- Home
- LLM Gateway Software
- Routerly
Routerly
What it is
Routerly is a free, self-hosted gateway that routes requests from applications to AI providers, tracks costs, and enforces budgets. Its configurable routing policies cover model selection, cost, provider health and performance, capabilities, context, budgets, rate limits, and fairness. Routerly accepts OpenAI and Anthropic wire formats, including streaming, so compatible clients can connect by changing the base URL. Supported providers include OpenAI, Anthropic, Google Gemini, Ollama, Mistral, Cohere, xAI, and custom HTTP endpoints. It tracks per-token costs using built-in pricing presets or custom model pricing. Budgets can be set globally, per project, or per token, and can measure cost, calls, or token usage over rolling or calendar windows. Projects can have separate Bearer tokens, model pools, routing settings, and budget limits. Configuration and usage records are stored in JSON files, with no external database required. Deployment options include Docker and an installer that supports Windows, macOS, and Linux. The maker says prompts and API keys remain on the user's infrastructure; provider API keys and project tokens are AES-256 encrypted at rest, and passwords are bcrypt-hashed. The self-hosted software is licensed under AGPL-3.0 and adds no markup to API calls.
For and against
For
- Supports OpenAI and Anthropic formats with streaming
- Routes to named providers and custom endpoints
- Budgets can track costs, calls, or token use
- Self-hosted deployment requires no external database
Against
- Requires self-hosted deployment
- Software is licensed under AGPL-3.0
The verdict
Routerly combines provider routing, usage tracking, and budget controls in a self-hosted gateway. Its format compatibility and project-level settings are useful for managing AI requests, while deployment and licensing are factors to consider.
Who it suits
Routerly is aimed at developers, including SaaS teams and local-first development use cases. Its separate project settings and budgets may suit teams routing requests across multiple AI providers.
Plans and prices
Free self-hosted
Free · Self-hosted · No markup on API calls · AGPL-3.0
Read 30 Sep 2026 · routerly.ai
On the record
- API compatibility
- It supports OpenAI and Anthropic wire formats with streaming, so clients can use Routerly by changing the base URL.routerly.ai · read 30 Sep 2026
- Budget controls
- Budgets can be set globally, per project, or per token, and can track cost, calls, or token usage over rolling or calendar windows.doc.routerly.ai · read 30 Sep 2026
- Cost tracking
- Routerly tracks per-token costs and supports built-in pricing presets and custom model pricing.routerly.ai · read 30 Sep 2026
- Data handling
- Routerly is self-hosted, and its maker says prompts and API keys stay on the user's infrastructure.blog.routerly.ai · read 30 Sep 2026
- Deployment
- The maker provides Docker and installer-based deployment, and says the installer supports Windows, macOS, and Linux.routerly.ai · read 30 Sep 2026
- Integrations
- The site names Cursor, Open WebUI, OpenClaw, LangChain, and LlamaIndex as clients or frameworks that can connect to Routerly.routerly.ai · read 30 Sep 2026
- Intended users
- The site describes Routerly as built for developers and use cases ranging from indie projects to enterprise deployments, including SaaS teams and local-first development.routerly.ai · read 30 Sep 2026
- License and pricing
- Routerly is free to self-host under the AGPL-3.0 license, and the site says it adds no markup to API calls.routerly.ai · read 30 Sep 2026
- Product
- Routerly is a self-hosted gateway between applications and AI providers that routes requests, tracks costs, and enforces budgets.routerly.ai · read 30 Sep 2026
- Project isolation
- Each project can have separate Bearer tokens, model pools, routing configuration, and budget limits.routerly.ai · read 30 Sep 2026
- Providers
- Supported providers include OpenAI, Anthropic, Google Gemini, Ollama, Mistral, Cohere, xAI, and custom HTTP endpoints.routerly.ai · read 30 Sep 2026
- Routing
- Its routing engine uses up to nine configurable policies, including LLM selection, cost, health, performance, capability, context, budget, rate limits, and fairness.blog.routerly.ai · read 30 Sep 2026
- Security
- The documentation says provider API keys and project tokens are AES-256 encrypted at rest, and user passwords are bcrypt-hashed.doc.routerly.ai · read 30 Sep 2026
- Storage and dependencies
- Routerly stores configuration and usage records in JSON files and does not require an external database.doc.routerly.ai · read 30 Sep 2026
