Pass IndexThe State of AISign in

Kimi K2 0711

Kimi K2 is a state-of-the-art mixture-of-experts (MoE) language model with 32 billion activated parameters and 1 trillion total parameters.

text → text · made by Moonshot AI

$0.57$2.3per Mtok in / out
Nous Research · 4 sellers

Sold by 11 ways

SellerLaneRate
AWS Bedrock 0 ways$0.6per Mtok in$2.5per Mtok out
AWS Bedrock cloudnot on the seller's list todaystandard$0.6per Mtok in$2.5per Mtok outraw.githubusercontent.com · read 2026-08-30
Crusoe 0 ways$2.5per Mtok in$2.5per Mtok out
Crusoe cloudnot on the seller's list todaystandard$2.5per Mtok in$2.5per Mtok outraw.githubusercontent.com · read 2026-08-30
Nous Research aggregatorstandard$0.57per Mtok in$2.3per Mtok outinference-api.nousresearch.com · read 2026-09-12
OpenRouter aggregatorstandard$0.57per Mtok in$2.3per Mtok outopenrouter.ai · read 2026-08-24
Vercel AI Gateway aggregatorstandard$0.57per Mtok in$2.3per Mtok outai-gateway.vercel.sh · read 2026-08-25
Baseten 0 ways$0.6per Mtok in$2.5per Mtok out
Baseten aggregatornot on the seller's list todaystandard$0.6per Mtok in$2.5per Mtok outraw.githubusercontent.com · read 2026-08-30
ElectronHub 0 ways$0.6per Mtok in$2.5per Mtok out
ElectronHub aggregatornot on the seller's list todaystandard$0.6per Mtok in$2.5per Mtok outapi.electronhub.ai · read 2026-08-30
Fireworks AI 0 ways$0.6per Mtok in$2.5per Mtok out
Fireworks AI aggregatornot on the seller's list todaystandard$0.6per Mtok in$2.5per Mtok outraw.githubusercontent.com · read 2026-08-30
Hugging Face Inference Providers 0 ways$0.6per Mtok in$2.5per Mtok out$0.15per Mtok cached
Hugging Face Inference Providers aggregatornot on the seller's list todaystandard$0.6per Mtok in$2.5per Mtok out$0.15per Mtok cachedmodels.dev · read 2026-08-30
Requesty aggregatorvertex$0.6per Mtok in$2.5per Mtok out$0.06per Mtok cachedrouter.requesty.ai · read 2026-08-28
PPIO 0 ways$4per Mtok in$16per Mtok out
PPIO aggregatornot on the seller's list todaystandard$4per Mtok in$16per Mtok outapi.ppinfra.com · read 2026-08-30

Measured 10 standings

PlaceBoardMetricScore
11thof 109Berkeley Function-Calling Leaderboard (BFCL) V4Overall Acc59.06
16thof 25SWE-Bench Pro (Public Dataset)Resolve Rate27.67
26thof 69Aider polyglot coding leaderboardPercent correct59.1
116thof 170Weirdml — Epoch AIAccuracy39.36
125thof 150Design Arena · uicomponent (models)Elo1045
132ndof 156Design Arena · codecategories (models)Elo1049
135thof 152Design Arena · dataviz (models)Elo1032
135thof 162Design Arena · website (models)Elo1063
141stof 155Design Arena · gamedev (models)Elo997
444thof 656Epoch capabilities index — Epoch AIECI Score140.13

About

Kimi K2 0711 — a text model from Moonshot AI, sold by 4 companies from $0.57 in and $2.3 out per million tokens, placed 11th of 109 on Berkeley Function-Calling Leaderboard (BFCL) V4.

It takes text and returns text, with a context window of 131,072 tokens. It was published in December 2024, trained on material up to October 2024. Its sellers say it can call a tool. The catalogue files it under code and agents. Four companies sell it. The cheapest is $0.57 in and $2.3 out per million tokens at Nous Research. Beside the standard rate there is a separately routed lane. It has been measured on 10 boards, and stands best at 11th of 109 on Berkeley Function-Calling Leaderboard (BFCL) V4.

Every current figure

Maker
Moonshot AI
Register
model
Takes
text
Returns
text
Context
131,072 tokens
Published
December 2024
Knowledge to
October 2024
Sellers
4
Maker's own price
not read
Price
$0.57 in and $2.3 out per million tokens — Nous Research
Boards
10
Best place
11th of 109 — Berkeley Function-Calling Leaderboard (BFCL) V4

Known as 3 names

Moonshotai-Kimi-K2-Instruct (FC)moonshotai/kimi-k2vertex/kimi-k2