Kimi K3

3P Confidential TEE

moonshotai/kimi-k3

Moonshot AI native multimodal agentic model with a 1M-token context window, built for long-horizon coding, knowledge work, and reasoning.

Input / 1M tokens: $3.3
Output / 1M tokens: $16.5
Cache read / 1M tokens: $0.33
Context window: 1048K tokens

Privacy & execution

This model supports confidential inference inside a hardware-isolated Trusted Execution Environment (TEE), protecting data while it is processed. HTTPS protects data in transit; client-to-model end-to-end encryption depends on the model and integration.

Attestation provides cryptographic evidence of the execution environment’s identity and configuration. Where response signatures are available, you can also verify the integrity of the request and response.

Verification documentation

Make your first request

Call /v1/chat/completions over HTTPS.

Get an API key and set the NEARAI_API_KEY environment variable.

curl --fail-with-body "https://cloud-api.near.ai/v1/chat/completions" \
  -H "Authorization: Bearer $NEARAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "moonshotai/kimi-k3",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ]
}'

This HTTP example uses HTTPS. Use the SDK below to verify Gateway and model attestations, then response signatures.

Build and Verify with the SDK

Keep the OpenAI SDK interface. Let the inference client verify Gateway and model attestations.

Verification guide

NEAR AI Inference SDK is available for JavaScript (Node.js 24+) and Python (3.12+). Set NEARAI_API_KEY in your environment before running these examples.

Python verifies only the Gateway for this provider; the JavaScript SDK also verifies its model attestation.

npm install @nearai/inference-sdk openai

import OpenAI from "openai";
import { InferenceClient } from "@nearai/inference-sdk/node";

const apiKey = process.env.NEARAI_API_KEY;
if (!apiKey) throw new Error("Set NEARAI_API_KEY first.");

// Verify Gateway and model attestations. This provider does not support field E2EE.
const inferenceClient = new InferenceClient({
  apiKey,
  baseUrl: "https://cloud-api.near.ai/v1",
  e2ee: false,
});

const openai = new OpenAI({
  apiKey,
  baseURL: inferenceClient.getBaseUrl(),
  fetch: inferenceClient.fetch,
});

const completion = await openai.chat.completions.create({
  model: "moonshotai/kimi-k3",
  messages: [{ role: "user", content: "Hello!" }],
});

// Verify the exact request/response bytes before displaying the answer.
const verified = await inferenceClient.verifyResponse(completion.id);
console.log(completion.choices[0]?.message.content ?? "");
console.log("Verified signer:", verified.signatureKind);

See the JavaScript SDK guide or the Python SDK guide.