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.
Perplexity decides how the agent reads intent, picks the next action, calls your tools and writes the reply. It's the decision engine inside the call.
Telephony
Phone network
STT
Listener
LLM · You are here
Reasoning
TTS
Voice
Tools
Actions
Connectors for this stage
Large Language Models
| 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 |
The LLM provider list is in the create agent API reference in the Bolna docs.
Run a test agent on a Perplexity model and compare its replies and latency with gpt-5.4-mini before moving real traffic.
Keep your voice agents on the same LLM vendor as the rest of your product, connected through your own Perplexity account.
Once a test call confirms your model ID works, run short, predictable outbound calls on a Perplexity model.
Simplismart serves speed-optimised open models to a Bolna voice agent on a shared endpoint or a dedicated deployment, including your own fine-tuned weights.
Together AI gives a Bolna voice agent a large serverless catalog of open models such as Llama, Qwen, DeepSeek and MiniMax, billed per token with no provisioning.
Anthropic Claude writes your Bolna voice agent's replies. Use claude-sonnet-5 for most agents, or claude-haiku-4-5 for faster, high-volume calls.
Understands callers and decides the reply.
18 providersConnects agents to the phone network.
14 providersTurns caller speech into text in real time.
10 providersTurns replies into natural speech.
12 providersLets agents act during and after calls.
7 providersWalk through provider choice, stack trade-offs and the exact workflow you want Bolna to automate.
Secure, compliant and dependable, from the first pilot to full scale.
Built for your busiest hour. Even if the model fails, the call doesn’t
A dedicated team, with service levels shaped around your business
Data residency, encryption, access controls, full audit trails and more
Run Bolna in your own cloud or on-premise, your data remains yours
Certified by
