NEAR AI Cloud | AI SDK 简体中文

NEAR AI Cloud provides TEE-backed inference through an OpenAI-compatible API. You can use it with the AI SDK through the @ai-sdk/openai-compatible module.

Setup

The NEAR AI Cloud provider is available via the @ai-sdk/openai-compatible module as it is compatible with the OpenAI API. You can install it with:

pnpm

npm

yarn

bun

pnpm add @ai-sdk/openai-compatible

npm install @ai-sdk/openai-compatible

yarn add @ai-sdk/openai-compatible

bun add @ai-sdk/openai-compatible

Provider Instance

To use NEAR AI Cloud, you can create a custom provider instance with the createOpenAICompatible function from @ai-sdk/openai-compatible:

import { createOpenAICompatible } from '@ai-sdk/openai-compatible';

const nearai = createOpenAICompatible({
  name: 'nearai',
  baseURL: 'https://cloud-api.near.ai/v1',
  apiKey: process.env.NEARAI_API_KEY,
  transformRequestBody: body => {
    const { reasoning_effort, ...rest } = body;
    return rest;
  },
});

Note

You can create an API key in NEAR AI Cloud. Make sure to set the NEARAI_API_KEY environment variable with your API key.

Language Models

You can create NEAR AI Cloud models using a provider instance. The first argument is the model ID from the public model catalog, e.g. zai-org/GLM-5.1-FP8.

const model = nearai('zai-org/GLM-5.1-FP8');

Example

You can use NEAR AI Cloud language models to generate text with the generateText function:

import { createOpenAICompatible } from '@ai-sdk/openai-compatible';
import { generateText } from 'ai';

const nearai = createOpenAICompatible({
  name: 'nearai',
  baseURL: 'https://cloud-api.near.ai/v1',
  apiKey: process.env.NEARAI_API_KEY,
  transformRequestBody: body => {
    const { reasoning_effort, ...rest } = body;
    return rest;
  },
});

const { text } = await generateText({
  model: nearai('zai-org/GLM-5.1-FP8'),
  prompt: 'Tell me about yourself in one sentence.',
});

console.log(text);

NEAR AI Cloud language models can also generate text in a streaming fashion with the streamText function:

import { createOpenAICompatible } from '@ai-sdk/openai-compatible';
import { streamText } from 'ai';

const nearai = createOpenAICompatible({
  name: 'nearai',
  baseURL: 'https://cloud-api.near.ai/v1',
  apiKey: process.env.NEARAI_API_KEY,
  transformRequestBody: body => {
    const { reasoning_effort, ...rest } = body;
    return rest;
  },
});

const result = streamText({
  model: nearai('zai-org/GLM-5.1-FP8'),
  prompt: 'Write a short haiku about private inference.',
});

for await (const message of result.textStream) {
  console.log(message);
}

You can use any supported modelId from the NEAR AI Cloud model catalog. Model metadata includes context length, modalities, and whether TEE attestation is supported for that model.