Kimi K3

moonshotai/kimi-k3

Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...

InputImageTextVideo
OutputText
Input / Outputclub$3.18 / $15.9per 1M tokens · USD
Context window1Mtoken
Maximum output943.7Ktoken

Pricing

Current model usage rates. Choose your plan to see its published prices.

Pricing
UsagePricing
InputUS$3.18/ 1M token
Cache readUS$0.318/ 1M token
OutputUS$15.9/ 1M token

Membership and model usage are billed separately. Compare plans

Capabilities

Input
ImageTextVideo
Output
Text
Context window
1,048,576 token
Maximum output
943,718 token
Reasoning
max · high · low

Providers

Model supply available through Vecbase.

Via OpenRouter

Access is subject to your account’s permissions and model availability.

Frequently asked questions

What is Kimi K3, and who develops it?

Kimi K3 is a model from Moonshot AI. Its model ID on Vecbase is moonshotai/kimi-k3. Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...

How much does Kimi K3 cost on Vecbase?

For Kimi K3, the Club plan lists USD 3.18 per 1 million input tokens and USD 15.9 per 1 million output tokens, as of 10/22/2026, 10:15:07 PM UTC. See the pricing table for cache rates, input-length tiers and other usage types. Membership fees are separate.

How many tokens fit in Kimi K3’s context window?

Kimi K3 has a context window of 1,048,576 tokens. Input and output must fit within the limits of the API you use.

What is the maximum output length for Kimi K3?

Kimi K3 can generate up to 943,718 tokens per response. Your API or request settings may set a lower limit.

Can Kimi K3 call tools in an agent workflow?

Yes. Kimi K3 supports tool calling. Your application provides the tool definitions and runs the tools the model requests.

Does Kimi K3 support structured outputs?

Yes. Kimi K3 supports structured output. Set the required format in your API request and check the returned data before using it.

Which input and output formats does Kimi K3 support?

Kimi K3 accepts Image, Text, and Video and produces Text.

Which providers make Kimi K3 available through Vecbase?

Vecbase offers Kimi K3 through OpenRouter. Availability may vary by provider.

Which model ID should an agent use to request Kimi K3?

Use moonshotai/kimi-k3 as the model identifier for Kimi K3. See Vecbase’s API documentation for authentication, required inputs and supported request formats.

Which reasoning settings are listed for Kimi K3?

Kimi K3 supports these reasoning levels: max, high, and low. Available options depend on your API.

What does an agent need to access Kimi K3 through Vecbase?

To use Kimi K3, you need an authenticated account with the required permissions, sufficient balance and the relevant capability enabled. See the documentation for setup.

Is a release date available for Kimi K3?

We do not yet have a confirmed release date for Kimi K3.

Which models can I compare with Kimi K3 on Vecbase?

You can compare Kimi K3 with Kimi Latest (moonshotai/kimi-latest), Kimi K2.5 (moonshotai/kimi-k2.5), and Vecbase Flash (vecbase-1.0-lite). Check their capabilities and prices to find the best fit for your task.