Providers, model types, and plan access currently supported by Assistant Core.
Assistant Core supports multiple AI models for chat, voice, and realtime conversations. Depending on your plan and assistant configuration, the right models appear in the relevant Web App or Admin Panel selector.
The Chat model for text messages, attachments, tool use, and Knowledge Base retrieval
Web App → Settings → Voice
Personal Voice Agent model and voice preferences for Standard mode and Realtime mode
Admin Panel → Assistant Settings
Assistant-level voice enablement, recording policy, and Stream Response Text
Platform/Admin catalog
Model catalog, voice lists, and plan access
The Chat model and Voice Agent models are separate choices. Changing the Chat model in the header does not change VAD, ASR, TTS, TTS voice, Realtime model, or Realtime voice in Settings → Voice.
Alloy, Ash, Ballad, Coral, Echo, Sage, Shimmer, Verse, Marin, Cedar
Verse
Gemini 3.1 Flash Live (Google AI)
Kore, Puck, Charon, Fenrir, Aoede
— (first in list)
Vietnamese (vi-VN) voices are currently available only on ElevenLabs: Huyền, Jade (female) and Nhật Nam (male). The other voices are English (en-US/en-GB) but can still read Vietnamese text.
Assistant Core converts provider cost to credits using your plan's billing
multiplier. These are the underlying OpenAI Standard rates in USD per 1 million
tokens:
Model
Input context
Input
Cached input
Cache write
Output
GPT-5.6 Luna
≤272K
$0.20
$0.02
$0.25
$1.20
GPT-5.6 Luna
>272K
$0.40
$0.04
$0.50
$1.80
GPT-5.6 Terra
≤272K
$2.00
$0.20
$2.50
$12.00
GPT-5.6 Terra
>272K
$4.00
$0.40
$5.00
$18.00
GPT-4.1
—
$2.00
$0.50
—
$8.00
GPT-4.1 Mini
—
$0.40
$0.10
—
$1.60
For GPT-5.6, more than 272K input tokens switches the full request to the long-context rates. The model supports up to 922K input tokens plus 128K output tokens within its 1.05M context window.
When you create an account or join an assistant, Assistant Core uses these defaults unless you choose your own preferences. You can change the Chat model from the Web App header; Voice Agent models and voices are changed in Settings → Voice.
Type
Default Model
Chat (LLM)
DeepSeek V4 Flash
Text to Speech
Grok 2 TTS
Speech to Text
Soniox STT Realtime v5
Voice Activity Detection
Silero VAD
Realtime Voice
Grok Voice Agent
Default models are the same across all plans. The difference between plans is the list of available models — higher plans unlock more models for you to switch to.
Each AI operation consumes credits from your wallet. More expensive models cost more credits. See Credits for details.
