> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.meetstream.ai/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.meetstream.ai/_mcp/server.

# Voice agent pricing and keys

> MeetStream agent pricing: a bridge server on your own stack costs the bot price only. Your own agent through the Agent Kit, or a managed voice agent (MIA) with MeetStream's inbuilt keys or your own keys, adds $0.25 per hour for the agent infrastructure.

An agent in a meeting always runs on a MeetStream bot. What you pay on top of the bot depends on who runs the agent. The setups follow the [three ways to integrate](/guides/introduction/integration-paths): your own stack first, then the managed agent (API name: **MIA**).

| Setup                                            | What you do                                                                                                                                                   | Price per meeting hour                                                                                  |
| ------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------- |
| **2a. Bridge server** (your own stack)           | Your server gets the live audio and sends audio, chat and images back over two WebSockets. You run any speech-to-text, LLM and voice, including local models. | Bot price only. No agent infrastructure fee and no model tokens.                                        |
| **2b. Your own agent** (Agent Kit)               | Your agent (Claude Code, Codex, Hermes, OpenClaw and others) runs on your own subscription and writes what the voice agent says.                              | Bot price + \$0.25 agent infrastructure. MeetStream charges no model tokens for your agent's reasoning. |
| **3a. Managed agent, MeetStream's inbuilt keys** | Pick the speech-to-text, LLM and voice models. You need no provider account.                                                                                  | Bot price + \$0.25 agent infrastructure + the per-hour price of the models that you pick.               |
| **3b. Managed agent, your own keys**             | Add your provider keys under **Integrations**, then pick any supported provider and model.                                                                    | Bot price + \$0.25 agent infrastructure. Your provider bills you for model usage.                       |

The bot price is **$0.35 per hour** (**$0.25 per hour** at volume). If the bot also makes a post-call transcript with the [MeetStream engine](/guides/transcription-recordings/providers/meetstream), add $0.10 per hour. With your own transcription provider key, that $0.10 is waived.

In a managed agent you can mix setups 3a and 3b: each pipeline section (`transcriber`, `model`, `voice`) uses either an inbuilt key or your own key.

---

## 2a. Bridge server

Use a bridge server when you want to run every model yourself, hosted or local (for example Parakeet for speech-to-text, a local LLM and a local text-to-speech model). The bot opens two WebSockets to your server: `live_audio_required.websocket_url` for the live audio and `socket_connection_url.websocket_url` for the control socket. You do not create a MIA agent.

**Price.** Bot price only. MeetStream charges no agent infrastructure and no model tokens.

See [Bridge Server Architecture](/guides/websockets/bridge-server-architecture) and the open-source starter [meetstream-ai/meetstream-agent](https://github.com/meetstream-ai/meetstream-agent).

---

## 2b. Your own agent

Use your own agent when you already run an agent (Claude Code, Codex, Hermes, OpenClaw, GitHub Copilot CLI and others) on your own subscription, and you want it to be the brain of the voice agent. MIA still joins the call, listens and speaks. Your agent writes the answers. Set `model.provider` to `"local_agent"` and connect your agent with the open-source [MeetStream Agent Kit](https://github.com/meetstream-ai/agent-kit).

**Price.** Bot price + \$0.25 per hour for the agent infrastructure. MeetStream charges no model tokens for your agent's reasoning: your agent uses your own subscription. Speech-to-text and voice work as for any other agent: with your own keys your provider bills you, and with inbuilt keys you pay the per-hour price of those models.

> **Warning**
>
> **Use this setup with care.** What people say and type in the meeting reaches an agent that has access to your computer and your terminal. Someone in the meeting can try to give your agent instructions (prompt injection). Keep the access level as low as possible: `readonly` is the default. Keep the activation code on. Your computer, your agent and the bridge must stay on for the whole call.

```bash
curl -X POST https://api.meetstream.ai/api/v1/mia \
  -H "Authorization: Token <YOUR_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "agent_name": "My agent in the meeting",
    "mode": "pipeline",
    "model": {
      "provider": "local_agent",
      "local_agent": {
        "url": "https://<your-tunnel-host>",
        "label": "Claude Code",
        "access": "readonly",
        "require_code": true
      }
    },
    "transcriber": { "provider": "deepgram", "model": "nova-3", "language": "en" },
    "voice": { "provider": "elevenlabs", "voice_id": "<YOUR_ELEVENLABS_VOICE_ID>" }
  }'
```

`model.model` and `model.system_prompt` are optional for `local_agent`. `transcriber` and `voice` are required. For the bridge setup, the pairing token, the activation code, the access levels and the connection test, see [MIA Screen Sharing and Custom Agents](/guides/features/mia-screen-sharing-and-custom-agents#4-your-agent-bring-claude-code-codex-and-more).

---

## 3a. Managed agent: MeetStream's inbuilt keys

Use MeetStream's inbuilt keys when you do not want to open accounts with model providers. Today the inbuilt keys cover:

* **OpenAI**: the LLM, and OpenAI speech-to-text and voice models.
* **Deepgram**: speech-to-text.

For any other provider, add your own key (setup 3b).

**Price.** Bot price + \$0.25 per hour for the agent infrastructure + the per-hour price of each model that you pick. If you pick only the LLM with an inbuilt key, you pay only for that model. The agent editor in the dashboard shows the per-hour price of your choices before the bot runs. MeetStream charges that rate for the time the bot is in the meeting.

### Request shape

Set `"key_source": "meetstream"` on each pipeline section that uses an inbuilt key. Do not send `api_key` in that section.

| `key_source`                       | Meaning                                                                                                                      |
| ---------------------------------- | ---------------------------------------------------------------------------------------------------------------------------- |
| `"meetstream"`                     | The section uses MeetStream's inbuilt key. Pipeline mode only.                                                               |
| `"user"`, or the field is not sent | The section uses your own key from **Integrations** (setup 3b). This is the behaviour of agents created before inbuilt keys. |

Create an agent that uses inbuilt keys for all three sections:

```bash
curl -X POST https://api.meetstream.ai/api/v1/mia \
  -H "Authorization: Token <YOUR_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "agent_name": "Meeting assistant (inbuilt keys)",
    "mode": "pipeline",
    "transcriber": {
      "provider": "deepgram",
      "model": "nova-3",
      "language": "en",
      "key_source": "meetstream"
    },
    "model": {
      "provider": "openai",
      "model": "gpt-4o-mini",
      "system_prompt": "You are a concise meeting assistant. Answer questions and track action items.",
      "key_source": "meetstream"
    },
    "voice": {
      "provider": "openai",
      "model": "tts-1",
      "voice_id": "nova",
      "key_source": "meetstream"
    }
  }'
```

Then send a bot with the `agent_config_id` from the response:

```bash
curl -X POST https://api.meetstream.ai/api/v1/bots/create_bot \
  -H "Authorization: Token <YOUR_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "meeting_link": "https://meet.google.com/abc-defg-hij",
    "bot_name": "Assistant",
    "agent_config_id": "<AGENT_CONFIG_ID>"
  }'
```

The models that you can use with inbuilt keys can change. If you pick a model that has no inbuilt-key price, the API returns `400` with the models that you can use (see [Errors](#errors)). The dashboard agent editor shows the same list.

### When inbuilt keys are not available on your account

Inbuilt keys may not be available on your account yet. Then `POST /api/v1/mia` and `PUT /api/v1/mia` return `400`:

```json
{ "message": "MeetStream-managed keys are not available for transcriber. Use your own key." }
```

The message names the section: `transcriber`, `model` or `voice`. If you send a bot with a saved agent that uses inbuilt keys, `create_bot` returns `400` with a message that names the sections, for example `MeetStream-managed keys are turned off. Edit the agent to use your own keys for: transcriber, model.` To fix it:

1. Add your provider key in the dashboard under **Configure > Integrations** (tabs **Models**, **Voice** and **Transcription**).
2. In that section, remove `key_source` (or set it to `"user"`).
3. Send the request again. Do not retry the same request in a loop: it gets the same answer.

---

## 3b. Managed agent: bring your own keys

Use your own keys when you want a provider or a model that the inbuilt keys do not cover, or when you want the provider to bill you directly. You can pick any provider in the [MIA API Guide](/guides/mia/mia-api-guide), for example OpenAI, Anthropic, Google, xAI, Deepgram, AssemblyAI and ElevenLabs.

**Price.** Bot price + \$0.25 per hour for the agent infrastructure. Your provider bills you for model usage on your own account.

1. Add each provider key in the dashboard under **Configure > Integrations** (tabs **Models**, **Voice** and **Transcription**). The agent configuration holds provider names and settings, never the keys.
2. Create the agent without `key_source` (or with `"key_source": "user"`). This works in pipeline mode and in realtime mode.

```bash
curl -X POST https://api.meetstream.ai/api/v1/mia \
  -H "Authorization: Token <YOUR_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "agent_name": "Meeting assistant (own keys)",
    "mode": "pipeline",
    "transcriber": { "provider": "deepgram", "model": "nova-3", "language": "en" },
    "model": {
      "provider": "anthropic",
      "model": "claude-sonnet-5-5",
      "system_prompt": "You are a concise meeting assistant. Answer questions and track action items."
    },
    "voice": { "provider": "elevenlabs", "voice_id": "<YOUR_ELEVENLABS_VOICE_ID>" }
  }'
```

If a provider key is missing, the API returns `400` `API key not configured for: ...`. Add the key under **Integrations**, or use an inbuilt key for that section.

---

## Errors

These `400` errors are about keys. The body is `{ "message": "..." }`.

| Message                                                                                                    | Cause                                                                   | Fix                                                                                                    |
| ---------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------ |
| `MeetStream-managed keys are not available for <section>. Use your own key.`                               | Inbuilt keys are not available on your account for that section.        | Use your own key for that section (see [above](#when-inbuilt-keys-are-not-available-on-your-account)). |
| `MeetStream-managed keys are available only in pipeline mode.`                                             | `key_source: "meetstream"` in a realtime agent.                         | Use `mode: "pipeline"`, or your own key in realtime mode.                                              |
| `<section>.key_source must be one of: user, meetstream.`                                                   | Another value in `key_source`.                                          | Send `"meetstream"` or `"user"`, or leave the field out.                                               |
| `<section>.api_key must be empty when <section>.key_source is "meetstream".`                               | The section has an inbuilt key and an `api_key`.                        | Remove `api_key` from that section.                                                                    |
| `<section>.provider '<provider>' has no MeetStream key. Use one of: ...`                                   | The inbuilt keys do not cover that provider.                            | Pick a provider from the list, or use your own key.                                                    |
| `<section>.model '<model>' has no MeetStream price. Use one of: ...`                                       | That model is not offered with inbuilt keys.                            | Pick a model from the list, or use your own key.                                                       |
| `API key not configured for: ...`                                                                          | Your own key for that provider is not saved.                            | Add the key under **Integrations**, or use an inbuilt key for that section.                            |
| `MeetStream-managed keys are turned off. Edit the agent to use your own keys for: ...` (from `create_bot`) | A saved agent uses inbuilt keys, and inbuilt keys are not available.    | Edit the agent to use your own keys for the sections in the message.                                   |
| `MeetStream no longer offers <provider> <model> for <section>. ...` (from `create_bot`)                    | A saved agent uses a model that is no longer offered with inbuilt keys. | Edit the agent to pick another model, or use your own key.                                             |

To check your prepaid balance and add credit, go to [app.meetstream.ai/billing](https://app.meetstream.ai/billing). The read-only [`GET /api/v1/billing/balance`](/api-reference/api-endpoints/billing/get-balance) endpoint is rolling out: until it is enabled for your account, it returns `404`.

## Related

* [What is MIA?](/guides/mia/what-is-mia): modes, providers and features.
* [Create an Agent](/guides/mia/create-an-agent): set up an agent in the dashboard.
* [MIA API Guide](/guides/mia/mia-api-guide): every field of the agent configuration.
* [MIA Screen Sharing and Custom Agents](/guides/features/mia-screen-sharing-and-custom-agents): screen tools, the bot desktop and your own agent.
* [Three ways to integrate](/guides/introduction/integration-paths): recording only, your own stack, or a managed agent.