Skip to content
AuraMatrix
← All models

Moonshot AI (Kimi)

Kimi K3

moonshot/kimi-k3ACTIVELast observed 2026-11-09 13:41 UTCLast confirmed against sources 2026-11-15 22:15 UTC

As of 2026-11-15, Kimi K3 costs $3.00 per 1 million input tokens and $15.00 per 1 million output tokens at the official list price (Kimi API). Source: AuraMatrix Token Price Index; snapshot SHA-256 65384338da4ef8f4….

Official list price · Kimi API

VERIFIED Source
Input
3.00
Output
15.00
Cached input
0.30
Cache write
3.00

USD per 1M tokens. A dash means the price was not recorded, not that it is free.

Cache write shown is the 5-minute TTL; 1-hour writes are $6. 1,048,576-token context.

Same channel, other plans: Batch 1.80 / 9.00.

Observed 2026-11-04 08:08 UTC. The source still stated these prices at the last daily check, 2026-11-15 22:15 UTC.

Email me when the price of Kimi K3 changes

One email after our daily check if a price changed; nothing on quiet days. Confirm via the link we send you; unsubscribe in one click.

Cheaper in the same tier

How to read this

Official list prices, blended 3 parts input to 1 part output, against models the vendors place in the same tier. Price only: a cheaper model is not an equal one, and nothing here measures quality.

What this price buys

Answer a question0.81¢A short question, a few paragraphs back.
Summarise a 30-page report7.2¢About 15,000 words in, a one-page summary out.
Coding assistant, one hour$5.40It re-reads the project on every step: lots of reading, some writing. With caching: $1.96.

Estimates from the official list price above: tokens read and written for a typical job of that size, times the price. Your own usage will differ. See how these are worked out, and try other jobs →

All channels

Latest observation per channel, with the time the daily re-check last confirmed it. USD per 1M tokens. Differences are against the official list price.
ChannelTypeRegionInputOutputCached invs officialinput / outputStatusSource
Kimi APIlowest inputMoonshot AI · observed 2026-11-04 08:08 UTC · confirmed 2026-11-15 22:15 UTCplatform.kimi.ai (formerly platform.moonshot.ai). Prices exclude taxes. The page renders in the browser; the snapshot is the rendered DOM captured by headless Chromium.Cache write shown is the 5-minute TTL; 1-hour writes are $6. 1,048,576-token context.Officialone list price worldwideglobalGlobal endpoint3.0015.000.30referenceVERIFIEDSource
Amazon Bedrock, global cross-regionAWS · observed 2026-11-03 03:31 UTC · confirmed 2026-11-15 22:15 UTCGlobal inference profile: requests may be served from any commercial region. Price read from the us-east-1 price list (global-* service tiers).Listed as "Kimi K3" (Moonshot AI). Converted from the price list's per-1K-token unit. Cache write is the 30-minute write.Cloudfixed price per regionglobalGlobal endpoint3.0015.000.300% / 0%VERIFIEDSource
Amazon Bedrock, US East (N. Virginia)AWS · observed 2026-11-03 03:31 UTC · confirmed 2026-11-15 22:15 UTCOn-demand, standard tier.Listed as "Kimi K3" (Moonshot AI). Converted from the price list's per-1K-token unit. Cache write is the 30-minute write.Cloudfixed price per regionUSUnited States3.3016.500.33+10% / +10%VERIFIEDSource

Service plans

Batch, Flex, Priority prices, latest observation per channel and plan. USD per 1M tokens. Differences are against the same channel's standard price.
PlanChannelInputOutputCached invs standardinput / outputStatusSource
BatchThe page states batch inference is billed at 60 percent of the standard price; these amounts are that percentage applied to the standard price.Kimi APIobserved 2026-11-04 08:08 UTC · confirmed 2026-11-15 22:15 UTC1.809.00—−40% / −40%VERIFIEDSource
FlexListed as "Kimi K3" (Moonshot AI). Converted from the price list's per-1K-token unit. Cache write is the 30-minute write.Amazon Bedrock, global cross-regionobserved 2026-11-03 03:31 UTC · confirmed 2026-11-15 22:15 UTC1.507.500.15−50% / −50%VERIFIEDSource
PriorityListed as "Kimi K3" (Moonshot AI). Converted from the price list's per-1K-token unit. Cache write is the 30-minute write.Amazon Bedrock, global cross-regionobserved 2026-11-03 03:31 UTC · confirmed 2026-11-15 22:15 UTC5.2526.250.525+75% / +75%VERIFIEDSource
BatchListed as "Kimi K3" (Moonshot AI). Converted from the price list's per-1K-token unit.Amazon Bedrock, US East (N. Virginia)observed 2026-11-03 03:31 UTC · confirmed 2026-11-15 22:15 UTC1.658.25—−50% / −50%VERIFIEDSource
FlexListed as "Kimi K3" (Moonshot AI). Converted from the price list's per-1K-token unit. Cache write is the 30-minute write.Amazon Bedrock, US East (N. Virginia)observed 2026-11-03 03:31 UTC · confirmed 2026-11-15 22:15 UTC1.658.250.165−50% / −50%VERIFIEDSource
PriorityListed as "Kimi K3" (Moonshot AI). Converted from the price list's per-1K-token unit. Cache write is the 30-minute write.Amazon Bedrock, US East (N. Virginia)observed 2026-11-03 03:31 UTC · confirmed 2026-11-15 22:15 UTC5.77528.8750.5775+75% / +75%VERIFIEDSource

China sites, priced in CNY

CNY (¥) per 1M tokens, as published on each operator's China site. Not converted, and not compared with the USD prices above: exchange rates move from day to day, list prices do not.
ChannelPlanInputOutputCached invs standardinput / outputStatusSource
Kimi API, China siteMoonshot AI · observed 2026-11-09 13:41 UTC · confirmed 2026-11-15 22:15 UTCCache write shown is the 5-minute TTL; 1-hour writes are 40.00.Standard¥20.00¥100.00¥2.00standardVERIFIEDSource
Kimi API, China siteMoonshot AI · observed 2026-11-09 13:41 UTC · confirmed 2026-11-15 22:15 UTCThe page states batch inference is billed at 60 percent of the standard price; these amounts are that percentage applied to the standard price.Batch¥12.00¥60.00—−40% / −40%VERIFIEDSource

Measured

One small request an hour, plus one longer request a day to measure speed, sent from our Los Angeles server over the last 7 days. This does not test model quality; it shows whether the API answered, how soon and how fast. All models →

ChannelAnsweredFirst tokenmedianSpeedtokens per secondCharged vs list priceLast call
Kimi API100%64 of 64 calls3.7 s166—2026-11-15 22:07 UTC

Price history

Input price per 1M tokens on each channel, from the first record to the last daily check. A price holds until the next record that states another one, so the lines are steps; a flat line means the price has not moved since we started recording.

ChannelSinceFirstCourseNowMoves
Amazon Bedrock, global cross-region2026-11-033.003.00·
Amazon Bedrock, US East (N. Virginia)2026-11-033.303.30·
Kimi API2026-11-043.003.00·
Kimi API, China site2026-11-09¥20.00¥20.00·

Names this model is listed under

  • kimi-k3
  • moonshotai/kimi-k3
  • moonshotai.kimi-k3

Compare with

Check a pricePaying for this model, or holding a quote?See where your price stands →

In your AIAsk your assistant: “Where is Kimi K3 cheapest right now, and how fast is it?”Connect in one click →

Sources

Each price above was read from one of these snapshots. The hash identifies the exact page content that was seen.

  1. AWS Price List API: Amazon Bedrock, us-east-1

    URL
    https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json
    Fetched
    2026-11-03 03:31 UTC
    SHA-256
    4140ede2ceeb96e0e7637afb59e4b66847a8bfeaf9c9bf1964aa77570ba440cf
    Size
    1,491,663 bytes
    Records
    • q-20261103-bedrock-global-kimi-k3 · Amazon Bedrock, global cross-region · read from a machine-readable price list by claude (agent) · reviewed by codex (agent) · Listed as "Kimi K3" (Moonshot AI). Converted from the price list's per-1K-token unit. Cache write is the 30-minute write.
    • q-20261103-bedrock-us-east-1-kimi-k3 · Amazon Bedrock, US East (N. Virginia) · read from a machine-readable price list by claude (agent) · reviewed by codex (agent) · Listed as "Kimi K3" (Moonshot AI). Converted from the price list's per-1K-token unit. Cache write is the 30-minute write.
    • q-20261103-bedrock-global-kimi-k3-flex · Amazon Bedrock, global cross-region (Flex) · read from a machine-readable price list by claude (agent) · reviewed by codex (agent) · Listed as "Kimi K3" (Moonshot AI). Converted from the price list's per-1K-token unit. Cache write is the 30-minute write.
    • q-20261103-bedrock-global-kimi-k3-priority · Amazon Bedrock, global cross-region (Priority) · read from a machine-readable price list by claude (agent) · reviewed by codex (agent) · Listed as "Kimi K3" (Moonshot AI). Converted from the price list's per-1K-token unit. Cache write is the 30-minute write.
    • q-20261103-bedrock-us-east-1-kimi-k3-batch · Amazon Bedrock, US East (N. Virginia) (Batch) · read from a machine-readable price list by claude (agent) · reviewed by codex (agent) · Listed as "Kimi K3" (Moonshot AI). Converted from the price list's per-1K-token unit.
    • q-20261103-bedrock-us-east-1-kimi-k3-flex · Amazon Bedrock, US East (N. Virginia) (Flex) · read from a machine-readable price list by claude (agent) · reviewed by codex (agent) · Listed as "Kimi K3" (Moonshot AI). Converted from the price list's per-1K-token unit. Cache write is the 30-minute write.
    • q-20261103-bedrock-us-east-1-kimi-k3-priority · Amazon Bedrock, US East (N. Virginia) (Priority) · read from a machine-readable price list by claude (agent) · reviewed by codex (agent) · Listed as "Kimi K3" (Moonshot AI). Converted from the price list's per-1K-token unit. Cache write is the 30-minute write.
  2. Kimi API: Model Pricing (rendered page)

    URL
    https://platform.kimi.ai/docs/pricing/chat
    Fetched
    2026-11-04 08:08 UTC
    SHA-256
    65384338da4ef8f4bcf75ff888212cb74992cff17cc8571487d078d77eb3b396
    Size
    307,748 bytes
    Records
    • q-20261104-kimi-api-kimi-k3 · Kimi API · recorded by hand from the page by claude (agent) · reviewed by codex (agent) · Cache write shown is the 5-minute TTL; 1-hour writes are $6. 1,048,576-token context.
    • q-20261104-kimi-api-kimi-k3-batch · Kimi API (Batch) · recorded by hand from the page by claude (agent) · reviewed by Jackie (owner) · The page states batch inference is billed at 60 percent of the standard price; these amounts are that percentage applied to the standard price.
  3. Kimi API 开放平台: 模型推理价格 (China site, rendered page, CNY)

    URL
    https://platform.kimi.com/docs/pricing/chat
    Fetched
    2026-11-09 13:41 UTC
    SHA-256
    595bc7211c579540cff9d3773c1197626a59f5ad96ceb190305448b8a678ff6d
    Size
    163,132 bytes
    Records
    • q-20261109d-kimi-cn-kimi-k3 · Kimi API, China site · recorded by hand from the page by claude (agent) · reviewed by codex (agent) · Cache write shown is the 5-minute TTL; 1-hour writes are 40.00.
    • q-20261109d-kimi-cn-kimi-k3-batch · Kimi API, China site (Batch) · recorded by hand from the page by claude (agent) · reviewed by Jackie (owner) · The page states batch inference is billed at 60 percent of the standard price; these amounts are that percentage applied to the standard price.
About these prices: units, what the status marks mean, corrections

Units

US dollars per 1 million tokens, as published by each channel. China-site price lists are shown in CNY, as published; nothing is converted. Last sweep 2026-11-15 22:15 UTC.

Trust status

  • Verified: read from the operator's own price page, and an independent second reader got the same numbers from the snapshot.
  • Listed: a marketplace listing, re-read the same way; what a marketplace bills can depend on where it routes, so it is never the reference.
  • Unverified: recorded, not yet re-read.

Not advice

Unofficial and not affiliated with any vendor. Vendor names are trademarks of their owners. The channel's own page is authoritative. Missing prices are unknown, not free.

Data

The whole dataset as JSON, the same records as these pages. Corrections: hello@auramatrix.ai