RouterBase API

About RouterBase API

RouterBase provides a unified, OpenAI-compatible API for accessing over 200 AI models from providers including OpenAI, Anthropic, Google DeepMind, Meta, Mistral, DeepSeek, Qwen, xAI, Cohere, Stability AI, Runway, Suno, ElevenLabs, and Black Forest Labs. Developers integrate by swapping the base URL in an existing OpenAI SDK configuration, with no provider-specific rewrites required. The service covers chat, image, video, and audio models, and supports streaming, tool calling, vision inputs, JSON mode, and prompt caching consistent with each provider's native API behavior.

The platform includes smart routing to select a provider by price, latency, or availability per request, automatic fallback between providers on failure, and unified billing across all connected providers in a single invoice. Usage analytics track spend by model, key, or project, with CSV export and API-based querying. Official SDKs are available for Python, Node.js, Go, and Ruby, and the OpenAI SDK works directly through a base URL change; tools such as LangChain, LlamaIndex, the Vercel AI SDK, Cursor, and Continue can connect through their existing OpenAI provider configuration.

Pricing follows a pass-through token cost model plus a flat platform fee, with no model-specific markups. Users can set per-key monthly spend caps and near-cap rate-limit webhooks. A free tier is available with a default limit of 60 requests per minute, while Pro and Enterprise tiers offer higher configurable limits. BYOK (bring your own key) is supported for OpenAI, Anthropic, and Google, allowing token costs to pass through to the user's own provider account while retaining any committed-spend discounts. Data can be processed in EU, US, or APAC regions, with region pinning and per-key region locks available on Enterprise plans, and prompts are not used for model training, with zero-retention flags applied where supported upstream.

Key features

• OpenAI-compatible API routing to 200+ models from OpenAI, Anthropic, Google, Meta, Mistral, DeepSeek, xAI and more
• Smart routing that auto-selects provider by price, latency or availability per request
• Automatic fallback to another provider within milliseconds if the primary fails
• Unified billing across all providers with a single invoice
• Usage analytics with spend tracking by model, key or project, exportable to CSV or API
• BYOK support for OpenAI, Anthropic and Google with flat platform fee and pass-through token costs

Frequently asked questions