AI models in InsertChat
GPT-5.2, Claude Sonnet 4.5, Gemini 3.0, Llama 4, Grok 4.1, and DeepSeek V3.2 — all in one workspace. Switch models per conversation, use fast models for FAQs and premium models for complex reasoning. All models share the same knowledge base, tools, and history. BYOK supported.
7-day free trial · Cancel anytime · No commitment
Browse models
available today
Pick the model per chat and keep your agent configuration stable.
OpenAI GPT models in InsertChat
Deploy GPT-5.2 and GPT-4.1 agents grounded in your knowledge base. Fast responses, advanced reasoning, and multi-channel deployment without coding.
Claude models in InsertChat
Create AI agents with Anthropic's Claude Sonnet 4.5, Haiku 4.5, and Opus 4.6. Superior reasoning, extended context, and nuanced responses grounded in your documents.
Gemini models in InsertChat
Deploy Gemini 3.0 Flash and Gemini 3.0 Pro agents with multimodal capabilities. Process images, PDFs, and text with cost-efficient, fast AI grounded in your data.
Llama models in InsertChat
Build AI agents with Meta's Llama 4 Maverick and Llama 4 Scout. Open-source models with full data privacy, BYOK support, and enterprise-ready performance for your knowledge base.
Grok models in InsertChat
Deploy xAI's Grok 4.1 Fast Instant and Grok 4.1 Fast Thinking for AI agents with real-time knowledge and 2M token context. Get up-to-date responses grounded in your documents.
Gemini 3.0 Flash in InsertChat
Build agents with Google's Gemini 3.0 Flash. Get fast, cost-efficient multimodal responses grounded in your knowledge base. No coding required.
Gemini 3.0 Pro in InsertChat
Deploy Gemini 3.0 Pro agents with advanced reasoning and multimodal understanding. Process images, documents, and text grounded in your data.
Nano Banana in InsertChat
Generate images directly in your AI agent with Nano Banana. Create visuals on the fly during conversations, grounded in your brand context.
Nano Banana Pro in InsertChat
Generate high-fidelity images with Nano Banana Pro. Premium quality visuals in your AI agent for product imagery, marketing assets, and creative workflows.
Claude Sonnet 4.5 in InsertChat
Deploy Claude Sonnet 4.5 agents with balanced speed and intelligence. Ideal for everyday tasks, document analysis, and customer-facing conversations.
Claude Haiku 4.5 in InsertChat
Build agents with Claude Haiku 4.5 for fast, lightweight AI. Ideal for high-volume support, quick lookups, and cost-sensitive deployments.
Claude Opus 4.6 in InsertChat
Deploy Claude Opus 4.6 for maximum reasoning power. Ideal for complex analysis, research workflows, and tasks requiring deep understanding.
GPT-5.2 Instant Chat in InsertChat
Build real-time conversational AI with GPT-5.2 Instant Chat. Fast, fluent responses for customer support, sales, and internal workflows.
GPT-5.2 Reasoning in InsertChat
Deploy GPT-5.2 Reasoning for multi-step logic, analysis, and complex problem-solving. Ideal for research, planning, and data-heavy workflows.
GPT-5.2 Pro in InsertChat
Deploy GPT-5.2 Pro for premium AI performance. The most capable OpenAI model for enterprise tasks, deep research, and mission-critical workflows.
GPT-4o in InsertChat
Build agents with GPT-4o for fast, multimodal AI. Process text, images, and documents with reliable outputs grounded in your knowledge base.
GPT-4o Mini in InsertChat
Deploy GPT-4o Mini for lightweight, affordable AI agents. Ideal for high-volume support, simple queries, and cost-sensitive use cases.
GPT-4.1 in InsertChat
Build agents with GPT-4.1 for reliable instruction-following and strong coding capabilities. Ideal for structured workflows and tool-heavy agents.
GPT-4.1 Mini in InsertChat
Deploy GPT-4.1 Mini for compact, efficient AI agents. Good instruction-following at lower cost for everyday support and workflow automation.
GPT-4.1 Nano in InsertChat
Build ultra-lightweight agents with GPT-4.1 Nano. The smallest OpenAI model for simple lookups, FAQs, and high-volume, low-cost deployments.
GPT-OSS in InsertChat
Deploy OpenAI's open-source GPT-OSS models (20B and 120B parameters) in InsertChat. Transparent, inspectable AI for teams that value openness.
GPT-OSS 20B in InsertChat
Deploy OpenAI's open-source GPT-OSS 20B in InsertChat. 128K context, $0.07/M input tokens, and transparent weights for fast, cost-efficient AI agents.
GPT-OSS 120B in InsertChat
Deploy OpenAI's open-source GPT-OSS 120B in InsertChat. 131K context, 120 billion parameters, and transparent weights for enterprise-grade open-source AI agents.
Codex 5.1 in InsertChat
Build code-generating AI agents with OpenAI Codex 5.1. Produce clean code, explain technical concepts, and automate development workflows in your agent.
Codex 5.1 Max in InsertChat
Deploy Codex 5.1 Max for the most capable code generation. Handle complex multi-file tasks, architecture decisions, and advanced programming challenges.
Codex 5.1 Mini in InsertChat
Build lightweight code-generating agents with Codex 5.1 Mini. Fast code snippets, explanations, and simple automations at lower cost.
DeepSeek V3.2 in InsertChat
Build AI agents with DeepSeek V3.2 for cost-efficient reasoning. Strong performance on coding, math, and analysis tasks at competitive pricing.
DeepSeek V3.2 Thinking in InsertChat
Deploy DeepSeek V3.2 Thinking for extended reasoning with visible thought chains. Ideal for complex problems requiring step-by-step deliberation.
Llama 4 Maverick in InsertChat
Deploy Llama 4 Maverick for open-source AI with strong multilingual and reasoning capabilities. Full data privacy with enterprise-grade performance.
Llama 4 Scout in InsertChat
Build agents with Llama 4 Scout for lightweight, open-source AI. Fast responses and strong efficiency for everyday tasks with full transparency.
Grok 4.1 Fast Instant in InsertChat
Deploy Grok 4.1 Fast Instant for ultra-fast, non-reasoning conversations. 2M token context with real-time speed for support and Q&A.
Grok 4.1 Fast Thinking in InsertChat
Deploy Grok 4.1 Fast Thinking for reasoning capabilities with fast response times. 2M token context with step-by-step problem solving.
Kimi K2 in InsertChat
Deploy Kimi K2 from Moonshot AI for strong multilingual performance and competitive reasoning. A versatile model for global teams and diverse use cases.
Kimi K2 Thinking in InsertChat
Deploy Kimi K2 Thinking for extended reasoning with visible thought chains. Ideal for complex multilingual analysis and deliberate problem-solving.
MiniMax M2.1 in InsertChat
Build AI agents with MiniMax M2.1 for versatile performance across text, reasoning, and creative tasks. Strong multilingual support.
Qwen3 235B in InsertChat
Deploy Qwen3 235B for powerful multilingual AI. Strong performance in Chinese, English, and 20+ languages with competitive reasoning and coding.
Qwen3 235B Thinking in InsertChat
Deploy Qwen3 235B Thinking for extended reasoning in 20+ languages. Visible thought chains for complex multilingual analysis and problem-solving.
GLM 4.7 in InsertChat
Deploy GLM 4.7 for strong Chinese-English bilingual AI. Competitive reasoning and generation for teams serving Chinese-speaking audiences.
GLM 4.6 Visual in InsertChat
Deploy GLM 4.6 Visual for image understanding and visual Q&A. Analyze screenshots, documents, and images in your AI agent conversations.
Mistral Nemo in InsertChat
Build agents with Mistral Nemo for European open-source AI. Lightweight, fast, and privacy-friendly with strong multilingual capabilities.
What teams get
with multi-model access
Balance quality, speed, and budget without rebuilding setup.
- Your agent behaves the same regardless of which model powers it — same knowledge base, same tools, same guardrails
- Route simple questions to a fast, cheap model and complex ones to a premium model — you control the cost per conversation
- Every model answers from your actual content, not its general training data — reducing hallucinations across the board
- One workspace replaces separate subscriptions to OpenAI, Anthropic, and Google — your team accesses everything in one place
Related Pages
Frequently asked questions
Tap any question to see how InsertChat would respond.
Contact supportInsertChat
AI Support
Hey! 👋 Browsing Product questions. Tap any to get instant answers.
What is InsertChat?
An AI agent workspace that lets you build agents grounded in your knowledge and deploy them to web, app, or API. Connect tools and integrations to complete workflows.
What's the difference between an agent and an InsertChat agent?
A basic agent is prompt-only. InsertChat agents are grounded in your sources, configurable per use case, and able to use tools and integrations.
How do agents stay accurate and avoid hallucinations?
Ground your agent in a knowledge base your team controls and keep it fresh. Use analytics to find gaps and improve coverage over time.
What can I connect as knowledge?
URLs, sitemaps, documents (PDF and office files), media like YouTube and audio, and structured data. The goal is a clear source of truth for answers.
Do sources stay up to date?
Yes. Refresh sources on demand or set up scheduled refresh depending on the source type.
Can I control how the agent behaves?
Yes. Control prompts, model choice, tool access, and agent experience so behavior stays consistent.
Which AI models can I use?
GPT-5.2, Claude Sonnet 4.5, Gemini 3.0, Llama 4, Grok 4.1, DeepSeek V3.2, and more. Choose the model per chat, or use BYOK to manage provider access yourself.
Can I pick different models for different workflows?
Yes. Use a faster model for common questions and a stronger model for complex reasoning. InsertChat supports that balance per conversation.
Where can I deploy an agent?
Website widget, in-app embed, or API. Keep one agent setup and reuse it across channels.
Do I need coding skills?
No. Build and deploy AI agents using our visual builder. The embed code is one line of JavaScript.
Can I customize the branding and UI?
Yes. Customize the widget to match your brand. White-label options are available for a fully branded experience.
Can I use my own domain?
Yes. Custom domains are supported, typically via enterprise options.
Does InsertChat support voice?
Yes. Voice dictation and text-to-speech let users speak instead of type.
Does InsertChat support vision?
Yes. Enable vision for agents when images help clarify a request or context.
What tools and integrations are supported?
Zendesk, HubSpot, Shopify, WooCommerce, calendar booking, web search, Perplexity, and webhooks for your own systems.
Can I control which tools the agent is allowed to use?
Yes. Tool access is controlled per agent so you enable only what you need.
Can the agent hand off to a human?
Yes. Configure human handoff so the agent escalates when needed. Full conversation history is passed along.
Do you provide analytics?
Yes. Track chats, leads, feedback, and credits used. Find gaps in coverage and prioritize fixes.
Is it mobile friendly?
Yes. The widget and embeds work well on desktop and mobile with no separate experience needed.
What's the fastest path to a successful deployment?
Start with one agent and a small set of high-value sources. Iterate using real questions from analytics.
What is the fastest way to get started?
Create an account, upload one document, and ask your first question. Most teams go live in under 5 minutes.
Product FAQ
What is InsertChat?
An AI agent workspace that lets you build agents grounded in your knowledge and deploy them to web, app, or API. Connect tools and integrations to complete workflows.
What's the difference between an agent and an InsertChat agent?
A basic agent is prompt-only. InsertChat agents are grounded in your sources, configurable per use case, and able to use tools and integrations.
How do agents stay accurate and avoid hallucinations?
Ground your agent in a knowledge base your team controls and keep it fresh. Use analytics to find gaps and improve coverage over time.
What can I connect as knowledge?
URLs, sitemaps, documents (PDF and office files), media like YouTube and audio, and structured data. The goal is a clear source of truth for answers.
Do sources stay up to date?
Yes. Refresh sources on demand or set up scheduled refresh depending on the source type.
Can I control how the agent behaves?
Yes. Control prompts, model choice, tool access, and agent experience so behavior stays consistent.
Which AI models can I use?
GPT-5.2, Claude Sonnet 4.5, Gemini 3.0, Llama 4, Grok 4.1, DeepSeek V3.2, and more. Choose the model per chat, or use BYOK to manage provider access yourself.
Can I pick different models for different workflows?
Yes. Use a faster model for common questions and a stronger model for complex reasoning. InsertChat supports that balance per conversation.
Where can I deploy an agent?
Website widget, in-app embed, or API. Keep one agent setup and reuse it across channels.
Do I need coding skills?
No. Build and deploy AI agents using our visual builder. The embed code is one line of JavaScript.
Can I customize the branding and UI?
Yes. Customize the widget to match your brand. White-label options are available for a fully branded experience.
Can I use my own domain?
Yes. Custom domains are supported, typically via enterprise options.
Does InsertChat support voice?
Yes. Voice dictation and text-to-speech let users speak instead of type.
Does InsertChat support vision?
Yes. Enable vision for agents when images help clarify a request or context.
What tools and integrations are supported?
Zendesk, HubSpot, Shopify, WooCommerce, calendar booking, web search, Perplexity, and webhooks for your own systems.
Can I control which tools the agent is allowed to use?
Yes. Tool access is controlled per agent so you enable only what you need.
Can the agent hand off to a human?
Yes. Configure human handoff so the agent escalates when needed. Full conversation history is passed along.
Do you provide analytics?
Yes. Track chats, leads, feedback, and credits used. Find gaps in coverage and prioritize fixes.
Is it mobile friendly?
Yes. The widget and embeds work well on desktop and mobile with no separate experience needed.
What's the fastest path to a successful deployment?
Start with one agent and a small set of high-value sources. Iterate using real questions from analytics.
What is the fastest way to get started?
Create an account, upload one document, and ask your first question. Most teams go live in under 5 minutes.