Skip to main content

​
What model name should I use?

Use model="isaac-0.2-2b-preview" for the latest hosted Isaac release (set provider="perceptron"), or drop to model="isaac-0.2-1b" when you need the lighter-weight variant. Swap the model to qwen3-vl-235b-a22b-thinking to call the hosted Qwen3 option without changing the rest of your code.

​
Do I have to self-host?

No. The hosted API is the fastest way to ship. Self-hosting is optional—pull the isaac-0.2-2b-preview weights, the isaac-0.2-1b weights, or the isaac-0.1 weights if you need to deploy on-prem or at the edge. The processor, tokenizer, and reference configs are included in each repo.

​
How do I stream partial results?

Use the stream=True flag (or the perceptron.question helper) to receive text.delta and points.delta events as the model reasons.

​
Why am I getting AuthError?

The SDK found no usable API key. Double-check that PERCEPTRON_API_KEY is set before running your script, or pass configure(api_key="sk-live-...") inline. If you use .env, call load_dotenv() before invoking configure. Still stuck? Contact support with logs or share a repro in our Discord.