Lobstack is a managed cloud platform for deploying autonomous AI agents. Each agent runs on a dedicated virtual machine with persistent memory, 700+ integrations, and goes live in under 90 seconds with zero DevOps.

How long does it take to deploy an AI agent?

You can deploy an AI agent on Lobstack in under 90 seconds. Describe what your agent should do, pick a model, and Lobstack handles all the infrastructure — no Docker, Kubernetes, or server setup needed.

What AI models does Lobstack support?

Lobstack supports 16 AI models including Claude Opus and Sonnet from Anthropic, GPT-5 and GPT-4o from OpenAI, Gemini 2.5 Pro from Google, plus DeepSeek, Mistral, and Grok. You can hot-swap models without losing agent memory or configuration.

Is Lobstack secure for enterprise use?

Yes. Every agent runs in a gVisor-sandboxed VM with AES-256 encryption at rest, TLS 1.3 in transit, HashiCorp Vault for secrets, row-level security on all tables, and full audit logging. Lobstack is SOC 2 aligned.

Docs/AI Models/Supported Models

Reference

AI Models

Lobstack supports 24 AI models from 10 providers. Switch models anytime from your dashboard — models are grouped by provider with badges for quick comparison.

Supported Models#

Model	Provider	Strengths	Plan Required
Claude Sonnet 4.5	Anthropic	Fast, great balance of capability and speed	All plans
Claude Opus 4.6	Anthropic	Most capable, complex reasoning and analysis	Pro+
GPT-4o	OpenAI	Strong general-purpose, multimodal	All plans
GPT-4o Mini	OpenAI	Fast and cost-effective for simpler tasks	All plans
o3-mini	OpenAI	Reasoning-focused, strong for logic tasks	All plans
GPT-5	OpenAI	Advanced coding and complex reasoning	Pro+
GPT-5.2	OpenAI	Most intelligent, state-of-the-art reasoning and vision	Pro+
GPT-5 Mini	OpenAI	Fast, cost-efficient GPT-5 for well-defined tasks	All plans
GPT-5 Nano	OpenAI	Ultra-fast, cheapest GPT-5 for summarization and classification	All plans
Gemini 2.0 Flash	Google	Very fast, good for high-volume tasks	All plans
Gemini 2.5 Pro	Google	Strong reasoning with large context window	Pro+
Gemini 2.0 Flash Lite	Google	Ultra-fast, most cost-effective	All plans
DeepSeek V3	DeepSeek	Extremely cost-effective, strong coding and math	All plans
DeepSeek R1	DeepSeek	Advanced chain-of-thought reasoning	All plans
Qwen Max	Alibaba	Strong multilingual, good for Asian language tasks	All plans
Qwen Plus	Alibaba	Cost-effective general-purpose, fast inference	All plans
Mistral Large	Mistral	Strong European model, multilingual and efficient	All plans
Mistral Small	Mistral	Fast and lightweight, great for high-volume tasks	All plans
Llama 3.3 70B	Meta (via Groq)	Open-source, ultra-fast inference via Groq	All plans
Ollama — Llama 3.3	Self-hosted	Runs locally on your VM, completely free	All plans
Grok 3	xAI	Real-time knowledge, strong for current events	All plans
Grok 3 Mini	xAI	Lightweight Grok, fast responses	All plans
Kimi K2	Moonshot	Large context window, multilingual	All plans
Moonshot v1 128K	Moonshot	128K context, good for long documents	All plans

Switching Models#

To change your AI model:

Open the Dashboard and navigate to Settings
Click Change model under the AI Model section
Browse models grouped by provider — each model shows badges like Latest, Fast, Cheap, or Free to help you compare
Select your model and click Save & Rebuild

The rebuild takes 2-4 minutes. Your chat history and memories are preserved — only the VM is recreated with the new model configuration.

💡

Starter plan restrictions

The Starter plan ($29/mo) does not include access to Claude Opus 4.6, GPT-5, GPT-5.2, or Gemini 2.5 Pro. Upgrade to Pro ($59/mo) or higher to use all models.

Self-Hosted Models (Ollama)#

Ollama models run directly on your agent's VM — no external API key required. This means zero per-message cost and complete data privacy. The trade-off is that inference speed depends on your server tier's hardware. Performance or Enterprise plans are recommended for self-hosted models.

Bring Your Own API Key#

You can provide your own API key for any supported provider — Anthropic, OpenAI, Google, DeepSeek, Alibaba Cloud (Qwen), Mistral, Groq (Llama), xAI (Grok), or Moonshot. When configured, your agent will use your key instead of the Lobstack default. This gives you full control over billing and rate limits. The Settings panel automatically detects your model's provider and shows the correct key format.

To add your API key:

Go to Settings in your dashboard
Click Add API Key
Paste your key and click Save & Rebuild

✅

Key security

Your API key is sent securely to your VM and stored in the agent config on your server. It is never stored in the Lobstack database in plain text. You can clear or change it at any time.

Message Overage Pricing#

If you exceed your plan's monthly message limit, overage charges apply per message based on the model:

Model	Provider	Overage / Message
Claude Sonnet 4.5	Anthropic	$0.02
Claude Opus 4.6	Anthropic	$0.05
GPT-4o	OpenAI	$0.02
GPT-5	OpenAI	$0.03
GPT-5.2	OpenAI	$0.04
GPT-5 Mini	OpenAI	$0.015
GPT-5 Nano	OpenAI	$0.01
Gemini 2.5 Pro	Google	$0.02
DeepSeek V3	DeepSeek	$0.005
DeepSeek R1	DeepSeek	$0.01
Qwen Max	Alibaba	$0.01
Qwen Plus	Alibaba	$0.005
Mistral Large	Mistral	$0.015
Mistral Small	Mistral	$0.005
Llama 3.3 70B	Meta / Groq	$0.005
Ollama (Llama 3.3)	Local (self-hosted)	Free
Grok 3	xAI	$0.02
Grok 3 Mini	xAI	$0.01
Kimi K2	Moonshot	$0.01
Moonshot v1 128K	Moonshot	$0.015

Model Routing#

Lobstack automatically routes your selected model to the correct provider API. When using the OpenClaw gateway, models are mapped to provider-prefixed identifiers (e.g., anthropic/claude-opus-4-6). This happens transparently — you just select the model name in your dashboard.

Templates Library Memory System