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 navigating large repositories, using tools, debugging, and iterating against images, logs, tests, and runtime feedback. Its architecture uses KDA and Attention Residuals for computational efficiency.
$0.076market price $0.152
$0.065market price $0.13
$4.67market price $9.34
Throughput is how fast the model writes (tokens per second, higher is better). Time to first token is how long before the answer starts (lower is better).
Share of requests served without a server error. Client errors (4xx) do not count.
Works with the OpenAI SDK pointed at our base URL. Every parameter is in the API reference.
Tokens processed per day on NagaAI.
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 navigating large repositories, using tools, debugging, and iterating against images, logs, tests, and runtime feedback.
On NagaAI, Kimi K3 costs $0.076 per 1M input tokens and $4.67 per 1M output tokens. You pay only for what you use, with no subscription.
Kimi K3 reads up to 1M tokens in one request, counting the prompt and the answer together.
Yes. Kimi K3 can call your functions as tools and can answer in a JSON schema you give it.
It takes text and images as input and returns text.
Create an API key, copy the model ID from the top of this page and send requests with the OpenAI or Anthropic SDK pointed at NagaAI. The API section on this page has a ready example.
Kimi K3.1 ProMoonShotAIKimi K2.7 CodeMoonShotAIKimi K2.6MoonShotAIKimi K2.5MoonShotAIKimi K2 ThinkingMoonShotAIKimi K2 0905MoonShotAI