Vercel AI SDK

Official Runcrate provider for the Vercel AI SDK — generateText, streamText, generateImage

The @runcrate/ai package is a Runcrate provider for the Vercel AI SDK. Use it to build AI-powered applications with generateText, streamText, generateImage, structured output, and tool calling — all backed by Runcrate’s 140+ open-source models.

Installation

npm install @runcrate/ai ai

Requires ai v6+ and Node.js 18+.

Quick Start

import { runcrate } from '@runcrate/ai';
import { generateText } from 'ai';

const { text } = await generateText({
  model: runcrate('deepseek-ai/DeepSeek-V3'),
  prompt: 'Explain quantum computing in simple terms.',
});

console.log(text);

Set the RUNCRATE_API_KEY environment variable, or pass apiKey directly when creating the provider.

Configuration

import { createRuncrate } from '@runcrate/ai';

const runcrate = createRuncrate({
  apiKey: 'rc_live_...',                       // or RUNCRATE_API_KEY env var
  baseURL: 'https://api.runcrate.ai/v1',      // default
  headers: { 'X-Custom-Header': 'value' },    // optional
});

A default instance is also exported for convenience:

import { runcrate } from '@runcrate/ai';
// Uses RUNCRATE_API_KEY env var automatically

---

Text Generation

Basic

import { runcrate } from '@runcrate/ai';
import { generateText } from 'ai';

const { text } = await generateText({
  model: runcrate('deepseek-ai/DeepSeek-V3'),
  prompt: 'What is the capital of France?',
});

Streaming

import { runcrate } from '@runcrate/ai';
import { streamText } from 'ai';

const result = streamText({
  model: runcrate('deepseek-ai/DeepSeek-V3'),
  prompt: 'Write a short story about a robot.',
});

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

Chat Messages

const { text } = await generateText({
  model: runcrate('meta-llama/Llama-4-Scout'),
  messages: [
    { role: 'system', content: 'You are a helpful assistant.' },
    { role: 'user', content: 'What is the capital of France?' },
  ],
});

Structured Output

import { runcrate } from '@runcrate/ai';
import { generateText, Output } from 'ai';
import { z } from 'zod';

const { output } = await generateText({
  model: runcrate('deepseek-ai/DeepSeek-V3'),
  output: Output.object({
    schema: z.object({
      name: z.string(),
      ingredients: z.array(z.string()),
      steps: z.array(z.string()),
    }),
  }),
  prompt: 'Generate a recipe for chocolate chip cookies.',
});

Image Generation

import { runcrate } from '@runcrate/ai';
import { generateImage } from 'ai';

const { image } = await generateImage({
  model: runcrate.imageModel('black-forest-labs/FLUX.1-schnell'),
  prompt: 'A futuristic cityscape at sunset',
  size: '1024x768',
});

console.log(image.base64);

Embeddings

import { runcrate } from '@runcrate/ai';
import { embed } from 'ai';

const { embedding } = await embed({
  model: runcrate.embeddingModel('BAAI/bge-large-en-v1.5'),
  value: 'The quick brown fox jumps over the lazy dog',
});

Model Methods

Method	Returns	Description
runcrate(modelId)	LanguageModel	Chat model (shorthand for chatModel)
runcrate.chatModel(modelId)	LanguageModel	Chat model for generateText, streamText
runcrate.completionModel(modelId)	LanguageModel	Completion model
runcrate.imageModel(modelId)	ImageModel	Image generation model for generateImage
runcrate.embeddingModel(modelId)	EmbeddingModel	Embedding model for embed, embedMany

---

When to Use Which SDK

SDK	Best For
@runcrate/ai	Next.js/React apps using the Vercel AI SDK — useChat, streamText, generateImage
@runcrate/sdk	Full platform access — instances, storage, billing, and inference in one client
OpenAI SDK	Drop-in compatibility — just change the base URL