StateSet API Docs home page
Search...
⌘K
Ask AI
Community
Support
Dashboard
Dashboard
Search...
Navigation
Core Concepts
Models
Documentation
Getting Started
StateSet One
StateSet Response
StateSet Commerce
StateSet Cloud
Documentation
GitHub
Community
Newsletter
Overview
Developer Guide
Service-as-a-Software (SaaS 3.0)
Security
StateSet Overview
Autonomous Agent Architecture
Global Commerce Architecture
StateSet: The Agentic Operating System
Quickstart
SDK Installation & Setup Guide
Platform Quickstarts
StateSet One
Guides
StateSet Response
Core Concepts
ResponseCX
Agents
Authentication
Models
Agent Framework and SDK
Computer Use AI Agents
ReasonCX
Realtime Voice
Guides
StateSet Commerce
Guides
On this page
o1-preview
GPT4o
Claude 3.5 Sonnet
Llama 3.1
Llama 3.1 405B (Preview)
Llama 3.1 70B (Preview)
Llama 3.1 8B (Preview)
Llama 3 Groq 70B Tool Use (Preview)
Llama 3 Groq 8B Tool Use (Preview)
Meta Llama 3 70B
Meta Llama 3 8B
Mixtral 8x7B
Gemini 1.5 Flash
Gemini 1.5 Pro
Gemma 7B
Gemma 2 9B
Whisper
Core Concepts
Models
Models supported by the Stateset ReSponse API
Stateset ReSponse supports the following AI models:
o1-preview
o1-preview is a variant of OpenAI’s o1 model, optimized for performance on a wide range of reasoning, physics and math tasks.
GPT4o
GPT4o is a variant of OpenAI’s GPT-4 model, optimized for performance on a wide range of tasks.
Claude 3.5 Sonnet
Claude 3.5 Sonnet is an advanced language model developed by Anthropic, known for its strong performance across a wide range of tasks.
Llama 3.1
Llama 3.1 is available in three variants:
Llama 3.1 405B (Preview)
Model ID: llama-3.1-405b-reasoning
Developer: Meta
Context Window: 131,072 tokens
Max Input Tokens: 16,000 (during preview)
Llama 3.1 70B (Preview)
Model ID: llama-3.1-70b-versatile
Developer: Meta
Context Window: 131,072 tokens
Max Input Tokens: 8,000 (during preview)
Llama 3.1 8B (Preview)
Model ID: llama-3.1-8b-instant
Developer: Meta
Context Window: 131,072 tokens
Max Input Tokens: 8,000 (during preview)
Note: During the preview launch, all Llama 3.1 models are limited to a maximum of 8,000 output tokens.
Llama 3 Groq 70B Tool Use (Preview)
Model ID: llama3-groq-70b-8192-tool-use-preview
Developer: Groq
Context Window: 8,192 tokens
Llama 3 Groq 8B Tool Use (Preview)
Model ID: llama3-groq-8b-8192-tool-use-preview
Developer: Groq
Context Window: 8,192 tokens
Meta Llama 3 70B
Model ID: llama3-70b-8192
Developer: Meta
Context Window: 8,192 tokens
Meta Llama 3 8B
Model ID: llama3-8b-8192
Developer: Meta
Context Window: 8,192 tokens
Mixtral 8x7B
Model ID: mixtral-8x7b-32768
Developer: Mistral
Context Window: 32,768 tokens
Gemini 1.5 Flash
Model ID: gemini-1.5-flash
Developer: Google
Context Window: 8,192 tokens
Gemini 1.5 Pro
Model ID: gemini-1.5-pro
Developer: Google
Context Window: 8,192 tokens
Gemma 7B
Model ID: gemma-7b-it
Developer: Google
Context Window: 8,192 tokens
Gemma 2 9B
Model ID: gemma2-9b-it
Developer: Google
Context Window: 8,192 tokens
Whisper
Model ID: whisper-large-v3
Developer: OpenAI
File Size: 25 MB
Authentication
Agent Framework and SDK
Assistant
Responses are generated using AI and may contain mistakes.