Choose and Configure Language Models

Your agent’s language model determines how it understands context, generates responses, and makes decisions. Dasha BlackBox supports multiple LLM providers, each with different strengths for voice conversations. What you’ll learn: Choosing a provider, configuring temperature, using custom endpoints, and optimizing for voice.

LLM latency typically accounts for 40–60% of total response time. We’ve measured this across millions of production calls — choosing the right provider and settings directly impacts conversation quality and caller satisfaction.

Recommended providers

Provider	Best for
Reflex-1	Low-latency voice conversations, native Dasha optimization
OpenAI	Production reliability, industry-leading quality

Reflex-1 is Dasha’s in-house model, built specifically for real-time voice. OpenAI remains our primary third-party provider, fully tested and optimized for Dasha BlackBox voice conversations.

Priority Tier: Enable priority tier for OpenAI to reduce latency at the cost of higher LLM pricing. This is recommended for latency-sensitive production deployments where response speed directly impacts conversation quality.

Alternative providers

The following providers are supported through OpenAI-compatible APIs. While functional, they have not been extensively tested on our platform. We recommend thorough testing before production use.

Provider	Notes
Groq	High throughput with open-source models
Grok (xAI)	Advanced reasoning capabilities
DeepSeek	Cost efficiency with high quality

Alternative providers may exhibit different latency characteristics, response formats, or edge-case behaviors compared to OpenAI. Test extensively with your specific use cases before deploying to production.

Configuration

Dashboard
API

Go to the LLM Config tab
Select your vendor from the dropdown
Choose a model
Configure temperature
Save your agent

API example: LLM configuration

llmConfig: {
  vendor: "openai",
  model: "gpt-4.1-mini",
  prompt: "You are a helpful assistant...",
  options: {
    temperature: 0.7,
    topP: 0.9
  }
}

LLM parameters

All LLM vendors support standard configuration parameters that control response behavior.

Temperature

Controls randomness and creativity in responses.

Range	Behavior	Use when
0.0–0.5	Focused, deterministic, consistent	FAQs, factual information, structured workflows
0.6–0.9	Balanced creativity and consistency	General conversation, customer support
1.0–2.0	Creative, varied, unpredictable	Rarely used for voice agents

For production voice agents, use temperature between 0.6–0.8. In our testing across thousands of calls, this range produces consistent yet natural-sounding responses. Lower values feel robotic; higher values risk hallucinations and off-topic tangents.

Top P (nucleus sampling)

Alternative to temperature for controlling randomness via probability mass.

Value	Effect
0.9	Only considers tokens in top 90% probability — more focused
1.0	Considers all tokens — standard behavior

OpenAI recommends using either temperature or topP, not both. If you set both, temperature takes precedence.

Custom compatible provider

Use any OpenAI-compatible API endpoint, including self-hosted models or alternative providers.

When to use custom providers

Self-hosted models for data privacy
Alternative providers with OpenAI-compatible APIs
Custom fine-tuned models
On-premise deployments

Configuration

Dashboard
API

Select Custom Compatible as your vendor
Enter the Endpoint URL (e.g., https://api.yourprovider.com/v1)
Enter your API Key (minimum 10 characters)
Enter the Model ID as recognized by your provider
Configure standard LLM parameters
Save your agent

API example: Custom provider configuration

llmConfig: {
  vendor: "customCompatible",
  model: "your-model-name",
  endpoint: "https://api.yourprovider.com/v1",
  apiKey: "your-provider-api-key",
  prompt: "You are a custom AI assistant.",
  options: {
    temperature: 0.7
  }
}
// Latency: Depends on your provider infrastructure

Custom providers must implement the OpenAI Chat Completions API format. Incompatible APIs cause agent failures. Test thoroughly before production use.

Testing and optimization

A/B testing LLMs

Compare different vendors for your specific use case:

Create identical agents with different LLM configs
Run parallel test calls with the same scenarios
Measure response quality, speed, length, and success rate
Compare costs over 100–1000 calls

Parameter tuning

Temperature tuning:

Start at 0.7 (balanced)
Test with real conversation scenarios
Adjust based on observations:
- Too robotic/repetitive → Increase to 0.8–0.9
- Too creative/inconsistent → Decrease to 0.5–0.6
- Hallucinating information → Decrease to 0.3–0.5

Next steps

Voice & Speech

Configure text-to-speech providers

Tools & Functions

Enable agents to call external APIs

Test Your Agent

Validate agent responses

Production Checklist

Pre-deployment verification

Introduction

Create

Test

Deploy

Monitor

Advanced Features

Troubleshooting

Recommended providers

Alternative providers

Configuration

LLM parameters

Temperature

Top P (nucleus sampling)

Custom compatible provider

When to use custom providers

Configuration

Testing and optimization

A/B testing LLMs

Parameter tuning

Next steps

Voice & Speech

Tools & Functions

Test Your Agent

Production Checklist

Introduction

Create

Test

Deploy

Monitor

Advanced Features

Troubleshooting

Documentation Index

​Recommended providers

​Alternative providers

​Configuration

​LLM parameters

​Temperature

​Top P (nucleus sampling)

​Custom compatible provider

​When to use custom providers

​Configuration

​Testing and optimization

​A/B testing LLMs

​Parameter tuning

​Next steps

Voice & Speech

Tools & Functions

Test Your Agent

Production Checklist

Recommended providers

Alternative providers

Configuration

LLM parameters

Temperature

Top P (nucleus sampling)

Custom compatible provider

When to use custom providers

Configuration

Testing and optimization

A/B testing LLMs

Parameter tuning

Next steps