Living reference

The Kimi model map

Model IDs, context windows, input modes, reasoning controls, and a practical guide to choosing the right lane.

Current referenceLast source check: July 20, 2026Primary sources: Kimi API and Kimi Code documentation
ModelModel IDContextInputReasoningStatus
Kimi K3
Flagship
kimi-k31,048,576Text + visionLow / High / MaxCurrent
Kimi K2.7 Code
Focused coding
kimi-k2.7-code262,144TextThinkingCurrent
K2.7 Code HighSpeed
Fast coding
kimi-k2.7-code-highspeed262,144TextThinkingCurrent
Kimi K2.6
General multimodal
kimi-k2.6262,144Text + visionThinking / InstantSupported

Choose by workload

The largest model is not automatically the most efficient model for every coding session.

Choose K3

Deep, long, or visual work

Use K3 when the task spans a large codebase, combines images with engineering, needs extended reasoning, or must run for a long time with little supervision.

Choose K2.7 Code

Steady repository work

Use the focused coding model for daily implementation, debugging, and contained agent loops where predictable instruction following matters.

Choose HighSpeed

Latency is the bottleneck

Use the high-speed coding model for rapid iteration. Kimi documents it as roughly five to six times faster with three times the quota usage.

Migration watch

The original K2 API model IDs are retired. The current API documentation also gives K2.5 and Moonshot V1 a platform-wide August 31 retirement date following the K3 launch.

What the context number does not tell you

A larger context window changes what can fit in one request, but it does not eliminate the need for retrieval design, acceptance tests, or cost controls. Long-context applications should track cache-hit behavior and task completion together.

Official references

Kimi API model list ↗

Kimi Code model configuration ↗

Kimi K3 launch report ↗