Skip to main content
OpenAI’s GPT-5 family is the current generation. gpt-5.4-mini is the default recommendation for most voice agents — it has low time-to-first-token and strong instruction following at a fraction of the cost of the full model.

​
Quick config

"llm_agent": {
  "agent_type": "simple_llm_agent",
  "agent_flow_type": "streaming",
  "llm_config": {
    "provider": "openai",
    "model": "gpt-5.4-mini",
    "max_tokens": 150,
    "temperature": 0.2
  }
}
To use your own OpenAI API key, connect it at platform.bolna.ai/auth/openai.

​
Supported models

ModelContextBest forNotes
gpt-5.51M tokensMost demanding reasoning and qualityFlagship; highest cost
gpt-5.41M tokensGeneral-purpose production agentsStrong reasoning, lower cost than 5.5
gpt-5.4-mini400K tokensMost voice agentsRecommended — fastest TTFT, lowest cost
gpt-4.11M tokensPrevious-gen; still availableUse if already deployed
gpt-4.1-mini1M tokensPrevious-gen; still availableUse if already deployed
gpt-4o128K tokensPrevious-gen; still availableUse if already deployed
Recommendation: Start with gpt-5.4-mini. Upgrade to gpt-5.4 or gpt-5.5 when you need complex multi-step reasoning or higher output quality (financial, medical, nuanced escalation).

​
Key settings

SettingTypeRecommendedDescription
providerstring"openai"Provider name
modelstring"gpt-4.1-mini"Model to use
max_tokensinteger150Cap on response length — keep short for voice
temperaturefloat0.2Lower = more deterministic; good for scripts
agent_flow_typestring"streaming"Always "streaming" for voice

​
Keep max_tokens short

Voice responses should be 1–3 sentences. max_tokens: 150 (about 100–120 spoken words) is appropriate for most turns. A higher cap doesn’t hurt quality but increases tail latency on long responses.

​
Writing prompts for voice

Prompts for voice agents differ from chat prompts:
  • Use imperative sentences: “Keep all responses under 3 sentences.”
  • Specify spoken format: “Never use bullet points or markdown — speak in complete sentences.”
  • Define handling for off-topic questions: “If asked something outside your scope, say: ‘I can only help with appointment scheduling today.’”
  • Include the welcome message in the prompt or agent config, not as part of the system prompt instructions.
See Prompting Guide for full guidance.

​
Function calling

GPT-4.1 and gpt-4.1-mini both support function calling. In Bolna, functions are defined in the Tools Tab and called automatically by the LLM during conversation. See Custom Function Calls for configuration.

​
FAQ

Use gpt-5.4-mini for most agents. Its time-to-first-token is lowest and cost per call is significantly less. Upgrade to gpt-5.4 when you need stronger reasoning or higher accuracy. Use gpt-5.5 for the most demanding tasks (complex financial/medical, long multi-step tool chains) where quality is the top priority.
Lower max_tokens, use gpt-4.1-mini instead of larger models, and write shorter system prompts (large prompts increase prefill time). See Latency for a full breakdown.
Yes. Connect your OpenAI account at platform.bolna.ai/auth/openai. Costs will be charged to your OpenAI account, not Bolna’s platform wallet (for the LLM component).