Kimi K2.7 Code
moonshotai/kimi-k2.7-code
improved long-horizon coding with vision.
cmd --model moonshotai/kimi-k2.7-code
Intelligence index
43
Output speed
40.5 tok/s
Input
$0.95 /M
Output
$4 /M
Cache read
$0.19 /M
Agent-loop cost
$0.42 /M in
Context window
256K tokens
Released
June 12, 2026
Modalities
→
vs. the lineup
Kimi K2.7 Code beside its stablemates and nearest rivals. The ◆ marks the best value in each column across every row shown.
pin a rival:
| Model | Intelligence | Coding | Speed | Input $/M | Output $/M | Blended $/M | Context |
|---|---|---|---|---|---|---|---|
| Kimi K3 | 59.7◆ | 76.2◆ | 39.4◆ | $3◆ | $15◆ | $6◆ | 1M◆ |
| Muse Spark 1.2 Contributor | 56.8◆ | 72.2◆ | —◆ | $0.10◆ | $0.20◆ | $0.13◆ | 1.05M◆ |
| Kimi K2.6 | 45.1◆ | 61.8◆ | —◆ | $0.95◆ | $4◆ | $1.71◆ | 256K◆ |
| Kimi K2.7 Code ◆ | 43◆ | 60.8◆ | 40.5◆ | $0.95◆ | $4◆ | $1.71◆ | 256K◆ |
| Kimi K2.5 | 36◆ | 46.8◆ | —◆ | $0.60◆ | $3◆ | $1.20◆ | 256K◆ |
| Kimi K2.7 Code HighSpeed | —◆ | —◆ | —◆ | $1.90◆ | $8◆ | $3.42◆ | 262K◆ |
| DeepSeek V4 Pro (latest)pinned | 45.3◆ | 59.4◆ | 63.3◆ | $0.66◆ | $1.98◆ | $0.99◆ | 1M◆ |
| DeepSeek V4 Flash (latest)pinned | 52◆ | 69.1◆ | 115.9◆ | $0.22◆ | $0.66◆ | $0.33◆ | 1M◆ |
coding performance
The Intelligence Index and its sub-scores, ranked against every scored model in the catalog. A metric that has not been measured for Kimi K2.7 Code has been left empty.
Coding Index
60.8
#23 of 40 scored
Terminal-Bench
67.4
#22 of 40 scored
Intelligence Index
43
#26 of 46 scored
Long-context reasoning
75
reasoning across a long context
SciCode
47.5
scientific coding
GPQA Diamond
89.6
graduate-level QA
usage calculator
How far a month of credits goes on Kimi K2.7 Code.
Input tokensfresh prompt
800Output tokensmodel reply
180Cache read tokensre-read context
50Kcost / request $0.011 · in $0.95 · out $4 · cache $0.19 per M
fresh input 7%output 7%cache reads 87%
Requests / 30 days
911
$10 credits ÷ $0.011 per request
~182 quick fixes~36 bug fixes~6 feature PRs
what real work costs
Real coding tasks priced end to end on Kimi K2.7 Code, from a quick lookup to a full-repo agent run.
One agent task
$0.12
180K in at 75% cache hit, 12K out
What you pay
$0.61 /M
all-in across every token that task touched
Sticker input
$0.95 /M
cache reads bill at $0.19 /M instead
| Task | Tokens in · out | Kimi K2.7 Code | Muse Spark 1.2 Contributor | Claude Haiku 4.5 |
|---|---|---|---|---|
| Quick lookup / one-liner | 8K · 1K | $0.0061 | $0.0003 | $0.0065 |
| Review a 500-line PR | 60K · 4K | $0.04 | $0.0027 | $0.04 |
| Fix a bug (agent loop) | 180K · 12K | $0.12 | $0.0072 | $0.12 |
| Refactor a module | 320K · 20K | $0.21 | $0.01 | $0.21 |
| Full-repo agent run | 900K · 45K | $0.50 | $0.03 | $0.49 |
frequently asked
What is Kimi K2.7 Code best for?
Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts architecture that accepts text and image input, and it always operates in a thinking mode, preserving full reasoning content across multi-turn conversations. With a 256K-token context window, it targets long-horizon coding, agentic task decomposition, and multi-turn dialogue. The model activates 32B parameters out of roughly 1T total.
How much does Kimi K2.7 Code cost?
$0.95/M input and $4/M output, cache reads $0.19/M. In an agent loop most input is cache-read, so the effective input rate is about $0.42/M.Which plan do I need?
Available on Go and above.
How do I switch to it?
Run
cmd --model moonshotai/kimi-k2.7-code, or type /model in a session and pick it. You can switch mid-session without losing context.Ship code that matches your taste
Command Code is the AI coding agent that continuously learns your taste. Start for $1.
Benchmarks from Artificial Analysis (v4.1)commandcode.ai/models/kimi-k2-7-code