Skip to main content

Overview

Moonshot’s Kimi models are built for long context and code. The K2 line is tuned for software work; K3 extends the context window to a million tokens.

Available Models

Kimi K3

4 credits • Moonshot AI’s flagship multimodal reasoning model with a one-million-token context window.
  • 1M context window
  • Exceptional reasoning (reasoning model)
  • Speed: Medium • Cost: High
  • Vision: images supported
  • Model id: kimi-k3

Kimi K2.7 Code

3 credits • A reasoning-first Kimi model optimized for agentic software engineering and complex coding work.
  • 256K context window
  • Exceptional reasoning (reasoning model)
  • Speed: Medium • Cost: Medium
  • Model id: kimi-k2.7-code

Kimi K2.7 Code Highspeed

4 credits • The high-throughput Kimi K2.7 Code variant for latency-sensitive coding and agent workflows.
  • 256K context window
  • Exceptional reasoning (reasoning model)
  • Speed: Fast • Cost: High
  • Model id: kimi-k2.7-code-highspeed

Kimi K2.6

3 credits • A multimodal Kimi model for general reasoning, tool use, and long-context tasks.
  • 256K context window
  • Exceptional reasoning (reasoning model)
  • Speed: Medium • Cost: Medium
  • Vision: images supported
  • Model id: kimi-k2.6

Kimi K2.5

2 credits • A capable multimodal Kimi model for reasoning over text, images, and video inputs.
  • 256K context window
  • Excellent reasoning (reasoning model)
  • Speed: Medium • Cost: Medium
  • Vision: images supported
  • Model id: kimi-k2.5

Setup

Using BoostGPT-Hosted API Keys

1

Select a model

In your BoostGPT dashboard, choose any Moonshot AI model when creating or configuring an agent.
2

Start chatting

Credits are deducted per step at the rate shown on each model above. Nothing else to configure.

Using Your Own API Key

Bring your own key to bill Moonshot AI directly instead of spending BoostGPT credits. See Bring Your Own Keys.

Next Steps

Model Comparison

Compare every model across all providers

Provider Overview

See all supported providers