# to11

## Docs

- [What is to11?](https://to11.ai/docs/get-started/index.md): What to11 is, who it's for, and how it fits your AI stack.
- [Quickstart](https://to11.ai/docs/get-started/quickstart.md): Send your first traced LLM request through to11 in a few minutes.
- [Core Concepts](https://to11.ai/docs/get-started/concepts.md): The mental model behind to11: the Organization, Workspace, and Project hierarchy, the gateway and its routing primitives, and the observability data plane.
- [Instrumentation](https://to11.ai/docs/instrument/overview.md): Get your application's LLM calls into to11 — automatically through the gateway, or by sending OpenTelemetry spans directly.
- [Telemetry](https://to11.ai/docs/instrument/telemetry.md): How to11 captures every LLM call as an OpenTelemetry-native GenAI trace, the OTel GenAI semantic conventions it follows, and the ten supported operation names.
- [Span Attributes](https://to11.ai/docs/instrument/span-attributes.md): Complete reference for every OpenTelemetry span attribute emitted by the gateway.
- [Context Propagation](https://to11.ai/docs/instrument/context-propagation.md): How to attach session metadata, tool execution, retrieval, and agent context to your LLM requests.
- [Distributed Tracing](https://to11.ai/docs/instrument/distributed-tracing.md): How to group LLM calls and agent-to-agent communication under a single trace.
- [Direct Ingestion](https://to11.ai/docs/instrument/direct-ingestion.md): How to send custom OpenTelemetry spans directly to the to11 collector from any OTel SDK.
- [Content Capture](https://to11.ai/docs/instrument/content-capture.md): How prompt and completion recording works in GenAI telemetry spans, and where to view captured content.
- [Metrics](https://to11.ai/docs/instrument/metrics.md): The GenAI metrics to11 records — names, units, and dimensions — and where you view them.
- [Deploy](https://to11.ai/docs/deploy/overview.md): How the to11 gateway routes, secures, and traces your LLM traffic.
- [Providers](https://to11.ai/docs/deploy/concepts/providers.md): What a connected provider is in to11, how its base URL, authentication, and model list work, and how providers relate to the routing layers.
- [Connect a provider](https://to11.ai/docs/deploy/concepts/connect-provider-drawer.md): Add a model provider to a project: enter a credential, name the connection, choose environments, and select models.
- [Models](https://to11.ai/docs/deploy/concepts/models.md): How a connected provider's model list works in to11, and how models are chosen when you build a routing rule.
- [Targets](https://to11.ai/docs/deploy/concepts/targets.md): What a target is in to11 — a model paired with a stored credential — and how targets feed managed routing.
- [Routes](https://to11.ai/docs/deploy/concepts/routes.md): What a route is in to11 — a model name mapped to a strategy and a set of targets — and how strategies control which target a request goes to.
- [Functions](https://to11.ai/docs/deploy/concepts/functions.md): Decouple what your application asks for from which model serves it, so you can swap models without changing code.
- [Routing Overview](https://to11.ai/docs/deploy/routing/overview.md): How the to11 gateway resolves a request through three routing layers: passthrough, managed routing, and function dispatch.
- [Passthrough Routing](https://to11.ai/docs/deploy/routing/passthrough.md): How the to11 gateway proxies a request straight to a provider in L1 passthrough mode, and how that relates to bring-your-own-key credentials.
- [Direct Routing](https://to11.ai/docs/deploy/routing/simple.md): Route a model to a single managed target so callers can use it without supplying their own provider key.
- [Weighted Routing](https://to11.ai/docs/deploy/routing/weighted.md): Split LLM traffic across multiple targets using weighted random selection.
- [Fallback Routing](https://to11.ai/docs/deploy/routing/fallback.md): Configure automatic failover so the gateway tries the next target when the current one fails.
- [Route by a stable name](https://to11.ai/docs/deploy/routing/functions.md): Call a stable route name instead of a model name, so you can swap the model behind it without changing application code.
- [A/B experiment](https://to11.ai/docs/deploy/routing/experiment.md): Split traffic across model variants for the same task and compare them in production.
- [Environments](https://to11.ai/docs/deploy/environments.md): Separate production from staging within a project using environments.
- [Promotion Policies](https://to11.ai/docs/deploy/promotion-policies.md): Govern how configuration changes move from one environment into the next.
- [Release Approvals](https://to11.ai/docs/deploy/release-approvals.md): Require review and sign-off before a routing or prompt change goes live.
- [Scheduled Changes](https://to11.ai/docs/deploy/scheduled-changes.md): See the provider and routing changes queued to apply later.
- [Observe](https://to11.ai/docs/observe/overview.md): See what your LLM application is doing in production.
- [Traces](https://to11.ai/docs/observe/traces.md): Explore and filter the requests flowing through your project.
- [Evaluate](https://to11.ai/docs/evaluate/overview.md): Measure and compare the quality of your LLM application. Coming soon.
- [Platform Administration](https://to11.ai/docs/platform/overview.md): Administer your organization: structure, members, access, API keys, and audit.
- [Data Centers](https://to11.ai/docs/platform/data-centers.md): Where to11 runs your data.
- [Organizations](https://to11.ai/docs/platform/organizations.md): Create and manage the top-level tenant that owns your members, roles, and API keys.
- [Workspaces](https://to11.ai/docs/platform/workspaces.md): Group related projects within an organization.
- [Projects](https://to11.ai/docs/platform/projects.md): Manage the individual applications that own providers, routing, environments, and traces.
- [Team](https://to11.ai/docs/platform/team.md): Invite people to your organization, manage the roster, and handle pending invitations.
- [Roles & Permissions](https://to11.ai/docs/platform/roles-and-permissions.md): Control what each member can do with roles, a permission catalog, per-user overrides, and trace access.
- [API Keys](https://to11.ai/docs/platform/api-keys.md): Create scoped API keys for programmatic access, and rotate or revoke them.
- [Authentication](https://to11.ai/docs/platform/authentication.md): How members sign in to to11 with a supported identity provider.
- [Audit Logs](https://to11.ai/docs/platform/audit-logs.md): Review a record of administrative and configuration changes, and export it.
- [Prompt Management](https://to11.ai/docs/platform/prompts/overview.md): What prompt management is, why prompts belong outside your application code, and how to11 versions, reviews, and releases them.
- [Authoring Prompts](https://to11.ai/docs/platform/prompts/authoring.md): The parts that make up a prompt version: blocks and their roles, few-shot examples, variables, conditions, tool definitions, and model config.
- [Versions & Releases](https://to11.ai/docs/platform/prompts/versions-and-releases.md): The Prompts list, statuses, immutable versioning, review, releasing to environments, and the permissions that gate each action.
- [Rendering Prompts](https://to11.ai/docs/platform/prompts/rendering.md): Render a released prompt version from your application at runtime, fill its variables, and send its messages and tools to the model.
- [Integrations](https://to11.ai/docs/integrations/overview.md): Connect to11 to your application through the LLM SDK you already use.
- [OpenAI SDK](https://to11.ai/docs/integrations/openai-sdk.md): How to use the OpenAI Python and Node.js SDKs with to11.
- [Anthropic SDK](https://to11.ai/docs/integrations/anthropic-sdk.md): How to use the Anthropic Python and TypeScript SDKs with to11.
- [Vercel AI SDK](https://to11.ai/docs/integrations/vercel-ai-sdk.md): How to use the Vercel AI SDK with to11.
- [TypeScript SDK](https://to11.ai/docs/reference/typescript-sdk.md): Install the to11 TypeScript SDK, render a prompt, and send it through the gateway.
- [Configuration](https://to11.ai/docs/reference/typescript-sdk/configuration.md): createClient options, credential resolution, and the provider-client helpers.
- [Sessions, conversations & turns](https://to11.ai/docs/reference/typescript-sdk/sessions-and-turns.md): Group gateway calls for tracing — from a single call to multi-agent.
- [Rendering prompts](https://to11.ai/docs/reference/typescript-sdk/rendering-prompts.md): Render a managed prompt, shape it per provider, or convert the neutral result.
- [Prompt management](https://to11.ai/docs/reference/typescript-sdk/prompts.md): Manage prompts, versions, labels, and the environments they serve into.
- [Errors](https://to11.ai/docs/reference/typescript-sdk/errors.md): The typed error classes the SDK throws, grouped by the surface that raises them.
- [Python SDK](https://to11.ai/docs/reference/python-sdk.md): Install the to11 Python SDK, render a prompt, and send it through the gateway.
- [Configuration](https://to11.ai/docs/reference/python-sdk/configuration.md): create_client options, credential resolution, and the provider-client helpers.
- [Sessions, conversations & turns](https://to11.ai/docs/reference/python-sdk/sessions-and-turns.md): Group gateway calls for tracing — from a single call to multi-agent.
- [Rendering prompts](https://to11.ai/docs/reference/python-sdk/rendering-prompts.md): Render a managed prompt, shape it per provider, or convert the neutral result.
- [Prompt management](https://to11.ai/docs/reference/python-sdk/prompts.md): Manage prompts, versions, labels, and the environments they serve into.
- [Errors](https://to11.ai/docs/reference/python-sdk/errors.md): The typed error classes the SDK raises, grouped by the surface that raises them.
- [Configuration Reference](https://to11.ai/docs/reference/configuration.md): Complete TOML configuration reference for the to11 AI Gateway — every section, field, type, and default.
- [API Reference](https://to11.ai/docs/reference/api.md): Gateway endpoints, headers, request/response formats, and error codes.
- [Providers](https://to11.ai/docs/reference/providers.md): Supported LLM providers, model routing, and format translation.
- [Streaming](https://to11.ai/docs/reference/streaming.md): How the gateway handles SSE streaming — fast-path passthrough vs normalized-path translation.
- [Error Handling](https://to11.ai/docs/reference/error-handling.md): How the gateway classifies, translates, and surfaces upstream provider errors across SDK formats.
- [Getting Help](https://to11.ai/docs/help/support.md): Where to get help with to11, ask questions, and report an issue.
- [Frequently Asked Questions](https://to11.ai/docs/help/faq.md): Common questions about using to11.

## OpenAPI Specs

- [openapi](https://to11.ai/docs/api-reference/openapi.json)