Skip to main content
The LLM decides what the agent says. Quality tier and latency are the primary selection factors. See each provider’s page for current model names.
Provider model lineups change frequently. The specific model names here are current examples — always check the relevant LLM provider page or the provider’s own docs for the latest recommended model.
LLM provider pages:

OpenAI

GPT-5.4-mini, GPT-5.4, GPT-5.5

Anthropic

Claude Sonnet 5, Haiku 4.5, Opus 4.8

Google Gemini

Gemini 2.5 Flash, Gemini 3.x

Azure OpenAI

GPT-5.x via Azure infrastructure

DeepSeek

DeepSeek V4 Flash, V4 Pro

Sarvam

Sarvam 105B Chat, for Indian languages

AWS Bedrock

gpt-5.6-luna served in India

OpenRouter

Unified gateway — all providers

Next steps

LLM providers

Setup guides for every LLM provider

Custom LLM inference

Connect an inference provider or your own self-hosted LLM

Choose a voice

The next provider in the pipeline

Back to the decision guide

Compare all provider categories side by side