26, 202600
Oct 27, 202600
Oct 28, 202600
Oct 29, 202600
Oct 30, 202600
Oct 31, 202600
Nov 1, 202600
Nov 2, 202600
Nov 3, 202600
Nov 4, 202600
Nov 5, 202600
Nov 6, 202600
Nov 7, 202600
Nov 8, 20261175
Nov 9, 2026110.6M
Nov 10, 20261863K
Nov 11, 202600
Nov 12, 202600
Nov 13, 202600

Token mix

How the 11.4M tokens split. Cache reads are usually most of an agent's tokens and are priced far below input.

  • Input33%
  • Output0.3%
  • Cache read65%
  • Cache write0%
  • Reasoning0.9%

Agents that carry Kimi K2.6

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

  1. OpenCode100% of this model's tokens1active users
  2. cc-mirror/curl<0.1% of this model's tokens1active users
  3. Codex CLI<0.1% of this model's tokens1active users

Benchmarks

The best result for Kimi K2.6 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
    151.6
    Rank #60 of 158 matched modelsNo conditions reportedModel released Apr 20, 2026Source: epoch.ai (opens in a new tab)
  • WebDev ArenaWeb development · LMArena
    1,509
    Rank #51 of 110 matched modelsNo conditions reportedPublished Oct 19, 2026Source: huggingface.co (opens in a new tab)
  • GPQA DiamondReasoning · Epoch AI
    90.8%
    Rank #40 of 160 matched modelsNo conditions reportedRun date May 1, 2026Source: epoch.ai (opens in a new tab)

    Near its ceiling: the top score is 96.5%, and Epoch AI estimates the reachable maximum at 97%. Differences between top models are small.

  • FrontierMath Tiers 1–3 (v2)Reasoning · Epoch AI
    57.2%
    Rank #49 of 90 matched modelsNo conditions reportedRun date Jun 10, 2026Source: epoch.ai (opens in a new tab)

    Near its ceiling: the top score is 95.1%, and Epoch AI estimates the reachable maximum at 95%. Differences between top models are small.

  • SimpleQA VerifiedKnowledge · Epoch AI
    34.9%
    Rank #58 of 86 matched modelsNo conditions reportedRun date Aug 10, 2026Source: epoch.ai (opens in a new tab)
  • SWE-bench VerifiedHistory · Epoch AI
    76.7%
    Rank #10 of 32 matched modelsNo conditions reportedRun date May 8, 2026Source: epoch.ai (opens in a new tab)

    History only. Newer agentic coding benchmarks are on the main board.

Not evaluated: Humanity's Last Exam, Terminal-Bench 4.1, CursorBench, DeepSWE, 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 Nov 12, 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
$0.47
Est. per 1M tokens
65% cache reads
At the community mix
$0.20
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 65% of Kimi K2.6 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 $0.16.
  • 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-k2.6
    $0.95 input per 1M tokens$4 output per 1M tokens$0.16 cache read per 1M tokensCache write not listed262K tokens of context
  • Azurekimi-k2.6
    $0.95 input per 1M tokens$4 output per 1M tokensCache read not listedCache write not listed262K tokens of context
  • OpenRoutermoonshotai/kimi-k2.6
    $0.65 input per 1M tokens$3.41 output per 1M tokens$0.15 cache read per 1M tokensCache write not listed262K tokens of context
  • Vercel AI Gatewaymoonshotai/kimi-k2.6
    $0.95 input per 1M tokens$4 output per 1M tokens$0.16 cache read per 1M tokensCache write not listed262K tokens of context
  • Deep Inframoonshotai/Kimi-K2.6
    $0.75 input per 1M tokens$3.50 output per 1M tokens$0.15 cache read per 1M tokensCache write not listed262K tokens of context

Specs

From models.dev (MIT), retrieved Nov 12, 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
Apr 20, 2026
Open weights
Yes
Reasoning
Yes
Tool calling
Yes

Top public profiles

Public profiles that used Kimi K2.6 most in this period, by tokens. Hidden accounts are never listed.

  1. 1Joscha Götzer@JosXa11.4Mtokens$11est. cost2active days$11 est. cost · 2 active days
  2. 2如是@MiFaZhan175tokens<$1est. cost1active days<$1 est. cost · 1 active days
  3. 3Casper@Casper01524tokens—est. cost1active daysno price · 1 active days

More from Moonshot AI

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

  1. Kimi K36.0% adoption57active users
  2. Kimi K3.1 Pro4.4% adoption42active users
  3. Kimi K2.7 Code1.8% adoption17active users
  4. Kimi For Coding1.4% adoption13active users
  5. Kimi K3 10.7% adoption7active users
  6. Kimi K3 Max0.4% 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 Nov 12, 2026 · Data through Nov 9, 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 Nov 12, 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