Back to Explore
MoonshotAI: Kimi K2.7 Code
Kimi·Released 2026-06-12
Open Source262K ctxotherMultimodal
Comparison data ready93% coverage16/18 fields directly observedUpdated Jul 25, 2026, 8:31 AM
About
MoonshotAI: 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...
Related Models
Pricing
Input
$0.78
per 1M tokens
Output
$3.50
per 1M tokens
Blended
$1.46
per 1M tokens
Cheaper than 35% of models. Median price is $0.69/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$1.46
Monthly
$43.80
vs. Similar Models
Claude Sonnet 5 (Non-reasoning, High Effort)Q:-0.2
$4.00+174%
OpenAI: GPT-5.2Q:+0.3
$4.81+230%
Xiaomi: MiMo-V2.5-ProQ:+0.3
$0.54-63%
GPT-5.6 Sol (Non-reasoning)Q:-0.7
$11.25+671%
Performance
45
tokens/sec
Faster than 11% of models
1.28
seconds
Faster than 46% of models
51.30
seconds
Faster than 8% of models
Market Median
95 tok/s
53% slower
Median TTFT
1.19s
8% slower
Throughput/Dollar
31
tok/s per $/1M
Speed Comparison
Llama 3 Instruct 70B
45 tok/s+1%
Qwen: Qwen3 Max Thinking
44 tok/s-1%
Claude Opus 5
44 tok/s-1%
Context Window
262K
tokens
Larger than 56% of models
Max Output
262K
tokens
100% of context
Benchmarks
MMLU-ProNot evaluated
GPQA Diamond
89.6%
HLE
32.8%
LiveCodeBenchNot evaluated
SciCode
47.5%
TerminalBench Hard
44.7%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025Not evaluated
IFBench
63.1%
Long Context Recall
66.3%
Tau2
90.1%
Market AverageTop Score