Skip to content
Model Season every model has a season

Kimi K3

moonshotai/kimi-k3-20260715
Moonshot AIChinaOpen weights

The 14th most-used model on the router over the last 7 days, with 1.4% of tokens. Weekly share peaked at 2.5% in the week of Jul 27, 2026, with 11T tokens processed since Jul 13, 2026.

Launch
Jul 16, 2026
Context
1M tokens
Modality
text, image and video → text
Reasoning
yes
License
Open weights
Input
$2.34 / 1M
Output
$11.70 / 1M
Share, last 7 days
1.4%
14th of 61 · Sep 4, 2026 to Sep 10, 2026
Peak weekly share
2.5%
week of Jul 27, 2026
Cumulative tokens
11T
since the week of Jul 13, 2026
Weeks in the top 10
2
of 8 weeks with volume

Weekly token share

Share of the router's weekly volume, since the first week with volume

0%1%2%3%Jul 13Jul 20Jul 27Aug 3Aug 10Aug 17Aug 24Aug 31peak 2.5% on Jul 27, 2026
See the numbers
WeekShare
Aug 31, 20261.715%
Aug 24, 20261.393%
Aug 17, 20261.416%
Aug 10, 20261.869%
Aug 3, 20261.955%
Jul 27, 20262.507%
Jul 20, 20262.121%
Jul 13, 20260.600%

Debuted in the week of Jul 13, 2026 and peaked at 2.5% 2 weeks later. The latest full week came in at 1.7%, 68% of peak.

What this model is used for new

Tasks where the model ranks among the leaders, and its share of each

Ranks among the leaders in 5 of the 29 classified tasks. Its largest share is in web search, 4.7% of the task's tokens; in the heaviest task where it appears, multi-step planning (6.6% of classified volume), it holds 3.0%.

Snapshot of the rolling 7-day window through Sep 10, 2026. Share: the model's tokens in the task over the task's total tokens. Weight: the task's share of classified volume.

Where to run it

Endpoints in the source's catalog, from cheapest to most expensive on input

ProviderInputOutputContextQuantizationZero retention
Sail Research$2.34$11.701Mfp4yes
Relace$2.40$12.001Mfp4yes
Morph$2.42$13.581Mfp8yes
Makora$2.55$12.751Mnot reportedyes
DigitalOcean$2.55$12.951Mnot reportedyes
DeepInfra$2.85$14.251Mbf16yes
Wafer$3.00$12.751Mnot reportedyes
Phala$3.00$15.001Mnot reportedyes
Chutes$3.00$15.001Mmxfp4no
Parasail$3.00$15.001Mfp4yes
Modal$3.00$15.001Mmxfp4yes
Together$3.00$15.001Mnot reportedyes
Fireworks$3.00$15.001Mnot reportedyes
BaseTen$3.00$15.001Mfp8yes
Moonshot AI$3.00$15.001Mmxfp4yes
Fireworks$3.30$16.501Mnot reportedyes
Alibaba$3.45$17.251Mnot reportedno
Fireworks$4.50$22.501Mnot reportedyes
Morph$6.00$22.501Mfp8yes

19 endpoints across 16 providers, with input from $2.34 to $6.00 per 1M tokens. 17 offer zero data retention.

Prices in US dollars per million tokens, from the latest archived endpoint catalog.

Benchmarks

Artificial Analysis indexes and benchmarks run by the source, with cost per task

Intelligence
43.8
8th of 82
Coding
76.2
9th of 111
Agents
50.6
8th of 86

GPQA Diamond 91.5%

$0.15 per task, 1182 tasks. 10th of 131 evaluated. Median of evaluated models: 80.2%, $0.024 per task.

τ-bench verified, airline 70.9%

$0.34 per task, 250 tasks. 58th of 122 evaluated. Median of evaluated models: 70.7%, $0.056 per task.

Artificial Analysis indexes, exposed by the catalog; benchmarks run by the source and archived on Sep 11, 2026. The gray mark is the median of evaluated models.

Against the week's largest models

The five largest proprietary and five largest open-weights models over the last 7 days

ModelLab7-day shareBlended priceContextIntelligenceWeeks in top 10
Proprietary
GPT-5.6 LunaOpenAIOpenAI11.5%$0.451M37.56
Gemini 3.8 FlashGoogleGoogle2.1%$1.501M41.20
Muse Spark 1.3 ContributorMetaMeta1.5%$0.1251M0
Claude Opus 5AnthropicAnthropic1.4%$10.001M50.71
GPT-5.6 SolOpenAIOpenAI1.4%$4.001M47.10
Open weights
Hy4 previewTencentTencent15.5%$1.251M1
DeepSeek V4 Flash 0731DeepSeekDeepSeek10.0%$0.0941.31M34.55
GLM 5.3 FlashZ.ai (GLM)Z.ai (GLM)10.0%$0.2371.31M41.92
MiMo-V2.5XiaomiXiaomi4.2%$0.1751M22.315
DeepSeek V4 Flash 0423DeepSeekDeepSeek3.9%$0.1111M24.819
Kimi K3this pageMoonshot AIMoonshot AI1.4%$4.681M43.82

Share over the last 7 days (Sep 4, 2026 to Sep 10, 2026). Blended price in US dollars per million tokens, weighted 75% input and 25% output. A dash means the number is not published, not zero.

What this page doesn't say. Share here is a slice of one router's traffic, where the deciding factor is usually price per token. It is not market, revenue or user share, and it does not tell you which model fits your workload.