Claude Fable 5$22.000/MClaude Opus 4.8$11.000/MClaude Opus 4.7$11.000/MClaude Opus 4.6$11.000/MClaude Opus 4.5$33.000/MClaude Sonnet 3.7$6.600/MClaude Opus 3$33.000/MClaude 2.1$12.800/MClaude 2$12.800/MGPT-5.5$12.500/MGPT-5.2$5.425/MGPT-5.2-Codex$5.425/MGPT-5$3.875/MGPT-4.5$97.500/MGPT-4 Turbo Preview$16.000/MGPT-4$39.000/MGPT-4-32k$78.000/Mo3$19.000/Mo3-mini$2.090/Mo4-mini$2.090/Mo1$28.500/Mo1-mini$5.700/Mo1-preview$28.500/MGemini 3.5 Pro$5.000/MGemini 3.1 Pro$5.000/MGemini 3 Pro$5.000/MGemini 2.5 Pro$3.875/MGemini 1.5 Pro$2.375/MGemini 1.0 Ultra$12.000/MGemini 1.0 Pro$0.800/MClaude Fable 5$22.000/MClaude Opus 4.8$11.000/MClaude Opus 4.7$11.000/MClaude Opus 4.6$11.000/MClaude Opus 4.5$33.000/MClaude Sonnet 3.7$6.600/MClaude Opus 3$33.000/MClaude 2.1$12.800/MClaude 2$12.800/MGPT-5.5$12.500/MGPT-5.2$5.425/MGPT-5.2-Codex$5.425/MGPT-5$3.875/MGPT-4.5$97.500/MGPT-4 Turbo Preview$16.000/MGPT-4$39.000/MGPT-4-32k$78.000/Mo3$19.000/Mo3-mini$2.090/Mo4-mini$2.090/Mo1$28.500/Mo1-mini$5.700/Mo1-preview$28.500/MGemini 3.5 Pro$5.000/MGemini 3.1 Pro$5.000/MGemini 3 Pro$5.000/MGemini 2.5 Pro$3.875/MGemini 1.5 Pro$2.375/MGemini 1.0 Ultra$12.000/MGemini 1.0 Pro$0.800/M
BETA
Subscribe
← Back to Index·All Moonshot AI models
Moonshot AI
Moonshot AIMultimodalAUTO PROFILELIVE INDEX

Kimi K2.7 Code

text+image->text

Kimi K2.7 Code is a code-specialist variant tuned for completion, refactoring, and test generation across major programming languages. Available via Moonshot AI. 262K-token context. Mid-tier pricing.

Kimi K2.7 Code is a multimodal AI model from Moonshot AI. It costs $0.740 per million input tokens and $3.500 per million output tokens (blended $1.568/M), with a 262K-token context window.

Modalities text, visionPricing source ↗Compare with another model →Estimate monthly cost →
INPUT
$0.740/M
per million input tokens
OUTPUT
$3.500/M
per million output tokens
BLENDED 70/30
$1.568/M
default reference rate · how it's calculated →
CONTEXT
262K
262,144 tokens
What it's good at
  • Code completion across languages
  • Multi-file refactoring
  • Test generation
  • Debugging from stack traces
  • Multimodal: handles images alongside text
Typical use cases
  • Pair-programming copilots
  • Codebase refactors
  • Code review automation
  • Repo-scale agents
Benchmarks
No published benchmark scores tracked for this model yet. Frontier and reasoning models from major providers have scores; smaller models and inference-host variants typically inherit the underlying open-weights score.
More from Moonshot AI
See all 4 →
Kimi k1.5
Reasoning · 128K ctx
in $2.500/Mout $10.000/M
Moonshot v1 128k
Long Context · 128K ctx
in $1.800/Mout $1.800/M
Moonshot v1 32k
Balanced · 32K ctx
in $0.400/Mout $0.400/M
Moonshot v1 8k
Compact · 8K ctx
in $0.120/Mout $0.120/M
Frequently asked questions

How much does Kimi K2.7 Code cost?

Kimi K2.7 Code costs $0.740 per million input tokens and $3.500 per million output tokens, for a blended reference rate of $1.568 per million tokens.

What is Kimi K2.7 Code's context window?

Kimi K2.7 Code supports up to 262K tokens of context (262,144 tokens).

What is Kimi K2.7 Code best for?

Kimi K2.7 Code is well suited to Code completion across languages, Multi-file refactoring and Test generation.

Who makes Kimi K2.7 Code?

Kimi K2.7 Code is developed and served by Moonshot AI.