Cerebras Provider

The Cerebras provider offers access to powerful language models through the Cerebras API, including their high-speed inference capabilities powered by Wafer-Scale Engines and CS-3 systems.

API keys can be obtained from the Cerebras Platform.

Setup

The Cerebras provider is available via the @ai-sdk/cerebras module. You can install it with:

pnpm add @ai-sdk/cerebras

Provider Instance

You can import the default provider instance cerebras from @ai-sdk/cerebras:

1
import { cerebras } from '@ai-sdk/cerebras';

For custom configuration, you can import createCerebras and create a provider instance with your settings:

1
import { createCerebras } from '@ai-sdk/cerebras';
2

3
const cerebras = createCerebras({
4
  apiKey: process.env.CEREBRAS_API_KEY ?? '',
5
});

You can use the following optional settings to customize the Cerebras provider instance:

• baseURL string

  Use a different URL prefix for API calls. The default prefix is https://api.cerebras.ai/v1.

• apiKey string

  API key that is being sent using the Authorization header. It defaults to the CEREBRAS_API_KEY environment variable.

• headers Record<string,string>

  Custom headers to include in the requests.

• fetch (input: RequestInfo, init?: RequestInit) => Promise<Response>

  Custom fetch implementation.

Language Models

You can create language models using a provider instance:

1
import { cerebras } from '@ai-sdk/cerebras';
2
import { generateText } from 'ai';
3

4
const { text } = await generateText({
5
  model: cerebras('llama3.1-8b'),
6
  prompt: 'Write a vegetarian lasagna recipe for 4 people.',
7
});

Cerebras language models can be used in the streamText function (see AI SDK Core).

You can create Cerebras language models using a provider instance. The first argument is the model ID, e.g. llama-3.3-70b:

1
const model = cerebras('llama-3.3-70b');

You can also use the .languageModel() and .chat() methods:

1
const model = cerebras.languageModel('llama-3.3-70b');
2
const model = cerebras.chat('llama-3.3-70b');

Reasoning Models

Cerebras offers several reasoning models including gpt-oss-120b, qwen-3-32b, and zai-glm-4.7 that generate intermediate thinking tokens before their final response. The reasoning output is streamed through the standard AI SDK reasoning parts.

For gpt-oss-120b, you can control the reasoning depth using the reasoningEffort provider option:

1
import { cerebras } from '@ai-sdk/cerebras';
2
import { streamText } from 'ai';
3

4
const result = streamText({
5
  model: cerebras('gpt-oss-120b'),
6
  providerOptions: {
7
    cerebras: {
8
      reasoningEffort: 'medium',
9
    },
10
  },
11
  prompt: 'How many "r"s are in the word "strawberry"?',
12
});
13

14
for await (const part of result.fullStream) {
15
  if (part.type === 'reasoning') {
16
    console.log('Reasoning:', part.text);
17
  } else if (part.type === 'text-delta') {
18
    process.stdout.write(part.textDelta);
19
  }
20
}

See AI SDK UI: Chatbot for more details on how to integrate reasoning into your chatbot.

Provider Options

The following optional provider options are available for Cerebras language models:

• reasoningEffort 'low' | 'medium' | 'high'

  Controls the depth of reasoning for GPT-OSS models. Defaults to 'medium'.

• user string

  A unique identifier representing your end-user, which can help with monitoring and abuse detection.

• strictJsonSchema boolean

  Whether to use strict JSON schema validation. When true, the model uses constrained decoding to guarantee schema compliance. Defaults to true.

Model Capabilities