# Use managed mode (/en/ai/platform/build/managed-mode) > For AI agents: see the complete documentation index at [llms.txt](/llms.txt). > Documentation: Conversational AI. > Documentation version: Preview. > This document describes only this version. [Version index](/llms/doc-versions-convoai-guides-v2.txt). Managed mode lets your agent use supported ASR, LLM, and TTS models without your own provider accounts or API keys. Agora provides access to the models. You choose the vendor and model to use for ASR, LLM, and TTS, or let the Platform select them. To use your own provider accounts instead, see [Use your own provider keys (BYOK)](/en/ai/platform/build/use-your-own-keys). ## Understand the tech An agent has ASR, LLM, and TTS models. To use managed mode for a model, choose a vendor and model from [Supported vendors and models](#supported-vendors-and-models), and don't provide a provider API key. You choose the credential mode for each model. For example, an agent can use managed ASR and TTS with your own LLM key. For details, see [Use your own provider keys](/en/ai/platform/build/use-your-own-keys). For a complete agent example, see [Create an agent](/en/ai/platform/get-started/start-stop-agent#create-an-agent). ## Choose managed models Set the managed models when you create an agent. This example uses Deepgram Nova 3 for ASR, OpenAI GPT-4.1 Mini for the LLM, and OpenAI TTS-1 for TTS. The SDK examples use the `client` that you create in [Prerequisites](/en/ai/platform/get-started/start-stop-agent#prerequisites). **Python SDK** Create each model without an API key: ```python from agora_agent import Agent, DeepgramSTT, OpenAI, OpenAITTS agent = ( Agent(client=client) .with_stt(DeepgramSTT(model="nova-3", language="en-US")) .with_llm( OpenAI( model="gpt-4.1-mini", system_messages=[ {"role": "system", "content": "You are a friendly support agent for Acme. Keep your answers short."} ], ) ) .with_tts(OpenAITTS(model="tts-1", voice="alloy")) ) saved_agent = agent.save(name="Support agent") ``` **TypeScript SDK** Create each model without an API key: ```ts import { Agent, DeepgramSTT, OpenAI, OpenAITTS } from 'agora-agents'; const agent = new Agent({ client }) .withStt(new DeepgramSTT({ model: 'nova-3', language: 'en-US' })) .withLlm( new OpenAI({ model: 'gpt-4.1-mini', systemMessages: [ { role: 'system', content: 'You are a friendly support agent for Acme. Keep your answers short.' }, ], }), ) .withTts(new OpenAITTS({ model: 'tts-1', voice: 'alloy' })); const savedAgent = await agent.save({ name: 'Support agent' }); ``` **Go SDK** Create each model without an API key: ```go agent := agentkit.NewAgent(client). WithStt(vendors.NewDeepgramSTT(vendors.DeepgramSTTOptions{Model: "nova-3", Language: "en-US"})). WithLlm(vendors.NewOpenAI(vendors.OpenAIOptions{ Model: "gpt-4.1-mini", SystemMessages: []map[string]interface{}{ {"role": "system", "content": "You are a friendly support agent for Acme. Keep your answers short."}, }, })). WithTts(vendors.NewOpenAITTS(vendors.OpenAITTSOptions{Model: "tts-1", Voice: "alloy"})) savedAgent, err := agent.Save(ctx, agentkit.SaveOptions{Name: "Support agent"}) if err != nil { log.Fatal(err) } ``` **REST API** Send a request to [Create an agent](/en/api-reference/api-ref/conversational-ai/platform/create-agent) with a `pipeline`: ```bash curl --request POST \ --url https://preview.ai.agora.io/conversational-ai/v1/projects//agents \ --header 'Authorization: Basic ' \ --header 'Content-Type: application/json' \ --data ' { "agent_name": "Support agent", "instructions": "You are a friendly support agent for Acme. Keep your answers short.", "pipeline": { "mode": "cascaded", "asr": { "credential": { "mode": "managed" }, "vendor": "deepgram", "model": "nova-3", "language": "en-US" }, "llm": { "credential": { "mode": "managed" }, "vendor": "openai", "style": "openai", "model": "gpt-4.1-mini" }, "tts": { "credential": { "mode": "managed" }, "vendor": "openai", "params": { "model": "tts-1", "voice": "alloy" } } } }' ``` In this example: - Each block sets `credential.mode` to `managed`. A managed block doesn't accept `fields` or a custom provider endpoint `url`. - The `asr` block uses Deepgram Nova 3 for US English. - The `llm` block uses OpenAI GPT-4.1 Mini. - The `tts` block uses OpenAI TTS-1, with the voice in `params`. You then start sessions with the agent as usual. For details, see [Start a session](/en/ai/platform/get-started/start-stop-agent#start-a-session). ## Supported vendors and models The following vendors and models are available in managed mode. ### ASR | Vendor | Models | | ----------------------------------------------- | ------------------- | | [ARES](/en/ai/platform/models/asr/ares) | Built-in ASR engine | | [Deepgram](/en/ai/platform/models/asr/deepgram) | `nova-2`, `nova-3` | ### LLM | Vendor | Models | | ------------------------------------------- | ------------------------------------------------------------------------- | | [OpenAI](/en/ai/platform/models/llm/openai) | `gpt-4o-mini`, `gpt-4.1-mini`, `gpt-5-nano`, `gpt-5-mini`, `gpt-5.6-luna` | ### TTS | Vendor | Models | | --------------------------------------------- | -------------------------------------- | | [MiniMax](/en/ai/platform/models/tts/minimax) | `speech-2.6-turbo`, `speech-2.8-turbo` | | [OpenAI](/en/ai/platform/models/tts/openai) | `tts-1` | ## Reference For more information, see the following pages: - [Use your own provider keys](/en/ai/platform/build/use-your-own-keys) - [Create an agent and start a session](/en/ai/platform/get-started/start-stop-agent) - For the settings each vendor supports, see the vendor pages under Models, for example [Deepgram](/en/ai/platform/models/asr/deepgram), [OpenAI](/en/ai/platform/models/llm/openai), and [MiniMax](/en/ai/platform/models/tts/minimax). ### API reference - [Create an agent](/en/api-reference/api-ref/conversational-ai/platform/create-agent) - [Update an agent](/en/api-reference/api-ref/conversational-ai/platform/update-agent)