Kimi K2.5
moonshotai/kimi-k2.5
multimodal frontend coding.
cmd --model moonshotai/kimi-k2.5
Intelligence index
35.4
Output speed
41.2 tok/s
Input
$0.60 /M
Output
$3 /M
Cache read
$0.10 /M
Agent-loop cost
$0.25 /M in
Context window
256K tokens
Released
January 27, 2026
Modalities
→
vs. the lineup
Kimi K2.5 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 K2.5 has been left empty.
Coding Index
46.8
#32 of 34 scored
Terminal-Bench
45.7
#32 of 34 scored
Intelligence Index
35.4
#35 of 40 scored
Long-context reasoning
65.3
reasoning across a long context
SciCode
49
scientific coding
GPQA Diamond
87.9
graduate-level QA
usage calculator
How far a month of credits goes on Kimi K2.5.
Input tokensfresh prompt
800Output tokensmodel reply
180Cache read tokensre-read context
50Kcost / request $0.0060 · in $0.60 · out $3 · cache $0.10 per M
fresh input 8%output 9%cache reads 83%
Requests / 30 days
1.7K
$10 credits ÷ $0.0060 per request
~332 quick fixes~66 bug fixes~11 feature PRs
what real work costs
Real coding tasks priced end to end on Kimi K2.5, from a quick lookup to a full-repo agent run.
One agent task
$0.08
180K in at 75% cache hit, 12K out
What you pay
$0.40 /M
all-in across every token that task touched
Sticker input
$0.60 /M
cache reads bill at $0.10 /M instead
| Task | Tokens in · out | Kimi K2.5 | MiniMax M3 | Claude Haiku 4.5 |
|---|---|---|---|---|
| Quick lookup / one-liner | 8K · 1K | $0.0042 | $0.0019 | $0.0065 |
| Review a 500-line PR | 60K · 4K | $0.03 | $0.01 | $0.04 |
| Fix a bug (agent loop) | 180K · 12K | $0.08 | $0.04 | $0.12 |
| Refactor a module | 320K · 20K | $0.14 | $0.06 | $0.21 |
| Full-repo agent run | 900K · 45K | $0.32 | $0.16 | $0.49 |
frequently asked
What is Kimi K2.5 best for?+
Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed visual and text tokens, it delivers strong performance in general reasoning, visual coding, and agentic tool-calling.
How much does Kimi K2.5 cost?+
$0.60/M input and $3/M output, cache reads $0.10/M. In an agent loop most input is cache-read, so the effective input rate is about $0.25/M.Which plan do I need?+
Available on Go and above.
How do I switch to it?+
Run
cmd --model moonshotai/kimi-k2.5, 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-k2-5