QUICKSILVER PRO / Setup
Vercel AI SDK
Connect Vercel AI SDK to QuickSilver Pro: endpoint, API key, trial model and setup notes.
Create an API key in the dashboard, then use the configuration below. The starter model is available on the API trial.
Set this in the terminal that starts the tool:
export QUICKSILVER_API_KEY='YOUR_QUICKSILVER_API_KEY'import { createOpenAICompatible } from '@ai-sdk/openai-compatible';
import { generateText } from 'ai';
const quicksilver = createOpenAICompatible({
name: 'quicksilver',
baseURL: 'https://api.quicksilverpro.io/v1',
apiKey: process.env.QUICKSILVER_API_KEY,
});
const { text } = await generateText({
model: quicksilver('claude-haiku-5-5'),
prompt: 'Explain this project in one paragraph.',
maxOutputTokens: 256,
});
console.log(text);Start with Claude Haiku 5.5 on the trial. Add credit to use Sonnet or Opus; those models are not included in the trial.
Choose a model
Haiku is the low-cost starting point. Sonnet and Opus support reasoning as well as tool calling. Choose a model for your task and check its catalog page for limits.
USD per million tokens · input / output · standard context rates
- Claude Haiku 5.5$0.025 ($0.125 >200K) / $0.125 ($0.625 >200K)
- Claude Sonnet 5.5$0.50 / $2.50
- Claude Opus 5.5$1.00 / $5.00
Before you start
Install ai and @ai-sdk/openai-compatible. Run this on your server with QUICKSILVER_API_KEY set. Do not put your key in browser code. This example explicitly uses the Chat Completions compatible provider.
Keep API keys in your environment or private user settings. Never commit them. Agent loops and long prompts consume credit; start with a small task and an output limit.