AI Models
Lobstack supports 30+ AI models across every major provider. Switch models anytime from your dashboard — models are grouped by provider with badges for quick comparison.
Meet Lobstack 1.2 — our flagship model
Current Generation (July 2026)#
| Model | Provider | Tier | Context Window | Notes |
|---|---|---|---|---|
| Lobstack 1.2 (flagship) | Lobstack | Managed | — | Token Intelligence routes to the best engine per message. No API key needed. |
| Claude Opus 5 | Anthropic | Flagship | 1M | Most capable — complex reasoning, analysis, and agentic work |
| GPT-5.6 Sol | OpenAI | Flagship | 1M | OpenAI's flagship — state-of-the-art coding and reasoning |
| DeepSeek V4 Pro | DeepSeek | Flagship | 1M | Flagship-class reasoning at a fraction of the price |
| Gemini 3.1 Pro | Premium | 1M | Strong multimodal reasoning with long context | |
| GPT-5.6 Terra | OpenAI | Premium | 1M | Balanced GPT-5.6 variant for demanding everyday work |
| Grok 4.5 | xAI | Premium | 500K | Real-time knowledge, strong for current events |
| Qwen 3.7 Max | Alibaba | Premium | 1M | Strong multilingual, excellent for Asian-language tasks |
| Mistral Medium 3.5 | Mistral | Premium | 128K | Efficient European model, multilingual |
| Claude Sonnet 5 | Anthropic | Standard | 1M | Best balance of capability and speed — recommended default |
| Gemini 3.5 Flash | Standard | 1M | Very fast, great for high-volume tasks | |
| Qwen 3.7 Plus | Alibaba | Standard | 1M | Cost-effective general-purpose, fast inference |
| DeepSeek V4 Flash | DeepSeek | Standard | 128K | Extremely cost-effective, strong coding and math |
| Claude Haiku 4.5 | Anthropic | Small | 200K | Fast and light for well-defined tasks |
| GPT-5.6 Luna | OpenAI | Small | 1M | Fast, cost-efficient GPT-5.6 for simpler tasks |
| Grok 4.1 Fast | xAI | Nano | 2M | Ultra-fast and cheap with a huge context window |
Previous Generation#
These models remain available for existing agent configurations. New agents should prefer the current generation above.
| Model | Provider | Tier | Context Window | Notes |
|---|---|---|---|---|
| Claude Opus 4.6 | Anthropic | Flagship | 1M | Previous Anthropic flagship |
| GPT-5.2 | OpenAI | Flagship | 256K | Previous OpenAI flagship |
| GPT-5 | OpenAI | Premium | 256K | Advanced coding and complex reasoning |
| Mistral Large | Mistral | Premium | 128K | Strong European model, multilingual |
| Qwen Max | Alibaba | Premium | 32K | Strong multilingual |
| DeepSeek R1 | DeepSeek | Premium | 1M | Retired by DeepSeek — automatically routes to DeepSeek V4 Pro |
| Claude Sonnet 4.5 | Anthropic | Standard | 200K | Previous-generation Sonnet |
| GPT-4o | OpenAI | Standard | 128K | Strong general-purpose, multimodal |
| Gemini 2.5 Pro | Standard | 1M | Strong reasoning with large context window | |
| Llama 3.3 70B | Meta (via Groq) | Standard | 128K | Open-source, ultra-fast inference via Groq |
| Grok 3 | xAI | Standard | 131K | Previous-generation Grok |
| GPT-5 Mini | OpenAI | Small | 256K | Fast, cost-efficient for well-defined tasks |
| DeepSeek V3 | DeepSeek | Small | 128K | Retired by DeepSeek — automatically routes to DeepSeek V4 Flash |
| Qwen Plus | Alibaba | Small | 128K | Cost-effective general-purpose |
| GPT-5 Nano | OpenAI | Nano | 128K | Ultra-fast, cheapest for summarization and classification |
| Mistral Small | Mistral | Nano | 128K | Fast and lightweight, great for high-volume tasks |
DeepSeek endpoint migration (July 2026)
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
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
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 Opus 5 | Anthropic | $0.05 |
| GPT-5.6 Sol | OpenAI | $0.04 |
| DeepSeek V4 Pro | DeepSeek | $0.01 |
| Gemini 3.1 Pro | $0.02 | |
| GPT-5.6 Terra | OpenAI | $0.03 |
| Grok 4.5 | xAI | $0.02 |
| Qwen 3.7 Max | Alibaba | $0.01 |
| Mistral Medium 3.5 | Mistral | $0.015 |
| Claude Sonnet 5 | Anthropic | $0.02 |
| Gemini 3.5 Flash | $0.015 | |
| Qwen 3.7 Plus | Alibaba | $0.005 |
| DeepSeek V4 Flash | DeepSeek | $0.005 |
| Claude Haiku 4.5 | Anthropic | $0.01 |
| GPT-5.6 Luna | OpenAI | $0.015 |
| Grok 4.1 Fast | xAI | $0.005 |
| Previous-generation models | Various | $0.005 – $0.05 (unchanged) |
Model Routing#
The Lobstack Agent Runtime automatically routes your selected model to the correct provider API. Internally, models are mapped to provider-prefixed identifiers (e.g., anthropic/claude-opus-5). This happens transparently — you just select the model name in your dashboard.