DocsAPI ReferenceSDKsCookbookChangelog

For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://modelgates.ai/docs/_mcp/server.

Call Model (Typescript)

Why callModel?

  • Items-Based Model: Built on ModelGates's Responses API with structured items (messages, tool calls, reasoning) instead of raw message chunks
  • Multiple Consumption Patterns: Get text, stream responses, or access structured data - all from a single call
  • Automatic Tool Execution: Define tools with Zod schemas and let the SDK handle execution loops
  • Type Safety: Full TypeScript inference for tool inputs, outputs, and events
  • Format Compatibility: Convert to/from OpenAI chat and Anthropic Claude message formats
  • Streaming First: Built on a reusable stream architecture that supports concurrent consumers

Quick Start

typescript
import { ModelGates } from '@modelgates/agent'; const modelgates = new ModelGates({  apiKey: process.env.MODELGATES_API_KEY,}); const result = modelgates.callModel({  model: 'openai/gpt-5-nano',  input: 'What is the capital of France?',}); // Get text (simplest pattern)const text = await result.getText();console.log(text); // "The capital of France is Paris."

Consumption Patterns

callModel returns a ModelResult object that provides multiple ways to consume the response:

Text Methods

typescript
// Get just the text contentconst text = await result.getText(); // Get the full response with usage dataconst response = await result.getResponse();console.log(response.usage); // { inputTokens, outputTokens, cachedTokens }

Streaming Methods

typescript
// Stream text deltasfor await (const delta of result.getTextStream()) {  process.stdout.write(delta);} // Stream reasoning (for reasoning models)for await (const delta of result.getReasoningStream()) {  console.log('Reasoning:', delta);} // Stream complete items by ID (recommended)for await (const item of result.getItemsStream()) {  console.log('Item update:', item.type, item.id);} // Stream all events (including tool preliminary results)for await (const event of result.getFullResponsesStream()) {  console.log('Event:', event.type);}

Tool Methods

typescript
// Get all tool calls from the responseconst toolCalls = await result.getToolCalls(); // Stream tool calls as they completefor await (const toolCall of result.getToolCallsStream()) {  console.log(`Tool: $`, toolCall.arguments);} // Stream tool deltas and preliminary resultsfor await (const event of result.getToolStream()) {  if (event.type === 'delta') {    process.stdout.write(event.content);  } else if (event.type === 'preliminary_result') {    console.log('Progress:', event.result);  }}

Input Formats

callModel accepts multiple input formats:

typescript
// Simple stringconst result1 = modelgates.callModel({  model: 'openai/gpt-5-nano',  input: 'Hello!',}); // Message array (OpenResponses format)const result2 = modelgates.callModel({  model: 'openai/gpt-5-nano',  input: [    { role: 'user', content: 'Hello!' },  ],}); // With system instructionsconst result3 = modelgates.callModel({  model: 'openai/gpt-5-nano',  instructions: 'You are a helpful assistant.',  input: 'Hello!',});

What's Next?

Explore the guides to learn more about specific features:

Example Tools

Ready-to-use tool implementations: