GoTry AI

Kimi K3

Language Moonshot AI Available Released Jul 16, 2026 Partly verified
Model ID
Context
1.05M
1.05M max output
Input price
$3.00
per 1M tokens · Moonshot AI Platform
Output price
$15.00
per 1M tokens
Epoch Capabilities Index
157.7
#12 of 71 listed
LMArena Text
1,488
#12 of 79 listed

Where to run it

2 offerings · prices as listed
MeterTierPrice
Moonshot AI Platform (opens in a new tab) Official Global · USD kimi-k3
InputStandard $3.00 / 1M tokens
OutputStandard $15.00 / 1M tokens
Cache readStandard $0.30 / 1M tokens
Cache write5-minute cache $3.00 / 1M tokens
1-hour cache $6.00 / 1M tokens
Moonshot AI Platform (opens in a new tab) Official China · CNY kimi-k3
InputStandard ¥20.00 / 1M tokens
OutputStandard ¥100.00 / 1M tokens
Cache readStandard ¥2.00 / 1M tokens
Cache write5-minute cache ¥20.00 / 1M tokens
1-hour cache ¥40.00 / 1M tokens
  1. 2 new prices on Moonshot AI Platform Cache write (5-minute cache) $3.00 · Cache write (1-hour cache) $6.00

Vendor-reported scores

Published by Moonshot AI, under the conditions it states
BenchmarkSettingScore
GPQA Diamondreasoning effort max93.5%
Humanity's Last Examfull set, no tools, reasoning effort max43.5%
full set, with general tools, reasoning effort max56%
Terminal-Bench 2.1Kimi Code harness, reasoning effort max88.3%
BrowseCompcontext compaction at 300K tokens, reasoning effort max91.2%
full 1M-token context, no context management, reasoning effort max90.4%
MCP-Atlas500-task public subset, 100-turn limit, Gemini 3.1 Pro judge, reasoning effort max84.2%
OSWorld-Verifiedreasoning effort max84.8%
MMMU-Prono tools, avg of 3 runs, reasoning effort max81.6%
with Python tool, avg of 3 runs, reasoning effort max83.4%

Cited scores

From third-party leaderboards, not measured by us
  • Epoch Capabilities Index 157.7

    #12 of 71 listed models · CI 155.1–160.7

    Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Sep 26, 2026 · changes we made

  • LMArena Text 1,488

    #12 of 79 listed models · max effort · CI 1,483–1,493 · 26,400 votes

    LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 25, 2026 · changes we made

  • Epoch AI · FrontierMath Tiers 1–3 72.2%

    #16 of 56 listed models · max effort · ±2.66

    Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Sep 26, 2026 · changes we made

  • Epoch AI · GPQA Diamond 93.1%

    #13 of 64 listed models · max effort · ±1.49

    Also listed: high effort 91.9% · low effort 84.8%

    Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Sep 26, 2026 · changes we made

  • LMArena Text · Chinese 1,540

    #7 of 79 listed models · max effort · CI 1,526–1,554 · 1,940 votes

    LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 25, 2026 · changes we made

  • LMArena Text · Coding 1,541

    #6 of 79 listed models · max effort · CI 1,533–1,548 · 6,878 votes

    LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 25, 2026 · changes we made