Vercel AI SDK

Use Chutes with the Vercel AI SDK.

The Vercel AI SDK can call Chutes through an OpenAI-compatible provider configured with baseURL, apiKey, and a live model ID.
Open source guideConnect quickstarts
OpenAI-compatible guideConnect draftEndpoint guide
Status
OpenAI-compatible client
Base URL
https://llm.chutes.ai/v1
Live model example
Qwen/Qwen3-32B-TEE
Catalog checked
Jun 25, 2026; context 40K

Full setup walkthrough

Everything you need is on this page — no need to leave for the toolkit. Each step is copy-paste runnable and uses a live model id from the catalog.

  1. 01

    Install the Chutes provider

    bash
    npm install @chutes-ai/ai-sdk-provider ai
  2. 02

    Create the provider and generate

    createChutes
    typescript
    import { createChutes } from '@chutes-ai/ai-sdk-provider';
import { generateText } from 'ai';

const chutes = createChutes({ apiKey: process.env.CHUTES_API_KEY });

const { text } = await generateText({
  model: chutes(process.env.CHUTES_MODEL ?? 'Qwen/Qwen3-32B-TEE'),
  prompt: 'Say hello in one sentence.',
});
console.log(text);
  3. 03

    Provide the API key

    In a Next.js app, put CHUTES_API_KEY=cpk_... in .env.local and read it server-side only.
    bash
    export CHUTES_API_KEY=cpk_...

The framework contract

Set
base_url / baseURL / api_base
Value
https://llm.chutes.ai/v1
Set
model
Value
Qwen/Qwen3-32B-TEE from the live catalog

Troubleshooting

Symptom
The model ID fails
Likely cause
The catalog changed or the client cached model metadata.
Fix
Refresh /v1/models and update the config.
Symptom
Auth falls into anonymous limits
Likely cause
The key is missing or not sent as Bearer auth.
Fix
Export CHUTES_API_KEY=cpk_... and send Authorization: Bearer.
Symptom
Routing aliases fail
Likely cause
Saved default aliases need a dashboard Model Routing pool.
Fix
Use a concrete model ID or an inline comma-separated pool first.