modelgrep

Longest-Context MoonshotAI Models

Match · Updated July 2026

Kimi K3 has the largest context window of any MoonshotAI model, at 1.0M tokens. Kimi K2.7 Code (262K) and Kimi K2.6 (262K) round out the top three.

1.0MContext
57.1Intelligence
$3.00Input /M

AI models with the largest context windows, ranked by token capacity. The best large language models for long documents, codebases and extended conversations.

  1. 1moonshotai logo
    kimi-k3
    ReasoningToolsJSON+157.1 intel · $3.00/M
    1.0M
    Context
  2. 2moonshotai logo
    kimi-k2.7-code
    ReasoningToolsJSON+141.9 intel · $0.730/M
    262K
    Context
  3. 3moonshotai logo
    kimi-k2.6
    ReasoningToolsJSON+144.2 intel · $0.950/M
    262K
    Context
  4. 4moonshotai logo
    kimi-k2.5
    ReasoningToolsJSON+135.4 intel · $0.570/M
    262K
    Context
  5. 5moonshotai logo
    kimi-k2-thinking
    ReasoningToolsJSON32.7 intel · $0.600/M
    262K
    Context
  6. 6moonshotai logo
    kimi-k2-0905
    ToolsJSON23.5 intel · $0.600/M
    262K
    Context

Frequently asked

Which MoonshotAI model has the largest context window?

Kimi K3 has the largest context window of any MoonshotAI model, at 1.0M tokens. Kimi K2.7 Code (262K) and Kimi K2.6 (262K) round out the top three.

What's a good alternative to Kimi K3?

Kimi K2.7 Code (262K) is the closest alternative on this metric, followed by Kimi K2.6 (262K). See the full ranking above for the tradeoffs.

How many MoonshotAI models are there?

modelgrep tracks 7 MoonshotAI models with live benchmarks, speed, latency and per-provider pricing, led on intelligence by Kimi K3. 6 of them qualify for this ranking.

More MoonshotAI rankings

All rankings