---
title: Models | Letta Docs
description: The Letta API supports all major frontier model providers
---

Select models shown below - for a complete model list with current pricing, see [app.letta.com/models](https://app.letta.com/models).

| Model                                                  | Provider  | Max Context | Vision Support? |
| ------------------------------------------------------ | --------- | ----------- | --------------- |
| ![](/images/providers/anthropic.svg) Claude Opus 4.6   | Anthropic | 200k        | ✓               |
| ![](/images/providers/anthropic.svg) Claude Opus 4.5   | Anthropic | 200k        | ✓               |
| ![](/images/providers/anthropic.svg) Claude Sonnet 4.5 | Anthropic | 200k        | ✓               |
| ![](/images/providers/anthropic.svg) Claude Haiku 4.5  | Anthropic | 200k        | ✓               |
| ![](/images/providers/openai.svg) GPT-5.2-Codex        | OpenAI    | 272k        | ✓               |
| ![](/images/providers/openai.svg) GPT-5.2              | OpenAI    | 272k        | ✓               |
| ![](/images/providers/google.svg) Gemini 3 Pro         | Google    | 1M          | ✓               |
| ![](/images/providers/google.svg) Gemini 3 Flash       | Google    | 1M          | ✓               |
| ![](/images/providers/zhipu.svg) GLM 4.7               | Z.ai      | 200k        | -               |
| ![](/images/providers/minimax.svg) MiniMax M2.1        | MiniMax   | 180k        | -               |
| ![](/images/providers/moonshot.svg) Kimi K2.5          | Moonshot  | 262k        | ✓               |

## Bring your own keys (BYOK)

Connect your own LLM API keys to use additional models from providers like OpenRouter, or to connect external coding plans. When using BYOK instead of hosted models through the Letta API, you are billed directly by the LLM API provider.

To configure BYOK in Letta Code, use the `/connect` command (see [full docs](/letta-code/models/index.md)). Providers can also be configured via the Letta Platform [models page](https://app.letta.com/models).

---

## Configuring models in the Letta API

In Letta Code, use `/model` to change models.

### Model handles

Models are specified using `provider/model-name` formatted handles:

- [Python](#tab-panel-84)
- [TypeScript](#tab-panel-85)

```
agent = client.agents.create(
    model="anthropic/claude-sonnet-4-5-20250929",
)
```

```
const agent = await client.agents.create({
  model: "anthropic/claude-sonnet-4-5-20250929",
});
```

### Providers

| Provider    | Prefix        | Example                                  |
| ----------- | ------------- | ---------------------------------------- |
| OpenAI      | `openai/`     | `openai/gpt-5.2`                         |
| Anthropic   | `anthropic/`  | `anthropic/claude-sonnet-4-5-20250929`   |
| Google AI   | `google_ai/`  | `google_ai/gemini-3-flash`               |
| Azure       | `azure/`      | `azure/gpt-4o`                           |
| AWS Bedrock | `bedrock/`    | `bedrock/anthropic.claude-3-5-sonnet`    |
| OpenRouter  | `openrouter/` | `openrouter/anthropic/claude-3.5-sonnet` |
| Ollama      | `ollama/`     | `ollama/llama3.2`                        |

### Model settings

Configure temperature, max tokens, and other settings:

- [Python](#tab-panel-86)
- [TypeScript](#tab-panel-87)

```
agent = client.agents.create(
    model="openai/gpt-5.2",
    model_settings={
        "provider_type": "openai",
        "temperature": 0.7,
        "max_output_tokens": 4096,
    },
    context_window_limit=128000
)
```

```
const agent = await client.agents.create({
  model: "openai/gpt-5.2",
  model_settings: {
    provider_type: "openai",
    temperature: 0.7,
    max_output_tokens: 4096,
  },
  context_window_limit: 128000,
});
```

### Reasoning settings

For OpenAI reasoning models (`o1`, `o3`):

```
agent = client.agents.create(
    model="openai/o3-mini",
    model_settings={
        "provider_type": "openai",
        "reasoning": {
            "reasoning_effort": "medium"  # "low", "medium", or "high"
        }
    }
)
```

For Claude extended thinking:

```
agent = client.agents.create(
    model="anthropic/claude-sonnet-4-5-20250929",
    model_settings={
        "provider_type": "anthropic",
        "thinking": {
            "type": "enabled",
            "budget_tokens": 10000
        }
    }
)
```

### Changing models

Update an existing agent’s model:

- [Python](#tab-panel-88)
- [TypeScript](#tab-panel-89)

```
client.agents.update(
    agent_id=agent.id,
    model="openai/gpt-5.2",
    context_window_limit=64000
)
```

```
await client.agents.update(agent.id, {
  model: "openai/gpt-5.2",
  context_window_limit: 64000,
});
```

Agents keep their memory and tools when you change models.