Private AI. Paid by Yield, from every chain.

curl https://api.infernear.dev/v1/chat/completions \
  -H "Authorization: Bearer $INFERNEAR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "Qwen/Qwen3.8-27B", "max_tokens": 256,
       "messages": [{"role": "user", "content": "Reply with the word ok."}]}'

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://api.infernear.dev/v1',
  apiKey: process.env.INFERNEAR_API_KEY, // inf_…
});

const completion = await client.chat.completions.create({
  model: 'Qwen/Qwen3.8-27B',
  messages: [{ role: 'user', content: 'Reply with the word ok.' }],
  max_tokens: 256,
});
console.log(completion.choices[0].message.content);

import { InferenceClient, verifyDeploymentImageProvenance } from '@nearai/inference-sdk';

// "Verified" must mean NEAR's own gateway images, not just genuine TEE hardware.
const build = (repository, workflow = '.github/workflows/build.yml') => ({ repository, workflow });
const GATEWAY_IMAGES = {
  'nearaidev/cloud-api': build('nearai/cloud-api'),
  'nearaidev/cvm-ingress': build('nearai/cvm-ingress', '.github/workflows/build-push.yml'),
};

const client = new InferenceClient({
  baseUrl: 'https://api.infernear.dev/v1',
  apiKey: process.env.INFERNEAR_API_KEY, // inf_…
  e2ee: true, // encrypt to the model's TEE key, here, before sending
  gatewayVerification: {
    verifiers: {
      deployment: ({ appCompose }) =>
        verifyDeploymentImageProvenance({ appCompose, imagePolicies: GATEWAY_IMAGES }),
    },
  },
});

const completion = await client.chat.completions.create({
  model: 'Qwen/Qwen3.8-27B',
  messages: [{ role: 'user', content: 'Reply with the word ok.' }],
  max_tokens: 256,
});

// Check the model's signature over the exact request and reply bytes.
const receipt = await client.verifyResponse(completion.id);
console.log(`Verified ${receipt.signatureKind} reply:`, completion.choices[0].message.content);