Conifer offers Router
Product
Router is Conifer's routing decision leased on its own to harnesses and companies.
- Currently Offered
Router is Conifer's routing decision leased on its own to harnesses and companies.
Router is the routing decision offered on its own rather than bundled with the gateway. A team that builds a coding agent or runs a large volume of AI leases the decision and serves the request on its own keys, with the call going straight to the lab through the customer's own stack.
The POST /v1/route endpoint returns a pick and up to three fallbacks and then steps aside. Auto and balanced choose the best value among the models that will answer well, best chooses the most capable model regardless of cost, and a named model is always served as that model with nothing substituted behind an identifier the customer chose.
Weave Router is a drop-in proxy that routes each inference request to the lowest-cost model that answers at frontier parity.
IonRouter is a high-throughput, low-cost inference API and drop-in OpenRouter alternative powered by Cumulus Labs' IonAttention engine.
Hosted gateway for routing and governing traffic across hosted and self-hosted AI models.
Microsoft-Decision-1 is the decision model from Microsoft, delivered through Foundry, that answers bounded questions rather than generating text.
Clef is Cloudflare's open-weight decision model family that returns typed decisions through a Jev-compatible API.
Open source AI gateway routing every model behind one zero-markup OpenAI-compatible endpoint.
Cloudflare AI: serverless inference, agents, RAG, and secure runtime primitives on the global edge.
Control plane governing AI access, spend and observability across models, agents and tools.
Baseten Inference Stack for high performance with custom kernels, decoding, caching on optimized infra.
Secure enterprise portal for multiple large language model platforms with reusable language skills and usage-based pricing.
Train models on B200s, T4s and inference-optimized infra with one-click deploy to production.
Weave Router is a drop-in proxy that routes each inference request to the lowest-cost model that answers at frontier parity.
IonRouter is a high-throughput, low-cost inference API and drop-in OpenRouter alternative powered by Cumulus Labs' IonAttention engine.
Hosted gateway for routing and governing traffic across hosted and self-hosted AI models.
River API lets developers fine-tune and run reinforcement learning on open-weight models.
Microsoft-Decision-1 is the decision model from Microsoft, delivered through Foundry, that answers bounded questions rather than generating text.
Clef is Cloudflare's open-weight decision model family that returns typed decisions through a Jev-compatible API.
Open source AI gateway routing every model behind one zero-markup OpenAI-compatible endpoint.
Fugu is a multi-agent orchestration API that routes complex tasks across a pool of frontier language models.
Cloudflare AI: serverless inference, agents, RAG, and secure runtime primitives on the global edge.
Control plane governing AI access, spend and observability across models, agents and tools.
Baseten Inference Stack for high performance with custom kernels, decoding, caching on optimized infra.
Custom AI model builder for enterprise infrastructure.
Adaptive OpenAI-compatible endpoint coordinating open-weight models for chat and agents.
Cloud networking gateway for routing, securing, transforming, and observing application traffic.
Replicate is a platform for running machine learning models via a simple cloud API, direct competitor to Cloudflare AI inference.
Secure enterprise portal for multiple large language model platforms with reusable language skills and usage-based pricing.
Train models on B200s, T4s and inference-optimized infra with one-click deploy to production.
