AI Providers

Nine providers.
Swappable per tool.

Here's the proof of it: AI isn't a connector bolted onto the side. It's the architecture. InTouch was built with AI at the center, and the vault, scheduling, access control, and audit sit behind it — which is exactly why nine providers drop in as first-class tools instead of one hard-wired vendor lock.

Anthropic Claude, OpenAI, Mistral, Groq, DeepSeek, xAI Grok, Google Gemini, and Ollama (local) — all eight ship as native task types in every edition. Hugging Face rounds out the set as a 9th, workflow-only provider. Each is a first-class tool — not an abstraction layer papering over differences. Use Claude's extended thinking where it helps, OpenAI's structured outputs where they help, Gemini's multi-modal where relevant, Groq for sub-second LPU inference, DeepSeek/Mistral for OpenAI-compatible cost-down options, xAI Grok for the Grok roster, and Ollama for anything that needs to stay inside your network. InTouch AI does what a single-vendor wrapper does — and the wrapper can never grow what InTouch already has at its core.

What Ships

Each Provider, With Its Distinctive Surface

Config-era tools pick a model for you and call it a feature. InTouch puts every surface on the table and lets the workflow choose — because the engine is AI-native, not AI-retrofitted.

Anthropic Claude (5 tool variants)

  • Claude Agent — multi-turn with tool use
  • Claude Batch — async batch API for high-volume
  • Claude Document — PDF and document reading
  • Claude Tools — direct tool-use without agent loop
  • Claude (base) — simple prompt-completion

Valid model IDs: claude-opus-4-6, claude-sonnet-4-6, claude-haiku-4-5-20251001.

OpenAI

  • Chat completions with function calling
  • Structured outputs / JSON mode
  • Embeddings (for the RAG pipeline)
  • Fine-tuning management (for fine-tuned models)
  • Image generation (DALL-E)
  • Whisper speech-to-text, TTS text-to-speech

Valid model IDs: gpt-4o, gpt-4o-mini.

Google Gemini

  • Text and multi-modal (image, document)
  • Function calling
  • Context caching for long-context prompts

Valid model IDs: gemini-2.5-flash, gemini-2.5-pro.

Ollama (Local)

  • Any model the operator installs locally (llama3.2, mistral, gemma2, your own fine-tunes)
  • Zero restrictions, zero API cost, no data leaving the network
  • Ideal for regulated domains (finance, legal, medical) and air-gapped deployments

Model names are operator-set — no fixed dropdown.

Mistral, Groq, DeepSeek, xAI

  • Mistral — mistral-large-latest and the Mistral roster via api.mistral.ai/v1
  • Groq — sub-second LPU inference; llama-3.3-70b-versatile and the Groq-hosted catalogue via api.groq.com/openai/v1
  • DeepSeek — deepseek-chat via api.deepseek.com/v1
  • xAI — Grok via api.x.ai/v1 (default grok-2)

All four use the OpenAI-compatible chat completions surface. Same task definition, swap the tool name and credential to switch provider.

Hugging Face (Workflow-only)

Hugging Face Inference is wired in as a workflow task type for batch — not as an Assistant chat backend. Useful when you want to call a specific HF model from a scheduled workflow (classification, embeddings, summarization) without standing up an inference server.

Built-In Safety

The Defaults Are the Right Defaults

This is the contract, now intelligent: tell InTouch AI what to do, and what to do when it doesn't work. The "doesn't work" clause stopped being a dumb rule and became an assessment — InTouch AI reads the failure, refreshes an expired token, smart-retries, and surfaces the one sentence that matters. Your API key never appears in any of it.

Safety Preamble

Every AI call prepends a safety preamble resisting prompt injection and enforcing output format. Override per tool when you need bare prompts; on by default.

Rate-Limit Handling

429s retried with exponential backoff and jitter. No hand-rolled retry loops. Invisible when it's working, diagnostic when it's not. It broke, here's why, it fixed it.

Audit Log

Every call logs provider, model, input tokens, output tokens, response. Budget tracking via SQL query on the audit table. Credentials stay encrypted in the vault — never in a script, never exposed even to the AI itself.

Swap Providers Without Rewriting

"If Anthropic Refuses, Swap to Ollama"

Anthropic (and OpenAI, and Gemini) have content policies. When a domain crosses a refusal line — financial advice, legal synthesis, medical reasoning — swap the tool reference to Ollama with a local model. Zero restrictions, zero API cost, no data leaving the network. The workflow definition doesn't change; only the tool name and credential do.

That same freedom is a dial. Run a workflow on pure AI while you're still earning trust in it, then graduate it toward fully deterministic — zero-AI-cost, identical every time, fully audited — once it has proven itself. Nobody else gives you the dial, because nobody else put the AI at the center to begin with.

Pick the Right AI for the Job

Not the one your SaaS vendor chose for you. That's the difference between an engine built AI-native and an older tool with AI stapled on — and you can't staple on a center. Free Personal edition, all 8 native providers included (plus Hugging Face as a 9th, workflow-only).

Download InTouch AIAI Assistant Detail

AI and data connectors in the InTouch Hub

Every one installs from the hub and runs on your own server. Browse all 2,286 connectors, or describe what you need and the assistant builds it.

  • Math — Connector for the math API (generated from its OpenAPI spec).
  • Openai — Connector for the openai API (generated from its OpenAPI spec).
  • Motaword — Connector for the motaword API (generated from its OpenAPI spec).
  • Telegram — Connector for the telegram API (generated from its OpenAPI spec).
  • Aiception — Connector for the aiception API (generated from its OpenAPI spec).
  • Wellknown — Connector for the wellknown API (generated from its OpenAPI spec).
  • Quickchart — Connector for the quickchart API (generated from its OpenAPI spec).
  • Webscraping — Connector for the webscraping API (generated from its OpenAPI spec).
  • Languagetool — Connector for the languagetool API (generated from its OpenAPI spec).
  • Moonmoonmoonmoon — Connector for the moonmoonmoonmoon API (generated from its OpenAPI spec).
  • Peoplegeneratorapi — Connector for the peoplegeneratorapi API (generated from its OpenAPI spec).
  • SQL — Run SQL against ten relational databases through one tool — MySQL, Oracle, PostgreSQL, SQL.