
Weave Router
Weave Router is a drop-in proxy that routes each inference request to the lowest-cost model that answers at frontier parity.
- Currently Offered

Weave Router is a drop-in proxy that routes each inference request to the lowest-cost model that answers at frontier parity.
Weave Router is a standalone Go service that sits in front of model providers and speaks Anthropic Messages, OpenAI Chat Completions, and Gemini generateContent. It embeds each request with a small ONNX model, scores it against intent clusters, and dispatches to the cheapest candidate that has historically performed at parity with the frontier model on that cluster.
The router is available as a managed service or self-hosted binary. It preserves prompt-caching warmth by pinning session routing decisions, supports BYOK deployments, and exposes a dashboard for key management, telemetry, and per-request cost and latency drill-down.


Engineering management software for analyzing delivery, resource allocation, and team performance.

Engineering management software for analyzing delivery, resource allocation, and team performance.

Mentlio locally computes workflow, quality, and productivity signals without collecting users' prompts or source code.




IonRouter is a high-throughput, low-cost inference API and drop-in OpenRouter alternative powered by Cumulus Labs' IonAttention engine.



AI inference platform delivering serverless and dedicated GPU inference with top-ranked speed and price-performance.


Hosted gateway for routing and governing traffic across hosted and self-hosted AI models.


A unified OpenAI-compatible API and gateway for accessing hundreds of LLMs from many providers.


AI21 Gateway reduces agent token costs through adaptive routing and context optimization.


Cloudflare AI: serverless inference, agents, RAG, and secure runtime primitives on the global edge.


Serverless Inference serves open models through an OpenAI-compatible API billed by token use.


Baseten Inference Stack for high performance with custom kernels, decoding, caching on optimized infra.


Conifer Gateway is one OpenAI- and Anthropic-compatible endpoint for more than 200 models.


Unified production inference platform with gateway, router, cache, observability, evaluation, fine-tuning, and custom GPU hosting.


SkyPilot Tokens is an inference API serving open models across verified GPU fleets for AI developers.


Model Deployments manages immutable model releases with promotion, rollback, logs and analytics.


Portkey AI provides a gateway platform for managing and observing large language model deployments.


Open source AI gateway routing every model behind one zero-markup OpenAI-compatible endpoint.


Dedicated Endpoints serves one model on GPU capacity reserved for an organization.

Router is Conifer's routing decision leased on its own to harnesses and companies.

IonRouter is a high-throughput, low-cost inference API and drop-in OpenRouter alternative powered by Cumulus Labs' IonAttention engine.

An open-source AI gateway and proxy that calls many large language model APIs in the OpenAI format.

AI inference platform delivering serverless and dedicated GPU inference with top-ranked speed and price-performance.

Hosted gateway for routing and governing traffic across hosted and self-hosted AI models.

A unified OpenAI-compatible API and gateway for accessing hundreds of LLMs from many providers.

AI21 Gateway reduces agent token costs through adaptive routing and context optimization.

Cloudflare AI: serverless inference, agents, RAG, and secure runtime primitives on the global edge.

Serverless Inference serves open models through an OpenAI-compatible API billed by token use.

Baseten Inference Stack for high performance with custom kernels, decoding, caching on optimized infra.

Conifer Gateway is one OpenAI- and Anthropic-compatible endpoint for more than 200 models.

Unified production inference platform with gateway, router, cache, observability, evaluation, fine-tuning, and custom GPU hosting.

SkyPilot Tokens is an inference API serving open models across verified GPU fleets for AI developers.

Model Deployments manages immutable model releases with promotion, rollback, logs and analytics.

Portkey AI provides a gateway platform for managing and observing large language model deployments.

Open source AI gateway routing every model behind one zero-markup OpenAI-compatible endpoint.

Dedicated Endpoints serves one model on GPU capacity reserved for an organization.

River API lets developers fine-tune and run reinforcement learning on open-weight models.
