AI Providers

The Workflow AI SDK provides provider functions that wrap AI SDK providers with durable execution capabilities. Each provider function creates a step function that returns a language model instance, ensuring proper state management in workflow contexts.

Overview

All provider functions follow the same pattern:

import { provider } from '@workflow/ai/providers/{provider}';

const modelFunction = provider(options);
const agent = new DurableAgent({
  model: modelFunction(modelId),
});

The provider wrappers automatically mark the model instantiation as a workflow step, ensuring durability.

Anthropic

Integrate with Claude models from Anthropic.

Import

import { anthropic } from '@workflow/ai/providers/anthropic';

Usage

import { DurableAgent } from '@workflow/ai';
import { anthropic } from '@workflow/ai/providers/anthropic';

const agent = new DurableAgent({
  model: anthropic({
    apiKey: process.env.ANTHROPIC_API_KEY,
  })('claude-3-5-sonnet-20241022'),
});

Signature

function anthropic(options?: {
  apiKey?: string;
  baseURL?: string;
  headers?: Record<string, string>;
}): (modelId: string) => Promise<LanguageModel>

object

Show properties

string

Anthropic API key. Defaults to ANTHROPIC_API_KEY environment variable.

string

Custom API base URL (for proxies or testing)

Record<string, string>

Additional HTTP headers for requests

Returns: Function that accepts a model ID and returns a Promise resolving to a LanguageModel

Available Models

claude-3-5-sonnet-20241022 - Latest Sonnet (most balanced)
claude-3-5-haiku-20241022 - Fast and efficient
claude-3-opus-20240229 - Most capable (legacy)
claude-3-sonnet-20240229 - Balanced (legacy)
claude-3-haiku-20240307 - Fast (legacy)

See Anthropic’s model documentation for the latest models.

Example

import { DurableAgent } from '@workflow/ai';
import { anthropic } from '@workflow/ai/providers/anthropic';
import { getWritable } from 'workflow';

export async function claudeWorkflow() {
  'use workflow';

  const agent = new DurableAgent({
    model: anthropic({
      apiKey: process.env.ANTHROPIC_API_KEY,
    })('claude-3-5-sonnet-20241022'),
    system: 'You are a helpful assistant.',
    temperature: 0.7,
  });

  await agent.stream({
    messages: [{ role: 'user', content: 'Hello!' }],
    writable: getWritable(),
  });
}

OpenAI

Integrate with GPT models from OpenAI.

Import

import { openai } from '@workflow/ai/providers/openai';

Usage

import { DurableAgent } from '@workflow/ai';
import { openai } from '@workflow/ai/providers/openai';

const agent = new DurableAgent({
  model: openai({
    apiKey: process.env.OPENAI_API_KEY,
  })('gpt-4o'),
});

Signature

function openai(options?: {
  apiKey?: string;
  organization?: string;
  project?: string;
  baseURL?: string;
  headers?: Record<string, string>;
}): (modelId: string) => Promise<LanguageModel>

object

Show properties

string

OpenAI API key. Defaults to OPENAI_API_KEY environment variable.

string

OpenAI organization ID (optional)

string

OpenAI project ID (optional)

string

Custom API base URL (for proxies or Azure OpenAI)

Record<string, string>

Additional HTTP headers for requests

Returns: Function that accepts a model ID and returns a Promise resolving to a LanguageModel

Available Models

gpt-4o - Latest and most capable GPT-4 model
gpt-4o-mini - Affordable and intelligent small model
gpt-4-turbo - Previous flagship model
gpt-3.5-turbo - Fast and cost-effective
o1-preview - Advanced reasoning (limited features)
o1-mini - Fast reasoning model

See OpenAI’s model documentation for the latest models.

Example

import { DurableAgent } from '@workflow/ai';
import { openai } from '@workflow/ai/providers/openai';
import { getWritable } from 'workflow';
import { z } from 'zod';

export async function gptWorkflow() {
  'use workflow';

  const agent = new DurableAgent({
    model: openai({
      apiKey: process.env.OPENAI_API_KEY,
    })('gpt-4o'),
    tools: {
      calculate: {
        description: 'Perform a calculation',
        inputSchema: z.object({
          expression: z.string(),
        }),
        execute: async ({ expression }) => {
          'use step';
          return eval(expression);
        },
      },
    },
  });

  await agent.stream({
    messages: [{ role: 'user', content: 'What is 12 * 34?' }],
    writable: getWritable(),
  });
}

Google AI

Integrate with Gemini models from Google.

Import

import { google } from '@workflow/ai/providers/google';

Usage

import { DurableAgent } from '@workflow/ai';
import { google } from '@workflow/ai/providers/google';

const agent = new DurableAgent({
  model: google({
    apiKey: process.env.GOOGLE_API_KEY,
  })('gemini-2.0-flash-exp'),
});

Signature

function google(options?: {
  apiKey?: string;
  baseURL?: string;
  headers?: Record<string, string>;
}): (modelId: string) => Promise<LanguageModel>

object

Show properties

string

Google AI API key. Defaults to GOOGLE_GENERATIVE_AI_API_KEY environment variable.

string

Custom API base URL (optional)

Record<string, string>

Additional HTTP headers for requests

Returns: Function that accepts a model ID and returns a Promise resolving to a LanguageModel

Available Models

gemini-2.0-flash-exp - Latest experimental Flash model
gemini-1.5-pro - Most capable production model
gemini-1.5-flash - Fast and efficient
gemini-1.0-pro - Legacy production model

See Google’s model documentation for the latest models.

Example

import { DurableAgent } from '@workflow/ai';
import { google } from '@workflow/ai/providers/google';
import { getWritable } from 'workflow';

export async function geminiWorkflow() {
  'use workflow';

  const agent = new DurableAgent({
    model: google({
      apiKey: process.env.GOOGLE_API_KEY,
    })('gemini-2.0-flash-exp'),
    system: 'You are a creative writing assistant.',
  });

  await agent.stream({
    messages: [
      { role: 'user', content: 'Write a short story about a robot.' },
    ],
    writable: getWritable(),
  });
}

xAI

Integrate with Grok models from xAI.

Import

import { xai } from '@workflow/ai/providers/xai';

Usage

import { DurableAgent } from '@workflow/ai';
import { xai } from '@workflow/ai/providers/xai';

const agent = new DurableAgent({
  model: xai({
    apiKey: process.env.XAI_API_KEY,
  })('grok-2-latest'),
});

Signature

function xai(options?: {
  apiKey?: string;
  baseURL?: string;
  headers?: Record<string, string>;
}): (modelId: string) => Promise<LanguageModel>

object

Show properties

string

xAI API key. Defaults to XAI_API_KEY environment variable.

string

Custom API base URL (optional)

Record<string, string>

Additional HTTP headers for requests

Returns: Function that accepts a model ID and returns a Promise resolving to a LanguageModel

Available Models

grok-2-latest - Latest Grok 2 model
grok-2-1212 - Grok 2 from December 2024
grok-beta - Beta version with latest features

See xAI’s documentation for the latest models.

Example

import { DurableAgent } from '@workflow/ai';
import { xai } from '@workflow/ai/providers/xai';
import { getWritable } from 'workflow';

export async function grokWorkflow() {
  'use workflow';

  const agent = new DurableAgent({
    model: xai({
      apiKey: process.env.XAI_API_KEY,
    })('grok-2-latest'),
    temperature: 0.8,
  });

  await agent.stream({
    messages: [
      { role: 'user', content: 'Explain quantum computing in simple terms' },
    ],
    writable: getWritable(),
  });
}

Using AI Gateway

Instead of provider functions, you can use Vercel AI Gateway with a string model identifier:

import { DurableAgent } from '@workflow/ai';

const agent = new DurableAgent({
  model: 'anthropic/claude-3-5-sonnet-20241022',
  // AI Gateway handles authentication and routing
});

This approach:

Centralizes API key management
Provides built-in caching and rate limiting
Enables easy provider switching
Requires AI Gateway configuration

Provider Comparison

Provider	Strengths	Best For
Anthropic	Long context, safety, reasoning	Complex analysis, content moderation
OpenAI	General capabilities, ecosystem	Wide range of tasks, familiar API
Google	Multimodal, speed	Image/video analysis, fast responses
xAI	Reasoning, real-time knowledge	Problem-solving, current events

Best Practices

Use environment variables: Store API keys in environment variables, never hardcode them
Choose the right model: Use smaller/faster models for simple tasks, larger models for complex reasoning
Set appropriate limits: Configure maxOutputTokens based on your use case
Handle rate limits: Workflow steps automatically retry on rate limits
Monitor costs: Track token usage through step results and telemetry
Test locally: Use local development mode to test without consuming API credits

Overview

Core API

AI SDK Integration

Runtime API

Framework Integrations

CLI

Overview

Anthropic

Import

Usage

Signature

Available Models

Example

OpenAI

Import

Usage

Signature

Available Models

Example

Google AI

Import

Usage

Signature

Available Models

Example

xAI

Import

Usage

Signature

Available Models

Example

Using AI Gateway

Provider Comparison

Best Practices

See Also

​Overview

​Anthropic

​Import

​Usage

​Signature

​Available Models

​Example

​OpenAI

​Import

​Usage

​Signature

​Available Models

​Example

​Google AI

​Import

​Usage

​Signature

​Available Models

​Example

​xAI

​Import

​Usage

​Signature

​Available Models

​Example

​Using AI Gateway

​Provider Comparison

​Best Practices

​See Also

Overview

Anthropic

Import

Usage

Signature

Available Models

Example

OpenAI

Import

Usage

Signature

Available Models

Example

Google AI

Import

Usage

Signature

Available Models

Example

xAI

Import

Usage

Signature

Available Models

Example

Using AI Gateway

Provider Comparison

Best Practices

See Also