Pick the model behind the branded assistant
Browse 274 models. Switch for speed, cost, or depth without changing the assistant.
7-day free trial · No card required
Search model pages
274 model pages match your filters.
Model family
Browse models
Pick models without changing content, branding, or deployment.
Build with Devstral 2
Use Devstral 2 in InsertChat for coding-heavy work, 256K-token context window, and a grounded route that keeps setup, comparison, and review in one place.
Build with Devstral Small 2
Use Devstral Small 2 in InsertChat for coding-heavy work, 256K-token context window, and a grounded route that keeps setup, comparison, and review in one place.
Build with Devstral Small 1.1
Use Devstral Small 1.1 in InsertChat for coding-heavy work, 128K-token context window, and a grounded route that keeps setup, comparison, and review in one place.
Build with fal FLUX 2 Flex
Deploy fal FLUX 2 Flex in InsertChat for a more flexible fal.ai FLUX tier for fast image experimentation and iteration. Ground responses in your knowledge base, compare this exact model version against other options in your stack, and keep the workflow tied to one operating surface.
Build with fal FLUX 2 Pro Edit
Deploy fal FLUX 2 Pro Edit in InsertChat for a fal.ai FLUX editing tier for controlled image changes and iterative visual workflows. Ground responses in your knowledge base, compare this exact model version against other options in your stack, and keep the workflow tied to one operating surface.
Build with fal FLUX 2 Pro
Deploy fal FLUX 2 Pro in InsertChat for a higher-end fal.ai FLUX image tier for polished visual generation and creative iteration. Ground responses in your knowledge base, compare this exact model version against other options in your stack, and keep the workflow tied to one operating surface.
Build with fal FLUX Pro Kontext
Deploy fal FLUX Pro Kontext in InsertChat for a fal.ai FLUX variant built around richer contextual image workflows. Ground responses in your knowledge base, compare this exact model version against other options in your stack, and keep the workflow tied to one operating surface.
Build with fal FLUX Pro V1.1
Deploy fal FLUX Pro V1.1 in InsertChat for a versioned fal.ai FLUX Pro release for teams comparing visual quality across FLUX generations. Ground responses in your knowledge base, compare this exact model version against other options in your stack, and keep the workflow tied to one operating surface.
Build with fal Kling 2.6 Pro Image
Deploy fal Kling 2.6 Pro Image to Video in InsertChat for a fal.ai-hosted Kling release for image-to-video generation and richer visual storytelling. Ground responses in your knowledge base, compare this exact model version against other options in your stack, and keep the workflow tied to one operating surface.
Build with fal Kling 3 Pro Image to
Deploy fal Kling 3 Pro Image to Video in InsertChat for a newer fal.ai Kling tier for teams comparing current image-to-video releases. Ground responses in your knowledge base, compare this exact model version against other options in your stack, and keep the workflow tied to one operating surface.
Build with fal LTX 2 19B Image to
Deploy fal LTX 2 19B Image to Video in InsertChat for a fal.ai-hosted LTX video tier for image-to-video workflows and motion experiments. Ground responses in your knowledge base, compare this exact model version against other options in your stack, and keep the workflow tied to one operating surface.
Build with fal Nano Banana 2 Edit
Deploy fal Nano Banana 2 Edit in InsertChat for the editing variant of Nano Banana 2 for quick image revisions on fal.ai. Ground responses in your knowledge base, compare this exact model version against other options in your stack, and keep the workflow tied to one operating surface.
Build with fal Nano Banana 2
Deploy fal Nano Banana 2 in InsertChat for a newer Nano Banana image tier on fal.ai for fast visual generation and experimentation. Ground responses in your knowledge base, compare this exact model version against other options in your stack, and keep the workflow tied to one operating surface.
Build with fal Qwen Image
Deploy fal Qwen Image in InsertChat for fal.ai's hosted Qwen Image tier for image generation inside a broader multi-model stack. Ground responses in your knowledge base, compare this exact model version against other options in your stack, and keep the workflow tied to one operating surface.
Build with fal Recraft V4 Pro Text to
Deploy fal Recraft V4 Pro Text to Image in InsertChat for a fal.ai-hosted Recraft release for polished text-to-image generation. Ground responses in your knowledge base, compare this exact model version against other options in your stack, and keep the workflow tied to one operating surface.
Build with fal Sora 2 Text to Video
Deploy fal Sora 2 Text to Video in InsertChat for fal.ai's hosted Sora 2 text-to-video tier for motion-heavy creative workflows. Ground responses in your knowledge base, compare this exact model version against other options in your stack, and keep the workflow tied to one operating surface.
Build with fal Veo 3.1 Fast
Deploy fal Veo 3.1 Fast in InsertChat for a faster fal.ai Veo 3.1 tier for quicker prompt iteration and review loops. Ground responses in your knowledge base, compare this exact model version against other options in your stack, and keep the workflow tied to one operating surface.
Build with fal Veo 3.1
Deploy fal Veo 3.1 in InsertChat for fal.ai's Veo 3.1 tier for polished video generation inside routed creative workflows. Ground responses in your knowledge base, compare this exact model version against other options in your stack, and keep the workflow tied to one operating surface.
Build with FLUX.2 [flex]
Use FLUX.2 [flex] in InsertChat for creative image workflows, production-sized context support, and a grounded route that keeps setup, comparison, and review in one place.
Build with FLUX.2 [klein] 4B
Use FLUX.2 [klein] 4B in InsertChat for creative image workflows, production-sized context support, and a grounded route that keeps setup, comparison, and review in one place.
Build with FLUX.2 [klein] 9B
Use FLUX.2 [klein] 9B in InsertChat for creative image workflows, production-sized context support, and a grounded route that keeps setup, comparison, and review in one place.
Build with FLUX.2 [max]
Use FLUX.2 [max] in InsertChat for creative image workflows, 67.3K-token context window, and a grounded route that keeps setup, comparison, and review in one place.
Build with FLUX.2 [pro]
Use FLUX.2 [pro] in InsertChat for creative image workflows, 67.3K-token context window, and a grounded route that keeps setup, comparison, and review in one place.
Build with Flux Schnell
Use Flux Schnell in InsertChat for creative image workflows, 512-token context window, and a grounded route that keeps setup, comparison, and review in one place.
What you get
Balance quality, speed, and budget without rebuilding setup.
- Keep the same sources, tools, and guardrails across models
- Route simple questions to faster, cheaper models
- Ground every model in your owned content
- Keep the visitor experience branded while teams choose the model
More to explore
Try the FAQ like a visitor.
Open product, pricing, security, integration, and free-tool questions in the same chat your visitors use.
InsertChat
Interactive FAQ
Hey. Pick a question below and see how InsertChat turns FAQs into clear, source-backed answers.
Product FAQ
What is InsertChat?
InsertChat is a white-label AI assistant for your website. Train it, brand it, publish it, and learn from visitor questions.
How does InsertChat use my website content?
Connect approved pages, docs, videos, FAQs, policies, and other sources. InsertChat turns them into source-backed answers and next steps.
Can I control the assistant's tone and sources?
Yes. Choose its sources, tone, welcome message, and prompts so it stays on brand.
How does InsertChat stay accurate?
Answers use approved content and source links. Analytics show unclear or missing answers so you can improve coverage.
Can it collect leads or route support questions?
Yes. InsertChat can collect details, qualify intent, add context, and send chats to the right inbox, CRM, workflow, or person.
Can I control how the assistant behaves?
Yes. Control prompts, model choice, tool access, and the branded assistant experience so behavior stays consistent.
Which AI models can I use?
InsertChat supports multiple model providers. Choose each assistant's model for quality, speed, and cost, or use BYOK.
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 assistant?
Use a widget, embed, full-page assistant, custom domain, in-app embed, or API. Reuse one setup across surfaces.
Do I need coding skills?
No. Build and deploy AI assistants using our visual builder. The embed code is one line of JavaScript.
Can I customize the branding and UI?
Yes. Customize the assistant name, logo, colors, welcome message, suggested prompts, tone, domain, and white-label presentation.
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 assistants 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 assistant is allowed to use?
Yes. Tool access is controlled per assistant 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, top questions, unanswered questions, most-used sources, and content gaps.
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 assistant 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. Connect one key source. Ask a test question, brand the assistant, then publish it on one page.