Skip to main content

OpenAI logoOpenAI

Access 31 OpenAI models through Mastra's model router. Authentication is handled automatically using the OPENAI_API_KEY environment variable.

Learn more in the OpenAI documentation.

OPENAI_API_KEY=your-api-key
import { Agent } from "@mastra/core";

const agent = new Agent({
  name: "my-agent",
  instructions: "You are a helpful assistant",
  model: "openai/codex-mini-latest"
});

// Generate a response
const response = await agent.generate("Hello!");

// Stream a response
const stream = await agent.stream("Tell me a story");
for await (const chunk of stream) {
  console.log(chunk);
}

Models​

ModelImageAudioVideoToolsStreamingContext Window
openai/codex-mini-latest✗✗✗✓✗200,000
openai/gpt-3.5-turbo✗✗✗✗✗16,385
openai/gpt-4✗✗✗✓✗8,192
openai/gpt-4-turbo✓✗✗✓✗128,000
openai/gpt-4.1✓✗✗✓✗1,047,576
openai/gpt-4.1-mini✓✗✗✓✗1,047,576
openai/gpt-4.1-nano✓✗✗✓✗1,047,576
openai/gpt-4o✓✗✗✓✗128,000
openai/gpt-4o-2024-05-13✓✗✗✓✗128,000
openai/gpt-4o-2024-08-06✓✗✗✓✗128,000
openai/gpt-4o-2024-11-20✓✗✗✓✗128,000
openai/gpt-4o-mini✓✗✗✓✗128,000
openai/gpt-5✓✗✗✓✗400,000
openai/gpt-5-chat-latest✓✗✗✗✗400,000
openai/gpt-5-codex✓✗✗✓✗400,000
openai/gpt-5-mini✓✗✗✓✗400,000
openai/gpt-5-nano✓✗✗✓✗400,000
openai/gpt-5-pro✓✗✗✓✗400,000
openai/o1✓✗✗✓✗200,000
openai/o1-mini✗✗✗✗✗128,000
openai/o1-preview✗✗✗✗✗128,000
openai/o1-pro✓✗✗✓✗200,000
openai/o3✓✗✗✓✗200,000
openai/o3-deep-research✓✗✗✓✗200,000
openai/o3-mini✗✗✗✓✗200,000
openai/o3-pro✓✗✗✓✗200,000
openai/o4-mini✓✗✗✓✗200,000
openai/o4-mini-deep-research✓✗✗✓✗200,000
openai/text-embedding-3-large✗✗✗✗✗8,191
openai/text-embedding-3-small✗✗✗✗✗8,191
openai/text-embedding-ada-002✗✗✗✗✗8,192

Advanced Configuration​

Custom Headers​

const agent = new Agent({
  name: "custom-agent",
  model: {
    id: "openai/codex-mini-latest",
    apiKey: process.env.OPENAI_API_KEY,
    headers: {
      "X-Custom-Header": "value"
    }
  }
});

Dynamic Model Selection​

const agent = new Agent({
  name: "dynamic-agent",
  model: ({ runtimeContext }) => {
    const useAdvanced = runtimeContext.task === "complex";
    return useAdvanced
      ? "openai/text-embedding-ada-002"
      : "openai/codex-mini-latest";
  }
});

Provider Options​

OpenAI supports the following provider-specific options via the providerOptions parameter:

const response = await agent.generate("Hello!", {
  providerOptions: {
    openai: {
      // See available options in the table below
    }
  }
});

Available Options​

include?:

("file_search_call.results" | "message.output_text.logprobs" | "reasoning.encrypted_content")[] | null | undefined

instructions?:

string | null | undefined

logprobs?:

number | boolean | undefined

maxToolCalls?:

number | null | undefined

metadata?:

any

parallelToolCalls?:

boolean | null | undefined

previousResponseId?:

string | null | undefined

promptCacheKey?:

string | null | undefined

reasoningEffort?:

string | null | undefined

reasoningSummary?:

string | null | undefined

safetyIdentifier?:

string | null | undefined

serviceTier?:

"default" | "auto" | "flex" | "priority" | null | undefined

store?:

boolean | null | undefined

strictJsonSchema?:

boolean | null | undefined

textVerbosity?:

"low" | "medium" | "high" | null | undefined

truncation?:

"auto" | "disabled" | null | undefined

user?:

string | null | undefined

Direct Provider Installation​

This provider can also be installed directly as a standalone package, which can be used instead of the Mastra model router string. View the package documentation for more details.

npm install @ai-sdk/openai

For detailed provider-specific documentation, see the AI SDK OpenAI provider docs.