Kimi K2.6
moonshotai/kimi-k2.6
long-horizon coding with vision.
cmd --model moonshotai/kimi-k2.6
Intelligence index
44.2
Output speed
56.7 tok/s
Input
$0.95 /M
Output
$4 /M
Cache read
$0.16 /M
Agent-loop cost
$0.40 /M in
Context window
256K tokens
Released
April 20, 2026
Modalities
→
vs. the lineup
Kimi K2.6 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 | 57.1◆ | 76.2◆ | 34.5◆ | $3◆ | $15◆ | $6◆ | 1M◆ |
| MiniMax M3 | 44.4◆ | 58.6◆ | 90.3◆ | $0.30◆ | $1.20◆ | $0.52◆ | 1M◆ |
| Kimi K2.6 ◆ | 44.2◆ | 61.8◆ | 56.7◆ | $0.95◆ | $4◆ | $1.71◆ | 256K◆ |
| Kimi K2.7 Code | 41.9◆ | 60.8◆ | 44.4◆ | $0.95◆ | $4◆ | $1.71◆ | 256K◆ |
| Kimi K2.5 | 35.4◆ | 46.8◆ | 41.2◆ | $0.60◆ | $3◆ | $1.20◆ | 256K◆ |
| Kimi K2.7 Code HighSpeed | —◆ | —◆ | —◆ | $1.90◆ | $8◆ | $3.42◆ | 262K◆ |
| DeepSeek V4 Propinned | 44.3◆ | 59.4◆ | 70.9◆ | $0.43◆ | $0.87◆ | $0.54◆ | 1M◆ |
| DeepSeek V4 Flashpinned | 40.3◆ | 56.2◆ | 122◆ | $0.14◆ | $0.28◆ | $0.18◆ | 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 K2.6 has been left empty.
Coding Index
61.8
#17 of 34 scored
Terminal-Bench
65.9
#18 of 34 scored
Intelligence Index
44.2
#20 of 40 scored
Long-context reasoning
69.7
reasoning across a long context
SciCode
53.5
scientific coding
GPQA Diamond
91.1
graduate-level QA
usage calculator
How far a month of credits goes on Kimi K2.6.
Input tokensfresh prompt
800Output tokensmodel reply
180Cache read tokensre-read context
50Kcost / request $0.0095 · in $0.95 · out $4 · cache $0.16 per M
fresh input 8%output 8%cache reads 84%
Requests / 30 days
1.1K
$10 credits ÷ $0.0095 per request
~211 quick fixes~42 bug fixes~7 feature PRs
what real work costs
Real coding tasks priced end to end on Kimi K2.6, from a quick lookup to a full-repo agent run.
One agent task
$0.11
180K in at 75% cache hit, 12K out
What you pay
$0.59 /M
all-in across every token that task touched
Sticker input
$0.95 /M
cache reads bill at $0.16 /M instead
| Task | Tokens in · out | Kimi K2.6 | MiniMax M3 | Claude Haiku 4.5 |
|---|---|---|---|---|
| Quick lookup / one-liner | 8K · 1K | $0.0059 | $0.0019 | $0.0065 |
| Review a 500-line PR | 60K · 4K | $0.04 | $0.01 | $0.04 |
| Fix a bug (agent loop) | 180K · 12K | $0.11 | $0.04 | $0.12 |
| Refactor a module | 320K · 20K | $0.20 | $0.06 | $0.21 |
| Full-repo agent run | 900K · 45K | $0.48 | $0.16 | $0.49 |
frequently asked
What is Kimi K2.6 best for?+
Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and can convert prompts and visual inputs into production-ready interfaces. Its agent swarm architecture scales to hundreds of parallel sub-agents for autonomous task decomposition - delivering documents, websites, and spreadsheets in a single run without human oversight.
How much does Kimi K2.6 cost?+
$0.95/M input and $4/M output, cache reads $0.16/M. In an agent loop most input is cache-read, so the effective input rate is about $0.40/M.Which plan do I need?+
Available on Go and above.
How do I switch to it?+
Run
cmd --model moonshotai/kimi-k2.6, 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.
commandcode.ai/models/kimi-k2-6