Providers

The Supervertaler Assistant supports multiple AI providers. You only need one to get started.

Switching Models

The current provider and model are shown in the status area at the bottom of the chat panel. You can switch models in two ways:

• Quick switch – click the provider/model label directly. A dropdown menu appears with all available models grouped by provider. The current model is marked with a tick. Select a different model to switch instantly.
• Settings – open the settings dialogue (gear icon) and switch to the AI Settings tab for full configuration including API keys, endpoints, and advanced options.

Supported Providers

Provider	Models
OpenAI	GPT-6 Astra, GPT-6.1 Sol, GPT-6 Luna
Anthropic	Claude Sonnet 5.5, Claude Opus 5.5, Claude Fable 5.1
Google	Gemini 3.8 Flash, Gemini 3.5 Flash-Lite, Gemini 3.1 Pro (Preview)
Grok	Grok 4.3
Mistral	Mistral Large, Mistral Small
DeepSeek	DeepSeek V4 Pro, DeepSeek V4 Flash
OpenRouter	Claude, GPT, Gemini, DeepSeek, and 200+ others via a single API key
Ollama	TranslateGemma, Qwen 3, Aya Expanse (local, no API key needed)
Custom	Any OpenAI-compatible API endpoint

Note

If you want privacy or offline use, try Ollama with a local model. No API key or internet connection needed. Ollama models whose names end in -cloud are the exception: they run on Ollama’s servers, so your text leaves your computer.

If you prefer a single account that covers many providers, OpenRouter gives you access to 200+ models with one key.

Local models: what to expect

A local model keeps every word on your computer, but expect less than from the large cloud models. In a test on a published Dutch patent, Gemma 4 31B, about the largest model a well-equipped PC can run, wrote fluent and mostly accurate English, but its terminology drifted from one batch to the next, which broke the consistency of the claims. Models of 7 to 8 billion parameters were not good enough for patent work at all. Claude Opus 5.5 stayed consistent throughout.

• Speed: without a graphics card a local model is slow. Reading Supervertaler’s instructions before the first segment can take 10 to 15 minutes; a model of about 30 billion parameters needs around 24 GB of graphics memory to run at a usable speed.
• What narrows the gap: termbases ticked for AI, and house rules in SuperMemory. In the same test, a local model applied six patent conventions it had been getting wrong as soon as they were in the shared memory bank.
• Test it on your own work: SuperBench translates the same segments with three models and has a fourth judge them.

The full test, with every paragraph side by side, is on supervertaler.com: Can a local AI model translate a patent?

Choosing a Model

For everyday translation questions, a smaller and cheaper model like GPT-6 Luna, Gemini 3.5 Flash-Lite, or DeepSeek V4 Flash works well. For complex tasks like document analysis, prompt generation, or when you need the highest quality suggestions, use a larger model like Claude Sonnet 5.5, GPT-6 Astra, or DeepSeek V4 Pro.

Some features are provider-specific:

Feature	Availability
Studio Tools	All providers except Ollama. GPT-6.1 Sol only with your own OpenAI key, not through OpenRouter (from v18/19.20.201; in v18/19.20.199 and 200, not GPT-6.1 Sol at all)
Image attachments	All providers with vision support
Document attachments	All providers
Memory bank context	All providers

See Also

• Supervertaler – Overview
• AI Settings – API keys, endpoints, advanced options
• AI Cost Guide – Token pricing and cost estimates