Skip to main content

    Moonshot AI

    Kimi K2.7 Code

    Moonshot's Kimi K2.7 Code is a native multimodal coding model with 1T total and 32B active parameters and a 256K-token context. It accepts text, images and video; thinking is mandatory. Moonshot reports about 30% fewer thinking tokens than K2.6 on coding and agentic evaluations. Published weights use a modified MIT license, and the first-party API is OpenAI-compatible.

    256K tokens
    Multimodal
    Max
    Provider
    Moonshot AI
    Context
    256K
    Catalog · As of Aug 11, 2026Stale · 31d old
    yno subscription tier
    Max
    Released
    Jun 12, 2026
    Speed
    Medium
    Reasoning
    Expert
    Modality
    Multimodal

    Benchmarks

    Quality

    AA Intelligence Index
    26.3points
    Artificial Analysis · Date unknownAge unknown
    AA Coding Index
    60.8points
    Artificial Analysis · Date unknownAge unknown
    GPQA Diamond
    89.6%
    Artificial Analysis · Date unknownAge unknown

    Speed and latency

    Output speed
    46.94tokens/s
    Configuration: Prompt length: 1,000 · Parallel queries: 1
    Artificial Analysis · Date unknownAge unknown
    Time to first token
    1.28s
    Configuration: Prompt length: 1,000 · Parallel queries: 1
    Artificial Analysis · Date unknownAge unknown
    Time to first answer token
    48.77s
    Configuration: Prompt length: 1,000 · Parallel queries: 1
    Artificial Analysis · Date unknownAge unknown

    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 K2.7 Code

    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

    • Code
    • Agentic Coding
    • Vision
    • Video
    • Open Weights
    • Debugging

    Use cases

    • Autonomous coding agents
    • Long-horizon software engineering
    • Self-hosted coding AI
    • CI/CD automation

    Strengths

    • Published weights under modified MIT
    • Native image and video input
    • Mandatory thinking
    • OpenAI-compatible API

    Best for

    Teams building coding agents that also inspect images and video

    Use Kimi K2.7 Code in yno.ai

    No credit card required

    Related models

    Kimi K3

    Moonshot AI

    Kimi K2.6

    Moonshot AI

    Kimi K2.5

    Moonshot AI

    Frequently asked

    What is Kimi K2.7 Code?
    Moonshot's Kimi K2.7 Code is a native multimodal coding model with 1T total and 32B active parameters and a 256K-token context. It accepts text, images and video; thinking is mandatory. Moonshot reports about 30% fewer thinking tokens than K2.6 on coding and agentic evaluations. Published weights use a modified MIT license, and the first-party API is OpenAI-compatible.
    How much does Kimi K2.7 Code cost in yno.ai?
    Kimi K2.7 Code is available on the Max tier of yno.ai.
    What can Kimi K2.7 Code do?
    Kimi K2.7 Code is best for Teams building coding agents that also inspect images and video. Its main capabilities include Code, Agentic Coding, Vision, Video, Open Weights, Debugging.
    How does Kimi K2.7 Code compare to other models?
    Kimi K2.7 Code excels at Published weights under modified MIT and is recommended for Autonomous coding agents, Long-horizon software engineering, Self-hosted coding AI, CI/CD automation. See related models below.
    How do I use Kimi K2.7 Code in yno.ai?
    Sign up for yno.ai, select Kimi K2.7 Code from the model picker, and start chatting.