Kimi K2.7 Code
View website
Released June 2026, Moonshot AI's strongest coding and agentic model, a 1T-parameter MoE (32B active) under a modified MIT license with always-on interleaved thinking carried across turns. Uses roughly 30% fewer thinking tokens than K2.6 and scores 81.1 on MCP Mark Verified.
At a glance
- Context window
- 262K tokens
- Modalities
- Text Text Image Image Video Video → Text Text
Capabilities
Function calling
Connect to external tools, APIs, and systems.
Structured output
Return responses in structured formats like JSON.
Web search
Search the web for up-to-date information.
Pricing by provider
| Provider | Input / 1M tokens | Output / 1M tokens | |
|---|---|---|---|
GPUhub
|
$0.90 | $3.75 | View |
|
Moonshot AI
|
$0.95 | $4.00 | View |
Novita
|
$0.95 | $4.00 | View |
Heads up: We do our best to keep these specs & prices accurate. However, cloud costs may fluctuate based on region, usage, and other factors not listed here. These are estimates based on common setups and are for informational purposes only. Always verify current rates & exact specs with the provider before provisioning.
Compare with other models
Estimated prices shown. Actual costs may vary based on context length, batch size, caching, and provider-specific pricing tiers.