High-volume outbound campaigns
The 2,500 concurrent request limit on deepseek-v4-flash fits large batch campaigns. The Bolna docs pair it with Deepgram Nova-2 for cost-sensitive setups; see the Deepgram integration.
DeepSeek 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
Get an API key from DeepSeek and connect it at platform.bolna.ai/auth/deepseek.
Connectors for this stage
Large Language Models
| Model | Context | Concurrent requests | Best for on Bolna |
|---|---|---|---|
deepseek-v4-flash | 1M tokens | 2,500 | Most voice agents. Recommended: fastest and lowest cost |
deepseek-v4-pro | 1M tokens | 500 | Complex reasoning tasks |
deepseek-chat, deepseek-reasoner | Not applicable | Not applicable | Deprecated July 24, 2026. Migrate to V4 |
The DeepSeek setup guide in the Bolna docs has the API config and migration notes.
The 2,500 concurrent request limit on deepseek-v4-flash fits large batch campaigns. The Bolna docs pair it with Deepgram Nova-2 for cost-sensitive setups; see the Deepgram integration.
Short, predictable calls where DeepSeek's quality is comparable to larger models at a lower price.
Ask a fixed set of questions across a long contact list at a lower LLM cost per call.
Automatic prompt caching lowers the cost of agents that repeat the same system prompt on every call.
Fireworks AI serves open models to a Bolna voice agent on serverless per-token access or on-demand GPU deployments, connected as an OpenAI-compatible custom LLM.
Google Gemini runs the conversation in a Bolna voice agent with a 1M token context and strong multilingual skills. gemini-2.5-flash is the recommended default.
Gemini Live runs a Bolna voice agent on Google's native-audio speech-to-speech model, with 30 prebuilt voices and session resumption for calls past 15 minutes.
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
