Receive the request
Your application sends a compatible request with a CostRouter API Key. The model name, message payload, and client workflow stay close to the SDK patterns you already use.
CostRouter replaces separate provider subscriptions with cost-aware routing and usage-based billing. Fund one balance, access every connected model through one API key, and pay only for actual usage.
Use one API for GPT, Claude, Gemini, DeepSeek, and more with transparent usage-based pricing and cost-aware routing.
Route Codex, Claude Code, Gemini CLI, Cursor, and custom coding agents through your CostRouter API key.
CostRouter receives a compatible API request, matches available model routes, selects a qualified path by price, latency, and availability, then returns a standard response with usage records.
Your application sends a compatible request with a CostRouter API Key. The model name, message payload, and client workflow stay close to the SDK patterns you already use.
CostRouter checks the requested model, endpoint capability, account configuration, and live channel status to find routes that can handle the request.
Among eligible routes, CostRouter weighs price, latency, and availability, then prioritizes a lower-cost path only when it meets the required reliability conditions.
The response is returned in a compatible format, while request status, token usage, and cost are recorded for usage logs, billing review, and later optimization.
CostRouter keeps routing, billing, and access rules visible so cost optimization stays auditable and controllable.
Review request logs, token usage, final charges, refunds, and billing records from the dashboard.
Set quotas, expiration, model limits, IP allowlists, and group routing rules for each API Key.
Routing decisions consider cost, latency, and availability, with account controls for advanced routing behavior.
Review supported models, live prices, route availability, and regional restrictions before production use.
Answers for pricing, compatibility, model routing, partner supply and production use.
Yes. OpenAI-compatible routes use familiar OpenAI-style request formats. In most cases, you point your existing SDK or HTTP client to the CostRouter base URL and use your CostRouter API Key.
CostRouter compares qualified routes in real time. When a lower-cost route is available and meets reliability requirements, requests can be sent through that route.
No. A single CostRouter API Key can access multiple supported models. Request formats stay close to the relevant provider style, depending on model capability, account permissions, and route availability.
Yes. You can request a specific model by name, or use routing rules that balance price, speed and availability for your workload.
Open Models to browse current model availability, provider details, endpoints, groups and pricing information.
No. It is useful for indie builders, startups, enterprise teams, agent workflows, and route providers that want to publish reliable model capacity.
CostRouter is designed so qualified route providers can expose supported models, route availability, pricing, and capacity rules.
Most SDK or HTTP integrations only need configuration changes: update the base URL and use a CostRouter API Key. More complex workflows can keep existing tools while gradually adopting routing controls.
Choose the channel that best matches your request.