modelbenchmark.io

Kimi K2.7 Code

Kimi · kimi-k2-7-code

Compare

Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking

Specification

moonshotai listing

Context
262K
Max output
262K
Released
2026-06-12
Knowledge cutoff
2025-01
Retires
2026-08-27
Open weights
yes
Input
text, image, video
Output
text

Price

US dollars per million tokens · moonshotai list price

Input
$0.95
Output
$4.00
Cache read
$0.19
Cache write
free

Batch and priority prices

US dollars per million tokens · per listing

PriceListing$/M
Priority inputfireworks_ai$1.425
Priority outputfireworks_ai$6.00

Rate limits

as listed

Requests per minute
20

Quality

7 benchmarks · 2 sources

Composite
63rd
percentile of 334 scored models
Rank
123 / 334
±0.08 sd
Evidence
7 × 2
3 or more benchmarks, from 2 or more sources
Effort range
one configuration only
reasoning86th2/4 bench
math70th3/7 bench
knowledge44th1/1 bench
general14th1/1 bench

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
OTIS Mock AIME 2024-202595.6 ±3.1defaultEpoch AI2026-08-07
GPQA diamond87.9 ±2.3defaultEpoch AI2026-08-07
FrontierMath-Tiers-1-3-v254.0 ±3.0defaultEpoch AI2026-06-13
Chess Puzzles21.0 ±4.1defaultEpoch AI2026-08-07
SimpleQA Verified36.5 ±1.5defaultEpoch AI2026-08-27
FrontierMath-Tier-4-v212.2 ±5.2defaultEpoch AI2026-06-13
LiveBench68.8default · 23 runsLiveBench2026-06-25

The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.

Available from 75 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
moonshotaivendor$0.95$4.00$0.19262K262K
alibaba-token-planfreefreefreefree262K262K
alibaba-token-plan-cnfreefreefreefree262K262K
kenarifreefree262K262K
kenari · freefreefree262K262K
scnet-token-planfreefreefree262K262K
volcengine-coding-planfreefreefree262K262K
routing-run$0.275$1.10200K32K
crof$0.55$2.25$0.05262K262K
inceptron · moonshotai$0.66$3.40$0.18free262K262K
deepinfra$0.68$3.40$0.136262K
deepinfra · moonshotai$0.68$3.40$0.136262K262K
ambient · moonshotai$0.69$3.49$0.14free262K262K
openrouter$0.71$3.50$0.15262K236K
openrouter · moonshotai$0.71$3.50$0.15262K236K
wandb · moonshotai$0.71$3.50$0.15262K262K
wandb · wandb$0.71$3.50$0.15262K
aiand · moonshotai$0.75$3.50$0.20262K262K
cortecs$0.75$3.50$0.201262K262K
venice$0.75$3.50$0.16256K66K
melious$0.8114$3.4776$0.2202262K262K
greenpt$0.9006$4.389$0.1881262K262K
302ai$0.95$4.00262K262K
abacus · moonshotai$0.95$4.00$0.19262K262K
aihubmix$0.95$3.9995$0.1608262K33K
azure$0.95$4.00$0.19262K262K
azure_ai$0.95$4.00$0.19262K262K2026-10-03
baseten · moonshotai$0.95$4.00$0.16262K262K
cline-pass · cline-pass$0.95$4.00$0.19262K262K
cloudflare$0.95$4.00$0.19262K262K
cloudflare-workers-ai · cf$0.95$4.00$0.19262K262K
dashscope · dashscope$0.95$4.00$0.19229K16K
databricks$0.95$4.00$0.19262K262K
edenai$0.95$4.00$0.19262K262K
empiriolabs$0.95$4.00$0.95256K131K
fireworks_ai$0.95$4.00$0.19262K33K
fireworks-ai · accounts$0.95$4.00$0.19262K262K
github-copilot$0.95$4.00$0.19256K32K
hpc-ai · moonshotai$0.95$4.00$0.19256K256K
huggingface · moonshotai$0.95$4.00262K262K
jalapeno$0.95$4.00271K262K
kilo · moonshotai$0.95$4.00$0.19262K236K
llmgateway$0.95$4.00$0.19262K262K
llmgateway-providers$0.95$4.00$0.19262K262K
llmgateway-providers · scx-ai-gp$0.95$4.00$0.19262K262K
llmgateway-providers · tencent$0.95$4.00$0.19262K262K
merge-gateway$0.95$4.00$0.19262K33K
moonshot$0.95$4.00$0.19262K262K
moonshotai-cn$0.95$4.00$0.19262K262K
nano-gpt · moonshotai$0.95$4.00$0.19262K66K
nano-gpt · tee$0.95$4.00$0.19262K66K
nebius$0.95$4.00262K262K
nebius · moonshotai$0.95$4.00262K8K
neuralwatt$0.95$4.00$0.095262K262K
novita$0.95$4.00$0.19262K262K
novita-ai · moonshotai$0.95$4.00$0.19262K262K
ofox · moonshotai$0.95$4.00$0.19262K262K
ollama-cloud$0.95$4.00$0.19262K262K
opencode$0.95$4.00$0.19262K262K
opencode-go$0.95$4.00$0.19262K262K
orcarouter · kimi$0.95$4.00$0.19262K262K
perplexity$0.95$4.00$0.19
perplexity-agent · moonshot-ai$0.95$4.00$0.19262K262K
pioneer · moonshotai$0.95$4.00$0.19$0.95256K33K
qwen_ai_platform · qwen-ai-platform$0.95$4.00$0.19229K16K
qwencloud · qwencloud$0.95$4.00$0.19229K16K
requesty$0.95$4.00$0.19262K262K
together_ai$0.95$4.00$0.19262K2026-08-27
togetherai · moonshotai$0.95$4.00$0.19262K131K
vercel · moonshotai$0.95$4.00$0.16256K33K
zenmux · moonshotai$0.95$4.00$0.16262K262K
crossmodel$1.00$4.16$0.18$1.00262K262K
openreason · moonshotai$1.0022$4.22262K262K
hyper$1.0344$4.3552$0.2069256K16K
tensorx · moonshotai$1.25$4.50$0.3125262K262K

Price history

append-only observations · a listing writes a row only when its price moves

DateHostField$/M
2026-09-02llmgatewayCache read$0.18
2026-09-10llmgatewayCache read$0.19
2026-09-02llmgateway-providers · scx-ai-gpCache read$0.18
2026-09-10llmgateway-providers · scx-ai-gpCache read$0.19
2026-09-02openrouter · moonshotaiCache read$0.18
2026-09-08openrouter · moonshotaiCache read$0.15
2026-09-02llmgatewayInput$0.89
2026-09-10llmgatewayInput$0.95
2026-09-02llmgateway-providers · scx-ai-gpInput$0.89
2026-09-10llmgateway-providers · scx-ai-gpInput$0.95
2026-09-02openrouter · moonshotaiInput$0.66
2026-09-08openrouter · moonshotaiInput$0.71
2026-09-02llmgatewayOutput$3.71
2026-09-10llmgatewayOutput$4.00
2026-09-02llmgateway-providers · scx-ai-gpOutput$3.71
2026-09-10llmgateway-providers · scx-ai-gpOutput$4.00
2026-09-02openrouter · moonshotaiOutput$3.40
2026-09-08openrouter · moonshotaiOutput$3.50
2026-09-06openrouterCache read$0.18
2026-09-13openrouterCache read$0.15
2026-09-06openrouterInput$0.66
2026-09-13openrouterInput$0.71
2026-09-06openrouterOutput$3.40
2026-09-13openrouterOutput$3.50

Other listings of this model

same model, different key

More from Kimi

most-hosted first