One Tokaroo key
Authenticate from a server or trusted harness. Permanent keys never belong in browser or mobile bundles.
Your application asks Tokaroo for Max, Pro, Auto, Fast, or Basic. Tokaroo makes the optimized routing decision, handles compatible fallback, meters the result, and returns the response in the format your software expects.
Keep your application, agent harness, tools, files, and execution environment. Replace separate model accounts and provider-specific routing code with one managed connection.
Authenticate from a server or trusted harness. Permanent keys never belong in browser or mobile bundles.
Choose the result you need instead of maintaining a catalog of vendor model IDs.
Tokaroo weighs compatibility, measured quality, price, speed, health, and availability across its managed provider network.
See the requested Tokaroo mode, token counts, latency, charge, balance, and aggregate benchmark savings.
Quality ratios compare candidates with the best freshly measured route for the task family. They are routing thresholds, not statistical percentiles.
The hardest and highest-stakes work where capability is the first requirement.
Serious daily technical, business, production, and customer-facing work.
The default for applications that want Tokaroo to make the whole routing decision.
Rapid answers, edits, extraction, and interactive back-and-forth.
Everyday questions and routine tasks where you need an answer, not a project.
The percentages are conservative fallback floors. With enough fresh, diverse evaluations, Tokaroo derives task-specific quality bands dynamically and optimizes inside the qualifying basket.
Quality is measured separately for reasoning, code, math, reading, writing, tools, multilingual, and spatial work.
The best fresh measured output in that task family becomes the 100% quality ceiling.
Only compatible candidates clearing the requested mode's quality checks enter its decision basket.
Tokaroo then weighs speed, price, reliability, context, tools, and availability inside that basket.
Awaiting fresh evidence | Conservative fallback floors
Awaiting fresh evidence | Conservative fallback floors
Awaiting fresh evidence | Conservative fallback floors
Awaiting fresh evidence | Conservative fallback floors
Awaiting fresh evidence | Conservative fallback floors
Awaiting fresh evidence | Conservative fallback floors
Awaiting fresh evidence | Conservative fallback floors
Awaiting fresh evidence | Conservative fallback floors
Evaluation evidence is limited to successful Tokaroo tests in the latest 30-day window; imported zero-sample signals are excluded. Basket membership, the concrete serving model, the serving provider, and private settlement cost remain internal.
Use Tokaroo directly or point an existing provider client at the matching base URL. LangChain and the Vercel AI SDK are optional client channels, not gateway dependencies.
Native HTTP, JSON, server-sent events, and WebSocket routes.
Use existing OpenAI clients with a base URL and key change.
Messages, tool use, streaming, and token counting for Claude-oriented clients.
GenerateContent, streamGenerateContent, and countTokens.
The researched catalog changes as availability, verified pricing, and compatibility change. Your five Tokaroo model names remain stable.
A useful router must do more than proxy a response. Tokaroo owns the route decision, compatible retry path, and request ledger.
Candidates must support the request's wire, tools, context, modality, and output constraints before they can be ranked.
Unhealthy or incompatible routes are excluded, and eligible provider fallback is handled behind the same response format.
Quality, latency, reliability, and verified price inputs inform optimized routing instead of a static vendor list.
Tokaroo mode, charge, tokens, latency, and aggregate benchmark savings are recorded against the key and workspace.
Applications ask for one of five Tokaroo modes while the underlying provider catalog can improve without application changes.
Native model families can be preferred for proven tool loops, but only inside the selected quality band and without removing compatible fallback.
These products clarify Tokaroo's role without turning Tokaroo into a hosted harness platform.
Gwen selects and runs agent harnesses, then sends their model traffic through Tokaroo. Gwen owns orchestration and execution; Tokaroo owns optimized model routing, fallback, and metering.
Tokaroo routes speech, transcription, realtime audio, and avatars through Raspy. Images and video use compatible routes from the broader model network.
Start with Auto and let Tokaroo make the routing decision.