OpenRouter

Custom tools work across the catalog: tool calling uses one request format for any tool capable model, Auto Exacto routes tool calling requests to the providers that handle them best, and the Agent SDK's tool() helper defines a customer's tools and executes them in the agent loop, including tools from MCP servers. An agent built on OpenRouter takes authenticated action in outside systems through the customer's own tools.

Sourceopenrouter.ai/docs/guides/features/tool-callingread 2026-09-22

The Agent SDK runs multi turn agent loops, calling tools and deciding the next step until a stop condition is met (step count, a specific tool call, maximum cost), and the subagent server tool lets a model hand self contained tasks to a worker model, optionally with its own tools, mid generation. No workflow definition, deterministic node or versioned flow is documented, so nothing lets a workflow mix deterministic nodes with agent steps.

Sourceopenrouter.ai/docs/agent-sdk/overviewread 2026-09-22

OpenRouter routes embedding requests to embedding models, and its RAG cookbook shows the customer building and storing their own index with those embeddings. The web search and web fetch server tools reach the public web, which is not the customer's corpus. No retrieval structure that OpenRouter maintains over the customer's own documents is documented; routing embedding calls maintains none.

Sourceopenrouter.ai/docs/api_reference/embeddingsread 2026-09-22

An approval gate ships in OpenRouter's Agent SDK (@openrouter/agent): a tool marked requireApproval pauses execution when the model calls it, so a person can approve or reject each call before it runs, and a StateAccessor carries approval decisions across separate request cycles, for example in a web application. Workspace guardrails also cap spend and restrict models and providers per member or key.

Sourceopenrouter.ai/docs/agent-sdk/call-model/tool-approval-stateread 2026-09-22

Access controls run deep: self serve SSO through Okta, Microsoft Entra ID, Google Workspace or any SAML provider on Enterprise plans, SCIM group mappings that grant workspace access from identity provider groups with an audit log of mapping and membership changes, workspaces that isolate API keys, routing defaults and guardrails per team, and per member and per key guardrails restricting models, providers and spend. The Enterprise page describes OpenRouter as SOC 2 compliant and GDPR compatible without naming a report, auditor or date.

Sourceopenrouter.ai/docs/guides/features/ssoread 2026-09-22

Every plan carries activity logs and export. Broadcast sends trace data for every API request, without instrumentation in the customer's code, to Arize AX, Braintrust, Datadog, Langfuse, LangSmith, Grafana, an OpenTelemetry collector, S3, a webhook and other destinations, configured per workspace by an organization admin.

Custom classifiers tag each generation with dimensions the customer defines, and the tags appear in the logs and roll up in the activity view; SCIM mapping changes keep a separate audit log. That gives step by step inspection of what the agent sent and received, audit records separate from runtime traces, and export to the customer's own tools.

Sourceopenrouter.ai/docs/guides/features/broadcastread 2026-09-22

The Agent SDK's StateAccessor persists conversation state (message history, tool results and approval decisions) between callModel invocations, and a hosted intern continues the same run when a later prompt carries its session_id. That is conversation state carried across turns of one conversation, and no memory layer with a stated scope and lifetime is documented.

Sourceopenrouter.ai/docs/agent-sdk/call-model/tool-approval-stateread 2026-09-22

In-Region Routing lets a buyer send requests through a region specific base URL (eu.openrouter.ai or us.openrouter.ai); the request is decrypted inside that region, routed only to provider endpoints there, and prompts and completions never leave it. It is available on the Business and Enterprise plans. Zero Data Retention routing also sends requests only to providers that do not retain data.

Sourceopenrouter.ai/docs/guides/features/in-region-routingread 2026-09-22

Ori Harness starts agent CLIs the customer already uses, such as Claude Code, Codex and OpenCode, with OpenRouter credentials and models; those agents are other vendors' products. Presets are saved request configurations, and Ori's built in skills set up and run Ori itself. No ready made workflows, templates or role specific agents of OpenRouter's own are documented.

Sourceopenrouter.ai/docs/guides/ori/harnessread 2026-09-22

The Ori runtime provides a built-in cron scheduler: features declare schedules, several per feature, that start headless runs with a durable event log, an overlap policy and optional jitter; schedules can catch up on runs missed during a restart and can be disabled without deletion, and ori schedules reports whether each timer is armed (Ori changelog). Those schedules start agent runs with no person initiating them.

Sourceopenrouter.ai/docs/guides/ori/changelogread 2026-09-22

Model and provider choice sit with the customer: the pricing page lists 500+ models from 80+ providers behind one API, and the Provider Routing page documents a provider object in each request that sets order, allowed and ignored providers, price, latency and throughput sorting and data policies, on top of default load balancing, model fallbacks, variants such as :nitro and :floor, and an auto router.

Sourceopenrouter.ai/docs/guides/routing/provider-selectionread 2026-09-22

OpenRouter documents a REST API with a full API reference, client SDKs for TypeScript, Python and Go, the @openrouter/agent Agent SDK, OAuth PKCE for apps that sign users in, Management API keys for programmatic key and spend control, and an Analytics API.

Sourceopenrouter.ai/docs/client-sdks/overviewread 2026-09-22

Ori Eval tests the customer's agent on real prompts from the customer's project: it writes an eval file, runs the models being compared with one harness and one model held fixed for each run so repeated runs use the same configuration, and returns scores and a recommendation; features can ship evaluations beside their code through the ori eval command. Retries and model fallbacks also sit in the routing layer.

Sourceopenrouter.ai/docs/guides/ori/evalread 2026-09-22

The web fetch server tool lets any model fetch a URL during a request: OpenRouter fetches and extracts the page, using the provider's native fetch where available and otherwise Exa, and returns the text to the model. That is a headless fetch with a third party engine wired in; no hosted browser, desktop session or remote computer control that an agent drives is documented.

Sourceopenrouter.ai/docs/guides/features/server-tools/web-fetchread 2026-09-22