Last updated
What is Perplexity used for in a Bolna voice agent?
Perplexity can serve as the LLM in a Bolna voice agent: you set the agent's LLM provider to perplexity, and Bolna routes each turn through LiteLLM to the Perplexity model ID you choose. Pick it if your team already works with Perplexity models; for most new agents the Bolna docs recommend starting with OpenAI gpt-5.4-mini.
How do I set up Perplexity with Bolna?
- In the Bolna dashboard, open Settings → Integrations, filter by LLM and connect your Perplexity account.
- In the agent config sent to the create agent API, set the LLM provider to
perplexity. - Set the model to a Perplexity model ID taken from Perplexity's own documentation.
- Place a test call to confirm the model responds, since an invalid model ID only fails once a call runs.
The LLM provider list is in the create agent API reference in the Bolna docs.
What does Bolna support with Perplexity?
| Item | What the Bolna docs say |
|---|---|
| Provider value | perplexity, set on the agent's LLM config |
| Routing | Through LiteLLM, using Perplexity's own model IDs |
| Recommended model | None listed in the Bolna docs |
| Dedicated docs page | None; listed with Groq, Cohere, Together and others as a LiteLLM-routed provider |
| Account connection | Perplexity card under Settings → Integrations |
| Validation | Provider and model are not checked at agent creation; errors show up on the call |
| Billing | Not on the preferred model list, so the LLM is billed by usage |
What can you build with Perplexity and Bolna?
Model trials. Run a test agent on a Perplexity model and compare its replies and latency with gpt-5.4-mini before moving real traffic.
Agents on a vendor you already use. Keep your voice agents on the same LLM vendor as the rest of your product, connected through your own Perplexity account.
Scripted reminder and follow-up calls. Once a test call confirms your model ID works, run short, predictable outbound calls on a Perplexity model.