@terramind/ai-sdk-provider

Use Terramind's unified LLM API with the Vercel AI SDK.

Installation

npm install @terramind/ai-sdk-provider ai
# or
pnpm add @terramind/ai-sdk-provider ai
# or
bun add @terramind/ai-sdk-provider ai

Quick Start

import { createTerramind } from '@terramind/ai-sdk-provider'
import { streamText } from 'ai'

// Initialize the provider
const terramind = createTerramind({
  apiKey: process.env.TERRAMIND_API_KEY,
})

// Use with any Terramind model
const result = await streamText({
  model: terramind('claude-sonnet-4-5'),
  prompt: 'Write a haiku about coding',
})

for await (const chunk of result.textStream) {
  process.stdout.write(chunk)
}

Available Models

Terramind provides access to multiple LLM providers through a single API:

• Claude: claude-sonnet-4-5, claude-sonnet-4, claude-haiku-4-5, claude-3-5-haiku, claude-opus-4-1
• GPT: gpt-5, gpt-5-codex
• Chinese Models: glm-4.6, kimi-k2, qwen3-coder
• Specialized: grok-code, big-pickle

Authentication

You can authenticate in two ways:

// 1. Pass API key directly
const terramind = createTerramind({
  apiKey: 'your-api-key'
})

// 2. Use environment variable (recommended)
// Set TERRAMIND_API_KEY in your .env file
const terramind = createTerramind()

Features

Streaming

import { streamText } from 'ai'

const result = await streamText({
  model: terramind('claude-haiku-4-5'),
  prompt: 'Explain quantum computing',
})

for await (const chunk of result.textStream) {
  process.stdout.write(chunk)
}

Tool Calling

import { generateText, tool } from 'ai'
import { z } from 'zod'

const result = await generateText({
  model: terramind('claude-sonnet-4-5'),
  prompt: 'What is the weather in San Francisco?',
  tools: {
    getWeather: tool({
      description: 'Get the weather for a location',
      parameters: z.object({
        location: z.string(),
      }),
      execute: async ({ location }) => ({
        temperature: 72,
        condition: 'sunny',
        location,
      }),
    }),
  },
})

console.log(result.text)

Structured Outputs

import { generateObject } from 'ai'
import { z } from 'zod'

const result = await generateObject({
  model: terramind('claude-sonnet-4-5'),
  schema: z.object({
    recipe: z.object({
      name: z.string(),
      ingredients: z.array(z.string()),
      steps: z.array(z.string()),
    }),
  }),
  prompt: 'Generate a recipe for chocolate chip cookies',
})

console.log(result.object.recipe)

Configuration Options

interface TerramindProviderSettings {
  /**
   * Terramind API key. Defaults to process.env.TERRAMIND_API_KEY
   */
  apiKey?: string

  /**
   * Base URL for the Terramind API.
   * Defaults to:
   * - Production: https://terramind.com/api/v1
   * - Development: http://localhost:3002/api/v1
   */
  baseURL?: string
}

Get an API Key

Visit terramind.com to sign up and get your API key.

Links

• Website
• Documentation
• API Reference
• GitHub
• Vercel AI SDK

License

MIT