# OpenRouter

Access Claude, Mistral, LLaMA, and dozens of other models through one OpenRouter API key on Bolna. Switch models anytime without reconfiguring your agents.

## How OpenRouter fits in the stack

**Best for**

Reasoning, policy handling, tool use, and response generation.

**Use this layer when**

You want to tune quality, cost, latency, or function-calling behavior.

**Connects to**

Transcribed caller input upstream and voice or actions downstream.

## The LLM is the reasoning layer

This provider decides how the agent interprets intent, selects next actions, calls tools, and formulates responses. It is the decision engine inside the voice stack.

**Telephony Phone Network**

→ **STT Listener**

→ **LLM Reasoning**

→ **TTS Voice**

→ **Tools Actions**

This page focuses on where OpenRouter fits in a production voice stack. For full setup steps, credentials, and API details, use the documentation link above.

# Overview

OpenRouter provides unified access to many of leading language models through a single API interface. With Bolna's OpenRouter integration, you can access Claude, GPT-4, Mistral, LLaMA, and many other models without managing multiple API keys or integrations.

OpenRouter is ideal for the teams that want flexibility to experiment with different models, change providers based on availability or pricing, or use multiple models for different scenarios, all possible through one integration.

## Features & Use Cases

**All the Best AI Models in One Place**

Use top models like Claude, GPT-4, Mistral, LLaMA, and Gemini through a single connection, so you don't have to juggle multiple accounts.

**Easy to Switch & Choose**

Swap between different AI models instantly to find the best mix of cost, speed, and quality without changing any code.

**Never Go Offline (Automatic Backup)**

If your favorite AI model goes down or gets too busy, OpenRouter automatically switches to a backup model so your calls never fail.

**Clear & Simple Pricing**

Easily see exactly what each model costs in real-time so you can stay right on budget.

**Always Stay Flexible**

Don't get stuck with just one company. Easily switch to the newest and best AI as soon as it comes out.

**Use Case: Finding the Perfect Match**

Easily test out different AI models side by side to see which one works best and costs the least for your specific needs.

**Use Case: Guaranteed Uptime**

Perfect for important support lines. With automatic backups, your voice agents will always answer the phone even if a major AI provider crashes.

**Use Case: Saving Money on Calls**

Automatically send simple questions to cheaper AI models while saving the expensive models for only the hardest problems.

# Other providers in this layer

- **Anthropic**: Connect Anthropic Claude to your Bolna voice agents for smart, natural conversations. Handles complex multi-turn dialogue with 200K token context windows.
- **Azure OpenAI**: Run OpenAI models on Azure with Bolna voice agents. Get enterprise compliance, SLAs, and data residency while powering intelligent phone conversations.
- **DeepSeek**: Use DeepSeek with Bolna voice agents for strong reasoning at a fraction of the cost. Great for high-volume voice automation where every token counts.

## See where OpenRouter fits in your production workflow

Use the demo to walk through provider selection, stack tradeoffs, and the exact workflow you want Bolna to automate.