> ## Documentation Index
> Fetch the complete documentation index at: https://www.bolna.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Choosing an LLM

> How to pick the right language model for your Bolna agent based on quality, latency and data-residency needs.

The LLM decides what the agent says. Quality tier and latency are the primary selection factors. See each provider's page for current model names.

<Note>
  Provider model lineups change frequently. The specific model names here are current examples — always check the relevant [LLM provider page](/docs/language-models) or the provider's own docs for the latest recommended model.
</Note>

| Tier | When to use | Examples |
| - | - | - |
| **Fast / cost-efficient** | Most agents — lead qualification, reminders, scheduling, FAQs | `gpt-5.4-mini`, `gemini-2.5-flash`, `deepseek-v4-flash` |
| **High quality** | Complex reasoning, financial/medical, sensitive conversations | `gpt-5.4`, `gpt-5.5`, `claude-sonnet-5` |
| **Enterprise** | Data residency requirements | Azure OpenAI |
| **Custom / self-hosted** | On-premise or proprietary models | [Custom LLM](/docs/custom) |

**LLM provider pages:**

<CardGroup cols={3}>
  <Card title="OpenAI" icon="o" href="/docs/openai-llm">
    GPT-5.4-mini, GPT-5.4, GPT-5.5
  </Card>

  <Card title="Anthropic" icon="a" href="/docs/anthropic">
    Claude Sonnet 5, Haiku 4.5, Opus 4.8
  </Card>

  <Card title="Google Gemini" icon="g" href="/docs/gemini-llm">
    Gemini 2.5 Flash, Gemini 3.x
  </Card>

  <Card title="Azure OpenAI" icon="microsoft" href="/docs/azure-openai">
    GPT-5.x via Azure infrastructure
  </Card>

  <Card title="DeepSeek" icon="d" href="/docs/deepseek">
    DeepSeek V4 Flash, V4 Pro
  </Card>

  <Card title="OpenRouter" icon="r" href="/docs/openrouter">
    Unified gateway — all providers
  </Card>
</CardGroup>

***

## Next steps

<CardGroup cols={2}>
  <Card title="LLM providers" icon="brain" href="/docs/language-models">
    Setup guides for every LLM provider
  </Card>

  <Card title="Bring your own model" icon="server" href="/docs/custom">
    Connect a custom or self-hosted LLM
  </Card>

  <Card title="Choose a voice" icon="volume-high" href="/docs/concepts/choosing-text-to-speech">
    The next provider in the pipeline
  </Card>

  <Card title="Back to the decision guide" icon="sliders" href="/docs/concepts/choosing-providers">
    Compare all provider categories side by side
  </Card>
</CardGroup>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.