# Dari

- [Dari Overview](https://docs.dari.dev/index.md): Use Dari's managed router or build and self-host your own.
- [Install the Dari CLI](https://docs.dari.dev/install-cli.md): Install the CLI for managing Dari routers from your terminal.
- [Router Quickstart](https://docs.dari.dev/router/quickstart.md): Send your first request through Dari's default model router.
- [Create A Router](https://docs.dari.dev/router/create-a-router.md): Create an endpoint that routes across your enabled models.
- [Configure Models](https://docs.dari.dev/router/configure-models.md): Choose the models and reasoning levels a router may select.
- [Configure Provider Credentials](https://docs.dari.dev/router/configure-provider-keys.md): Save provider authentication once, then select it for routers and custom models.
- [Router Evals](https://docs.dari.dev/evals/overview.md): Add benchmark scores as evidence for model selection.
- [Claude Code](https://docs.dari.dev/router/coding-agents/claude-code.md): Run Claude Code through a Dari Router.
- [Codex](https://docs.dari.dev/router/coding-agents/codex.md): Run Codex through a Dari Router.
- [Pi](https://docs.dari.dev/router/coding-agents/pi.md): Run Pi through a Dari Router.
- [Chat Completions API](https://docs.dari.dev/router/send-chat-completions.md): Send OpenAI-compatible Chat Completions requests through a router.
- [OpenAI Responses API](https://docs.dari.dev/router/send-responses.md): Send OpenAI Responses requests through a router.
- [Anthropic Messages API](https://docs.dari.dev/router/send-anthropic-messages.md): Send Anthropic Messages requests through a router.
- [How Routing Works](https://docs.dari.dev/router/overview.md): Understand Dari's managed router and default endpoint.
- [Speculative Routing](https://docs.dari.dev/router/speculative-routing.md): Reduce follow-up latency by selecting the next route alongside the current response.
- [Activity Overview](https://docs.dari.dev/router/model-activity.md): Inspect routed usage, spend, savings, tokens, and cache activity from the CLI.
- [Models & Routing](https://docs.dari.dev/router/model-activity/models-routing.md): Compare model usage, cost, latency, outcomes, and route changes from the CLI.
- [People & Keys](https://docs.dari.dev/router/model-activity/people-keys.md): List routed activity by attributed person and API key from the CLI.
- [Conversations](https://docs.dari.dev/router/model-activity/conversations.md): List conversations and inspect their routed steps from the CLI.
- [Tools & Skills](https://docs.dari.dev/router/model-activity/tools-and-skills.md): Inspect observed tool and skill usage from the CLI.
- [Authentication](https://docs.dari.dev/authentication.md): Choose the credential for each Dari workflow.
- [API Keys](https://docs.dari.dev/api-keys.md): Create Routing and Management keys.
- [Router Framework](https://docs.dari.dev/framework/overview.md): Host one OpenAI- and Anthropic-compatible endpoint across multiple models.
- [Quickstart](https://docs.dari.dev/framework/quickstart.md): Build and run a router with a local policy and executor.
- [Models](https://docs.dari.dev/framework/models.md): Declare candidates and let the router filter them by capability.
- [Policies](https://docs.dari.dev/framework/policies.md): Choose an eligible model with a local function, selector, or hosted service.
- [Pi Runtime](https://docs.dari.dev/framework/pi-runtime.md): Execute catalog models with Dari's built-in provider adapter.
- [Custom Executors](https://docs.dari.dev/framework/custom-executors.md): Connect models to your own SDK, service, or transport.
- [Protocols And Streaming](https://docs.dari.dev/framework/protocols-and-streaming.md): Use OpenAI Chat Completions and Anthropic Messages with one normalized router.
- [Prompt Caching](https://docs.dari.dev/framework/prompt-caching.md): Keep a warm model when switching would cost more than it saves.
- [Auto Router](https://docs.dari.dev/framework/auto-router.md): Use Dari's hosted selection policy with your own executors.
- [Jev Router](https://docs.dari.dev/framework/jev-router.md): Route with TypeSafe's Jev System One model instead of Dari's trained routing policy.
- [Operations](https://docs.dari.dev/framework/operations.md): Run a reliable router across requests, replicas, and provider failures.
- [Speculative Routing](https://docs.dari.dev/framework/speculative-routing.md): Overlap a likely execution with an advanced policy selection.
- [Decision Pipeline](https://docs.dari.dev/framework/decision-pipeline.md): Use the advanced policy-engine phases when selection needs orchestration.
- [Router API Overview](https://docs.dari.dev/api-reference/router/overview.md): Send routed model traffic over HTTP.
- [Chat Completions API](https://docs.dari.dev/api-reference/router/chat-completions.md): Send a routed OpenAI-compatible chat completion request
- [Responses API](https://docs.dari.dev/api-reference/router/responses.md): Send a routed OpenAI Responses request
- [Anthropic Messages API](https://docs.dari.dev/api-reference/router/messages.md): Send a routed Anthropic Messages request
- [Request Costs](https://docs.dari.dev/api-reference/router/request-costs.md): Look up model reference costs for your routed requests without performing inference.
- [Management API Overview](https://docs.dari.dev/api-reference/managed/overview.md): Manage routers, keys, credentials, evals, organizations, and activity over HTTP.
- [Routing Activity API](https://docs.dari.dev/api-reference/managed/activity.md): Read routing telemetry for one organization.
- [Activity Filter Options](https://docs.dari.dev/api-reference/managed/activity/filter-options.md): List users, API keys, routers, models, and providers available to activity filters.
- [Activity Overview](https://docs.dari.dev/api-reference/managed/activity/overview.md): Usage, spend, savings, tokens, cache, model mix, key sources, and API-key activity.
- [Model Activity](https://docs.dari.dev/api-reference/managed/activity/models.md): Per-model usage, cost, latency, outcomes, pricing coverage, and route transitions.
- [People & Keys](https://docs.dari.dev/api-reference/managed/activity/people.md): List routed activity attributed to people and API keys.
- [Conversations](https://docs.dari.dev/api-reference/managed/activity/conversations.md): List routed conversations and inspect their model steps.
- [Tools & Skills](https://docs.dari.dev/api-reference/managed/activity/tools-and-skills.md): Read observed tool and skill usage, inventories, and capability details.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.