Skip to main content

    Moonshot AI

    Kimi K2.6

    Moonshot's Kimi K2.6 remains available alongside K3. Its 1T-parameter MoE activates 32B parameters and supports a 256K-token context, text, images and video, with thinking or instant responses. Moonshot reports orchestration of up to 300 sub-agents over 4,000 coordinated steps and a SWE-Bench Pro score of 58.6 under its published evaluation setup.

    256K tokens
    Multimodal
    Max
    Superseded
    Provider
    Moonshot AI
    Context
    256K
    Catalog · As of Aug 11, 2026Stale · 31d old
    yno subscription tier
    Max
    Released
    Apr 20, 2026
    Speed
    Medium
    Reasoning
    Expert
    Modality
    Multimodal

    Benchmarks

    Quality

    AA Intelligence Index
    31.3points
    Artificial Analysis · Date unknownAge unknown
    AA Coding Index
    61.8points
    Artificial Analysis · Date unknownAge unknown
    GPQA Diamond
    91.1%
    Artificial Analysis · Date unknownAge unknown

    Speed and latency

    Output speed
    86tokens/s
    Artificial Analysis · As of Aug 11, 2026Stale · 31d old

    API pricing

    API input cost
    $0.95/ 1M tokens
    Artificial Analysis · Date unknownAge unknown
    API output cost
    $4.00/ 1M tokens
    Artificial Analysis · Date unknownAge unknown

    Benchmark variant: Kimi K2.6

    AA data retrieved Sep 11, 2026 · Artificial Analysis

    Indexes use points; evaluations use accuracy percentages. API measurements do not measure yno application performance. Methodology

    Capabilities

    • Agentic
    • Code
    • Vision
    • Video
    • Tool Use
    • Long Horizon

    Use cases

    • Agent swarms
    • Long-running coding agents
    • Visual analysis
    • 4K-step coordinated workflows

    Strengths

    • Vendor-reported SWE-Bench Pro 58.6
    • Vendor-described 300-agent orchestration
    • Native image and video input
    • 256K context

    Best for

    Enterprise teams running large-scale multi-agent workflows that need to reason over hours

    Use Kimi K2.6 in yno.ai

    No credit card required

    Related models

    Frequently asked

    What is Kimi K2.6?
    Moonshot's Kimi K2.6 remains available alongside K3. Its 1T-parameter MoE activates 32B parameters and supports a 256K-token context, text, images and video, with thinking or instant responses. Moonshot reports orchestration of up to 300 sub-agents over 4,000 coordinated steps and a SWE-Bench Pro score of 58.6 under its published evaluation setup.
    How much does Kimi K2.6 cost in yno.ai?
    Kimi K2.6 is available on the Max tier of yno.ai.
    What can Kimi K2.6 do?
    Kimi K2.6 is best for Enterprise teams running large-scale multi-agent workflows that need to reason over hours. Its main capabilities include Agentic, Code, Vision, Video, Tool Use, Long Horizon.
    How does Kimi K2.6 compare to other models?
    Kimi K2.6 excels at Vendor-reported SWE-Bench Pro 58.6 and is recommended for Agent swarms, Long-running coding agents, Visual analysis, 4K-step coordinated workflows. See related models below.
    How do I use Kimi K2.6 in yno.ai?
    Sign up for yno.ai, select Kimi K2.6 from the model picker, and start chatting.