Skip to content

Kimi K3

moonshot/kimi-k3
Language

The current Kimi flagship, with a 1.05M context. Sourceable through Webparam on request; not provisioned on this account yet.

Model overview

Context window

1.05M

tokens

Input price

R62.30

per 1M tokens

Output price

R311.00

per 1M tokens

Weekly volume

tokens / week

Open weights

No

API only

Capabilities

3

of 11 tags

Description

Kimi K3 is a language model from Moonshot AI. Webparam does not stock this model yet and can source it on request — tell us what you need it for and we will come back with availability and a price. Moonshot AI’s stated focus is long-context agentic intelligence (Kimi). The weights are not published, so it is API-only.

Capabilities

Tool calling
Calls functions you define and returns their arguments as structured data, the basis of agents.
JSON mode
Constrains the response to valid JSON matching a schema you supply.
Streaming
Emits tokens as they are generated, so answers appear progressively rather than all at once.

Strengths & weaknesses

Strengths

  • 1.05M context
  • Flagship-class quality
  • Price quoted from the supplier's own rate card, not estimated

Weaknesses

  • Priced with Western flagships rather than below them
  • Not provisioned on this account yet — lead time applies

Pricing

Pricing for Kimi K3, per 1M tokens
RatePriceUnit
InputR62.30per 1M tokens
OutputR311.00per 1M tokens

This model is not provisioned yet; the rate is quoted on request.

Context window

1.05Mtokens

covers prompt and response together, so a long input leaves less room for the answer.

1.05M tokens against a peer range of 32K to 10M, median 256K. Compared across 34 language models. Logarithmic scale.

Supported features

Feature support for Kimi K3
FeatureSupport
Tool callingSupported
JSON modeSupported
StreamingSupported
Vision inputNot supported
Audio inputNot supported
Long contextNot supported
Open weightsNot supported
ReasoningNot supported
Fine-tunableNot supported
BatchNot supported
CachingNot supported

Example use cases

  • General assistants

  • Retrieval-augmented answering

  • Everyday production traffic

Kimi K3 compared with Kimi K2.6 and AC Flash 4.5
AttributeKimi K3Kimi K2.6AC Flash 4.5
Context window1.05M262K
Input priceR62.30R16.60R10.00
Output priceR311.00R72.70R40.00
Tool callingSupportedSupportedSupported
JSON modeSupportedSupportedSupported
Vision inputNot supportedNot supportedNot supported
Open weightsNot supportedNot supportedNot supported
Prompt cachingNot supportedNot supportedNot supported

Best value in each row is highlighted. Blank cells are facts the supplier does not publish, not zeroes.

Provider information

View Moonshot AI
Moonshot AI5 models

Moonshot AI · 月之暗面 · Beijing, China · est. 2023

Moonshot's Kimi line made long context its signature, and its K2 generation paired that with serious agentic tool use, released with open weights. The lab moves fast and publishes aggressively, making Kimi one of the most-watched model families in the ecosystem.

Recent releases

    Documentation

    Frequently asked questions

    Input is billed at R62.30 per 1M tokens and output at R311.00 per 1M tokens. Every figure on this page is an illustrative placeholder.