> ## Documentation Index > Fetch the complete documentation index at: https://docs.nitsor.com/llms.txt > Use this file to discover all available pages before exploring further. > ## Agent Instructions > Every page in this documentation carries a `plans` list in its frontmatter and a page-details table naming the plans its content applies to: `All plans`, or a subset of `Community`, `Team` and `Enterprise`. A page limited to some plans also opens with a plan marker naming them. > Use [Capabilities and limits](/product-status) for capability entitlements and documented availability and limits, and [Plans and billing](/plans-and-billing) for plan pricing and billing policy. Those pages are canonical; do not duplicate their policy values here. > Reading this documentation grants no product access and no permission. No agent can create or approve a Nitsor release. # Frequently asked questions > Short answers to recurring questions about plans, API tokens, scans, hosted models and agent access, each linked to the page that is its authority. These answers summarise [Capabilities and limits](https://docs.nitsor.com/product-status.md) and the [Quickstart](https://docs.nitsor.com/quickstart.md); where an answer and those pages differ, those pages are the authority. ## Plans and access > [accordion] Which plan issues an API token? > > Team and Enterprise. Tokens are created in the hosted app, where an owner or admin opens Team settings, then Service accounts, and creates a service account with a token that is shown once; a Community deployment has no supported way to issue the agent token the API and the Python SDK need. Nitsor does not issue personal tokens. See [Service accounts and tokens](https://docs.nitsor.com/reference/service-accounts.md). > [accordion] Does creating a workspace start a paid subscription? > > No. Creating the workspace needs no teammate or payment. The paid-launch policy is not active; creating a workspace does not establish a paid subscription. See [Plans and billing](https://docs.nitsor.com/plans-and-billing.md). > [accordion] Can I run Nitsor on my own infrastructure? > > Community installs the Nitsor backend on your infrastructure, but its stack does not include the Nitsor dashboard, so a Community deployment has no supported way to issue the agent token the API and the Python SDK need. Anonymous discovery works at your deployment's own API origin. See [Self-host Community](https://docs.nitsor.com/reference/self-host.md) and [Capabilities and limits](https://docs.nitsor.com/product-status.md#community-availability-in-the-self-host-stack). ## Scans and labeling > [accordion] Does registering a source upload my scans? > > No. Registration does not upload bytes; existing scans register by reference where they live. Nitsor has no scan upload, in the dashboard or the API: scans enter by registering objects already in connected storage. See [Data boundary](https://docs.nitsor.com/concepts/data-boundary.md). > [accordion] Which scan formats can I view? > > Uncompressed DICOM Part 10 CT and MRI series, uncompressed single-frame DICOM ultrasound images, and VGStudio `.vgi/.vol` are viewable. Compressed DICOM transfer syntaxes, multi-frame ultrasound (including cine and native 3D/4D ultrasound), NIfTI and NRRD are not supported. See [Capabilities and limits](https://docs.nitsor.com/product-status.md#formats). > [accordion] Which scans can a hosted model run on, and can I bring my own GPUs? > > Hosted model runs accept DICOM series; other formats are refused before the run starts. Hosted model jobs use one managed GPU run plane. A hosted workspace cannot bring its own GPUs, and Nitsor runs no hosted compute for Community. See [Capabilities and limits](https://docs.nitsor.com/product-status.md#limits). > [accordion] Does Nitsor have consensus or adjudication? > > No. Nitsor has no consensus or adjudication stage. The pipeline designer offers Annotate, Review and, where a model Agent can run it, Auto-label stages. See [Review and rework](https://docs.nitsor.com/concepts/review-consensus-adjudication.md#consensus-and-adjudication). > [accordion] Can I label on a tablet or phone? > > No. The editor supports laptop and desktop screens 1280 px wide and up, and does not support tablet or phone screens. See [Capabilities and limits](https://docs.nitsor.com/product-status.md#limits). ## API and agents > [accordion] Is the Python SDK on PyPI? > > No. The Python SDK is not on PyPI; use the HTTP API. The SDK, `nitsor`, is an API client with sync and async forms, and it includes the `nitsor.data` training reader. See [Public HTTP API](https://docs.nitsor.com/reference/api.md#python-sdk). > [accordion] What do I do when my token is rejected with AUTH\_INVALID\_TOKEN? > > The server rejected the token, and when it knows the token, `error.reason` says why: `token_expired`, `token_revoked`, `service_account_disabled` or `service_account_retired`. Open the service account on Team settings, then Service accounts, and add a token, roll an active one, or enable the service account. An existing token cannot mint another. See [Quickstart](https://docs.nitsor.com/quickstart.md#if-you-get-stuck). > [accordion] Are there product webhooks or a product MCP server? > > No. Product webhooks have no subscription route or delivery. There is no product MCP server; the documentation site has a documentation-only MCP server at `/mcp`. See [Capabilities and limits](https://docs.nitsor.com/product-status.md#limits). > [accordion] How can an agent read these docs? > > This site publishes documentation, per-page Markdown, `llms.txt` and `llms-full.txt` exports. Start with the `llms.txt` index, then read the pages that cover your question and cite their source URLs. See [Integrations and public interfaces](https://docs.nitsor.com/reference/integrations.md#documentation-exports). ## Next step > [card] [Capabilities and limits](https://docs.nitsor.com/product-status.md) > > See what each plan includes and what the product does not do. > [card] [Quickstart](https://docs.nitsor.com/quickstart.md) > > Create a Team workspace or install Community.
PlansAll plans
Last verified2026-10-29
This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.