Skip to content
Moonshot AI

Kimi K2

moonshot/kimi-k2
Open weightsLanguage

Moonshot's open agentic flagship, long-context stamina and tool use that holds up across extended sessions.

Model overview

Context window

256K

tokens

Input price

—

quoted on request

Output price

—

quoted on request

Weekly volume

—

tokens / week

Open weights

Yes

self-hostable

Capabilities

5

of 11 tags

Description

Kimi K2 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). Its mean it can also be self-hosted under its licence.

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.
Open weights
The parameters are published, so the model can be inspected, fine-tuned and self-hosted under its licence.
Caching
Reuses already-processed prompt prefixes across requests, cutting input cost for repeated context.

Strengths & weaknesses

Strengths

  • Long-context quality that survives real use
  • Agentic tool use
  • Open weights

Weaknesses

  • Output price above Chinese peers
  • Vision requires the separate VL model

Pricing

Pricing for Kimi K2, per 1M tokens
RatePriceUnit
Input— quoted on request—
Output— quoted on request—

Prompt caching is supported, so repeated prefixes bill below the listed input rate. This model is not provisioned yet; the rate is quoted on request.

Context window

256Ktokens

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

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

Supported features

Feature support for Kimi K2
FeatureSupport
Tool callingSupported
JSON modeSupported
StreamingSupported
Vision inputNot supported
Audio inputNot supported
Long contextNot supported
Open weightsSupported
ReasoningNot supported
Fine-tunableNot supported
BatchNot supported
CachingSupported

Example use cases

  • Long-document analysis

  • Agent workflows

  • Research assistants

Related models

Comparison

Compare against anything →
Kimi K2 compared with Kimi K2 Thinking and DeepSeek V3.2
AttributeKimi K2Kimi K2 ThinkingDeepSeek V3.2
Context window256K256K128K
Input priceR0.00R0.00R0.00
Output price— not charged— not charged— not charged
Tool callingSupportedSupportedSupported
JSON modeSupportedNot supportedSupported
Vision inputNot supportedNot supportedNot supported
Open weightsSupportedSupportedSupported
Prompt cachingSupportedNot supportedSupported

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 R0.00 per 1M tokens, and there is no separate output charge. Prompt caching bills repeated prefixes below the listed input rate. Every figure on this page is an illustrative placeholder.