/

/

Kimi K3

Kimi K3

Kimi K3 is a Kimi model available in SteelEngine. It supports a 1.05M token context window. Pricing starts at $3/1M input tokens and $15/1M output tokens. Key capabilities include Tool choice, Structured outputs, Reasoning low, high, max.

The highest-priced model in the Kimi lineup, for the hardest reasoning and planning work. A recommended default among SteelEngine’s Kimi models.

INPUT / 1M

$3

CACHED INPUT / 1M

$0.3

OUTPUT / 1M

$15

CONTEXT WINDOW

1.05M

MAX OUTPUT

1.05M

RELEASED

PRICING

What Kimi K3 costs to run.

List prices in USD per 1M tokens. Cached input applies when a request reuses a prompt the provider has already cached.

01 / INPUT

$3

per 1M input tokens

02 / CACHED INPUT

$0.3

per 1M cached input tokens

03 / OUTPUT

$15

per 1M output tokens

LONG CONTEXT

SUPPORTED CAPABILITIES

What Kimi K3 supports.

Capabilities show up as model settings on SteelEngine workflow blocks and agents, so teams can tune each step without changing providers.

CAPABILITIES

Tool choice, Structured outputs, Reasoning low, high, max, Max output 1.05M

CONTEXT WINDOW

1.05M

MAX OUTPUT TOKENS

1.05M

MODEL ID

kimi-k3

PROVIDER

Kimi

BUILD WITH STEELENGINE

Put Kimi K3 to work.

Use this model in deterministic workflow steps or production agents, with approvals, guardrails, and a full audit trail around every call.