Models

Within AgentKit, models are adapters that wrap a given provider (ex. OpenAI, Anthropic)‘s specific model version (ex. gpt-3.5).

Each Agent can each select their own model to use and a Network can select a default model.

import { openai, anthropic, gemini } from "@inngest/agent-kit";

How to use a model

Create a model instance

import { openai, createAgent } from "@inngest/agent-kit";


const model = openai({ model: "gpt-3.5-turbo" });
const modelWithApiKey = openai({ model: "gpt-3.5-turbo", apiKey: "sk-..." });

import { anthropic, createAgent } from "@inngest/agent-kit";


const model = anthropic({ model: "claude-3-5-haiku-latest" });

const modelWithBetaFlags = anthropic({
  model: "claude-3-5-haiku-latest",
  betaHeaders: ["prompt-caching-2024-07-31"],
});

const modelWithApiKey = anthropic({
  model: "claude-3-5-haiku-latest",
  apiKey: "sk-...",
  // Note: max_tokens is required for Anthropic models
  defaultParameters: { max_tokens: 4096 },
});

import { gemini, createAgent } from "@inngest/agent-kit";

const model = gemini({ model: "gemini-1.5-flash" });

Configure model hyper parameters (temperature, etc.)

You can configure the model hyper parameters (temperature, etc.) by passing the defaultParameters option:

import { openai, createAgent } from "@inngest/agent-kit";

const model = openai({
  model: "gpt-3.5-turbo",
  defaultParameters: { temperature: 0.5 },
});

import { anthropic, createAgent } from "@inngest/agent-kit";

const model = anthropic({
  model: "claude-3-5-haiku-latest",
  defaultParameters: { temperature: 0.5, max_tokens: 4096 },

});

import { gemini, createAgent } from "@inngest/agent-kit";


const model = gemini({
  model: "gemini-1.5-flash",
  defaultParameters: { temperature: 0.5 },
});

Providing a model instance to an Agent

import { createAgent } from "@inngest/agent-kit";

const supportAgent = createAgent({
  model: openai({ model: "gpt-3.5-turbo" }),
  name: "Customer support specialist",
  system: "You are an customer support specialist...",
  tools: [listChargesTool],
});

Providing a model instance to a Network

import { createNetwork } from "@inngest/agent-kit";

const network = createNetwork({
  agents: [supportAgent],
  defaultModel: openai({ model: "gpt-4o" }),
});

List of supported models

For a full list of supported models, you can always check the models directory here.

"gpt-4.5-preview"
"gpt-4o"
"chatgpt-4o-latest"
"gpt-4o-mini"
"gpt-4"
"o1"
"o1-preview"
"o1-mini"
"o3-mini"
"gpt-4-turbo"
"gpt-3.5-turbo"

"claude-3-5-haiku-latest"
"claude-3-5-haiku-20241022"
"claude-3-5-sonnet-latest"
"claude-3-5-sonnet-20241022"
"claude-3-5-sonnet-20240620"
"claude-3-opus-latest"
"claude-3-opus-20240229"
"claude-3-sonnet-20240229"
"claude-3-haiku-20240307"
"claude-2.1"
"claude-2.0"
"claude-instant-1.2";

"gemini-1.5-flash"
"gemini-1.5-flash-8b"
"gemini-1.5-pro"
"gemini-1.0-pro"
"text-embedding-004"
"aqa"

"grok-2-1212"
"grok-2"
"grok-2-latest"
"grok-3"
"grok-3-latest"
"grok-4"
"grok-4-latest"

Environment variable used for each model provider

OpenAI: OPENAI_API_KEY
Anthropic: ANTHROPIC_API_KEY
Gemini: GEMINI_API_KEY
Grok: XAI_API_KEY

Contribution

Is there a model that you’d like to see included in AgentKit? Open an issue, create a pull request, or chat with the team on Discord in the #ai channel.

Contribute on GitHub - Fork, clone, and open a pull request.