Skip to main content
AI Choice Engine

Moonshot AI

Kimi K2.7 Code

Kimi K2.7 Code is a Moonshot AI model with 262K context, $0.95 in / $4 out per million tokens, last verified October 1, 2026. Open weights: yes. Public-board scores are linked to the publisher; vendor-only figures stay in the watch-out, not on the board.

Kimi K2.7 Code is Moonshot's coding-specialised build of K2.6 — same 1T MoE and 256K context, tuned for agentic coding workflows.

Recorded profile verification October 1, 2026Individual provider fields may change

AI model specification details
SpecificationKimi K2.7 Code
ProviderMoonshot AI
TierBalanced
Context window262K
Max outputNot verifiedUnverified
Input / 1M tokens$0.95
Output / 1M tokens$4
WeightsOpen
Parameters1T total / 32B active (MoE)
Reasoning levelsNot verifiedUnverified
Modalitiestext, image, video
LicenseModified MIT
API model idkimi-k2.7-code
ReleasedJune 12, 2026

Pricing tiers: Standard kimi-k2.7-code is $0.95/$4.00 per MTok with cached input $0.19. The separate kimi-k2.7-code-highspeed endpoint is $1.90/$8.00 with cached input $0.38. Both list 262,144-token context. Prices exclude tax; weights are 1T total/32B active under Modified MIT.

Publisher evidence

Published benchmark results

Each result keeps its source date visible. Dates refer to source publication or capture unless the source explicitly states when it measured the result. A missing benchmark is not treated as a zero.

Published benchmark results for Kimi K2.7 Code
BenchmarkScoreSource dateSource
Artificial Analysis Intelligence IndexKimi K2.7 Code262026-10-01Artificial Analysis · View source

Best for

  • Agentic coding on open weights
  • Kimi ecosystem teams
  • Repo-scale refactors at K2.6 rates

Watch out

Thinking is always on; Kimi Code routes non-thinking requests to K2.6. Context is 262,144 and a hard output cap/complete effort menu remains unverified. Modified MIT requires prominent Kimi K2.7 Code UI attribution above 100M monthly active users or $20M monthly revenue. Named benchmark results are dated configurations, not permanent ranks.

History

Kimi K2.7 Code timeline

Release and status events for this model that passed two-source verification — dated, sourced, and linked.

Source receipts

Catalog figures for this model were checked against the following sources.

Common questions

Kimi K2.7 Code

Answered from the verified figures on this page rather than general guidance.

How much does Kimi K2.7 Code cost per million tokens?
Kimi K2.7 Code lists base rates of $0.95 per million input tokens and $4 per million output tokens. Estimate both input and output token volume and any additional charges for your workload. Standard kimi-k2.7-code is $0.95/$4.00 per MTok with cached input $0.19. The separate kimi-k2.7-code-highspeed endpoint is $1.90/$8.00 with cached input $0.38. Both list 262,144-token context. Prices exclude tax; weights are 1T total/32B active under Modified MIT.
What is Kimi K2.7 Code's context window?
Kimi K2.7 Code accepts about 262K tokens of context. That only matters if you routinely send very long documents, large codebases, or multi-turn histories that approach that limit.
What is Kimi K2.7 Code best for?
Kimi K2.7 Code is a balanced tier from Moonshot AI. It suits agentic coding on open weights, kimi ecosystem teams, repo-scale refactors at k2.6 rates. Thinking is always on; Kimi Code routes non-thinking requests to K2.6. Context is 262,144 and a hard output cap/complete effort menu remains unverified. Modified MIT requires prominent Kimi K2.7 Code UI attribution above 100M monthly active users or $20M monthly revenue. Named benchmark results are dated configurations, not permanent ranks.
Can I self-host Kimi K2.7 Code?
Kimi K2.7 Code publishes open weights, but self-hosting depends on the licence, hardware footprint, quantisation quality, and serving stack. A hosted API is often cheaper until you have measured throughput and concurrency on your own hardware.
Model comparison catalogBenchmark library