OpenAI

Accédez à 47 modèles OpenAI via le routeur de modèles de Mastra. L’authentification est gérée automatiquement à l’aide de la variable d’environnement OPENAI_API_KEY.

Pour en savoir plus, consultez la documentation OpenAI.

.env

OPENAI_API_KEY=your-api-key

src/mastra/agents/my-agent.ts

import { Agent } from "@mastra/core/agent";

const agent = new Agent({
  id: "my-agent",
  name: "My Agent",
  instructions: "You are a helpful assistant",
  model: "openai/chatgpt-image-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);
}

Modèles

37 available models

Model	Context	Tools	Reasoning	Image	Audio	Video	Input $/1M	Output $/1M
openai/chatgpt-image-latest	—						—	—
openai/gpt-4.1	1.0M						$2	$8
openai/gpt-4.1-mini	1.0M						$0.40	$2
openai/gpt-4o	128K						$3	$10
openai/gpt-4o-2024-08-06	128K						$3	$10
openai/gpt-4o-2024-11-20	128K						$3	$10
openai/gpt-4o-mini	128K						$0.15	$0.60
openai/gpt-5	400K						$1	$10
openai/gpt-5-mini	400K						$0.25	$2
openai/gpt-5-nano	400K						$0.05	$0.40
openai/gpt-5-pro	400K						$15	$120
openai/gpt-5.1	400K						$1	$10
openai/gpt-5.2	400K						$2	$14
openai/gpt-5.2-chat-latest	128K						$2	$14
openai/gpt-5.2-pro	400K						$21	$168
openai/gpt-5.3-chat-latest	128K						$2	$14
openai/gpt-5.3-codex	400K						$2	$14
openai/gpt-5.3-codex-spark	128K						$2	$14
openai/gpt-5.4	1.1M						$3	$15
openai/gpt-5.4-mini	400K						$0.75	$5
openai/gpt-5.4-nano	400K						$0.20	$1
openai/gpt-5.4-pro	1.1M						$30	$180
openai/gpt-5.5	1.1M						$5	$30
openai/gpt-5.5-pro	1.1M						$30	$180
openai/gpt-5.6	1.1M						$5	$30
openai/gpt-5.6-luna	1.1M						$0.20	$1
openai/gpt-5.6-sol	1.1M						$5	$30
openai/gpt-5.6-terra	1.1M						$2	$12
openai/gpt-image-1-mini	—						—	—
openai/gpt-image-1.5	—						—	—
openai/gpt-image-2	—						$5	$30
openai/gpt-realtime-2.1	128K						$4	$24
openai/o3	200K						$2	$8
openai/o3-pro	200K						$20	$80
openai/text-embedding-3-large	8K						$0.13	—
openai/text-embedding-3-small	8K						$0.02	—
openai/text-embedding-ada-002	8K						$0.10	—

Configuration avancée

En-têtes personnalisés

src/mastra/agents/my-agent.ts

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

Sélection dynamique du modèle

src/mastra/agents/my-agent.ts

const agent = new Agent({
  id: "dynamic-agent",
  name: "Dynamic Agent",
  model: ({ requestContext }) => {
    const useAdvanced = requestContext.task === "complex";
    return useAdvanced
      ? "openai/text-embedding-ada-002"
      : "openai/chatgpt-image-latest";
  }
});

Options du Provider

OpenAI prend en charge les options propres au Provider suivantes via le paramètre providerOptions :

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

Options disponibles

conversation?:

string | null | undefined

include?:

("web_search_call.results" | "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

promptCacheOptions?:

{ mode?: "explicit" | "implicit" | undefined; ttl?: "30m" | undefined; } | undefined

promptCacheRetention?:

"in_memory" | "24h" | null | undefined

reasoningEffort?:

string | null | undefined

reasoningMode?:

"standard" | "pro" | undefined

reasoningContext?:

"auto" | "current_turn" | "all_turns" | undefined

reasoningSummary?:

string | null | undefined

safetyIdentifier?:

string | null | undefined

serviceTier?:

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

store?:

boolean | null | undefined

Controls whether OpenAI stores your API requests for model training. Required to be "false" if your organization has zero data retention enabled. See: https://platform.openai.com/docs/guides/your-data#zero-data-retention

passThroughUnsupportedFiles?:

boolean | undefined

strictJsonSchema?:

boolean | null | undefined

textVerbosity?:

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

truncation?:

"auto" | "disabled" | null | undefined

user?:

string | null | undefined

systemMessageMode?:

"remove" | "system" | "developer" | undefined

forceReasoning?:

boolean | undefined

allowedTools?:

{ toolNames: string[]; mode?: "auto" | "required" | undefined; } | undefined

Installation directe du Provider

Ce Provider peut aussi être installé directement comme package autonome, utilisable à la place de la chaîne du routeur de modèles Mastra. Consultez la documentation du package pour plus de détails.

npm

npm install @ai-sdk/openai

pnpm

pnpm add @ai-sdk/openai

Yarn

yarn add @ai-sdk/openai

Bun

bun add @ai-sdk/openai

Pour une documentation détaillée propre au Provider, consultez la documentation du Provider AI SDK OpenAI provider.