KuraberuAIupdated 16 Sept 2026

Kimi K2 0905 pricing.

prices as of · 27 providers · 31 prices

Moonshot AI's Kimi K2 0905 holds 262k tokens of context. Open weights, so anyone may host it, which is why the prices below differ so much.

Kimi K2 0905 costs $0.60 in and $2.50 out per million tokens from Moonshot AI; the cheapest price we can explain is $3 at NanoGPT, checked 16 Sept 2026.

tool callingstructured outputopen weights262k contextreleased 4 Sept 2025
Compare withvs Kimi K2 Thinkingvs Qwen3.5 122B-A10Bor any model →

Moonshot AI list price

$4.30/M tokens

$0.60 in · $2.50 out

read · 21% above the market median

Cheapest price we can explain

$3/M tokens

$0.40 in · $1.80 out · 30% under list

NanoGPT
View at NanoGPT ↗

read

What it costs for your work

pages a month

Moonshot AI list price

$0.51a month

cheapest we can explain · NanoGPT

$0.348a month

difference

$0.162saved

A page is about 600 tokens in and 60 out, a support reply 200 in and 300 out, an email 150 in and 250 out. Nothing else is counted: no cache discount, no batch rate, no free tier.

Every provider selling Kimi K2 0905

Four groups, decided by the price and by what the provider publishes about it. Prices are per million tokens, and the share is that row against Moonshot AI's price.

The maker's list price

1 price

What the lab that trained the model charges on its own API.

  • Moonshot AI

    The price Moonshot AI charges for the model it trained. Every row below is measured against it.

    131k context hereMoonshot AI ↗

    $0.60 / $2.50in / out per M

    1.00×of list price

Cheaper, and we know why

12 prices

Below list, with a published reason: hosting the open weights, a regional price list, credits, a stated discount.

  • NanoGPT

    Routes to a host serving the open weights; precision not disclosed.

    NanoGPT ↗

    $0.40 / $1.80in / out per M

    0.70×of list price

  • Helicone

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    $0.50 / $2in / out per M

    0.81×of list price

  • DeepInfra

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    131k context hereDeepInfra ↗

    $0.50 / $2in / out per M

    0.81×of list price

  • Eden AI

    Routes to a host serving the open weights; precision not disclosed.

    131k context hereEden AI ↗

    $0.50 / $2in / out per M

    0.81×of list price

  • OpenCode Zen

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    $0.40 / $2.50in / out per M

    0.86×of list price

  • FastRouter

    8% under the list price, an ordinary reseller margin.

    131k context hereFastRouter ↗

    $0.55 / $2.20in / out per M

    0.90×of list price

  • LLM Gateway

    5% under the list price, an ordinary reseller margin.

    131k context hereLLM Gateway ↗

    $0.57 / $2.30in / out per M

    0.93×of list price

  • Jiekou

    5% under the list price, an ordinary reseller margin.

    Jiekou ↗

    $0.57 / $2.30in / out per M

    0.93×of list price

  • Vercel AI Gateway

    5% under the list price, an ordinary reseller margin.

    131k context hereVercel AI Gateway ↗

    $0.57 / $2.30in / out per M

    0.93×of list price

  • io.net Intelligence

    5% under the list price, an ordinary reseller margin.

    33k context hereio.net Intelligence ↗

    $0.57 / $2.30in / out per M

    0.93×of list price

  • Requesty

    5% under the list price, an ordinary reseller margin.

    131k context hereRequesty ↗

    $0.57 / $2.30in / out per M

    0.93×of list price

  • Abacus

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision turbo.

    256k context here

    $0.15 / $8in / out per M

    1.97×of list price

Same price as the maker

15 prices

The same price the maker charges, sold by someone else.

Cheaper, and nobody says why

1 price · never ranked

Below list on a closed model with nothing to account for it. Shown, never ranked, never a pick.

  • Featherless

    We could not read this provider's prices reliably, so the row is listed but never ranked.

    33k context hereFeatherless ↗

    $0.60 / $2.50in / out per M

    1.00×of list price

Given away with limits

2 free tiers · never ranked

These providers give Kimi K2 0905 away inside a quota of their own. A limit is not a price, so none of them counts as cheapest here or anywhere else on the site.

  • iFlow
  • NVIDIA build

Frequently asked

Who sells Kimi K2 0905 cheapest?
NanoGPT, at $0.40 in and $1.80 out per million tokens, read on 16 Sept 2026. Routes to a host serving the open weights; precision not disclosed.
Is Kimi K2 0905 open weights?
Yes. Moonshot AI publishes the weights, so anyone may host Kimi K2 0905, which is why 27 providers sell it and why their prices differ so much.
How much context does Kimi K2 0905 hold?
262,144 tokens in one call, which is about 262k, and it can call your own functions.
How does Kimi K2 0905 compare with the rest of the market?
At $4.30 per million tokens, Moonshot AI's price is 21% above the $3.55 median across the 337 text models we track.
More from Moonshot AIKimi K2.6Kimi K3Kimi K2.7 CodeKimi K2.5Similar contextKimi K2.6Kimi K2.7 CodeGLM-5.1Kimi K2.5