From 9f30309dd9d0d14d2ff237ea41114353199088e8 Mon Sep 17 00:00:00 2001 From: hongyi-chen Date: Tue, 26 May 2026 18:43:30 +0000 Subject: [PATCH 1/2] Document local model tunneling for custom inference endpoints Adds a new 'Using local models' section explaining that endpoint URLs must be publicly accessible (localhost and private network URLs are rejected) and how to expose a local model server through a tunneling service like ngrok. Co-Authored-By: Oz --- .../inference/custom-inference-endpoint.mdx | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/src/content/docs/agent-platform/inference/custom-inference-endpoint.mdx b/src/content/docs/agent-platform/inference/custom-inference-endpoint.mdx index 604a004c..7dcd58ba 100644 --- a/src/content/docs/agent-platform/inference/custom-inference-endpoint.mdx +++ b/src/content/docs/agent-platform/inference/custom-inference-endpoint.mdx @@ -54,6 +54,14 @@ When you explicitly select an endpoint-routed model from the model picker, Warp The configuration flow mirrors the [Bring Your Own API Key](/agent-platform/inference/bring-your-own-api-key/) setup, so the steps will feel familiar if you've already configured BYOK. +## Using local models + +Warp routes inference requests through its servers, so endpoint URLs must be publicly accessible. `localhost`, `127.0.0.1`, and other private or local network URLs are rejected when configuring a custom inference endpoint. + +To route through a model running on your own machine (for example, Ollama, LM Studio, vLLM, or llama.cpp), expose it through a tunneling service like [ngrok](https://ngrok.com/) and use the public tunnel URL as the base URL in your endpoint configuration. + +For example, with a default Ollama install listening on port `11434`, run `ngrok http 11434` and use the resulting `https://*.ngrok-free.app` URL as your endpoint. Other tunneling services that produce a publicly reachable HTTPS URL (Cloudflare Tunnel, Tailscale Funnel, and similar) work the same way. + ## Billing behavior ### Warp AI credits From 0874dac97c564a4c38b71d12c3d28c609642c621 Mon Sep 17 00:00:00 2001 From: Hong Yi Chen Date: Tue, 26 May 2026 11:53:51 -0700 Subject: [PATCH 2/2] Update src/content/docs/agent-platform/inference/custom-inference-endpoint.mdx Co-authored-by: oz-for-oss[bot] <277970191+oz-for-oss[bot]@users.noreply.github.com> --- .../docs/agent-platform/inference/custom-inference-endpoint.mdx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/content/docs/agent-platform/inference/custom-inference-endpoint.mdx b/src/content/docs/agent-platform/inference/custom-inference-endpoint.mdx index 7dcd58ba..23a4d4b9 100644 --- a/src/content/docs/agent-platform/inference/custom-inference-endpoint.mdx +++ b/src/content/docs/agent-platform/inference/custom-inference-endpoint.mdx @@ -60,7 +60,7 @@ Warp routes inference requests through its servers, so endpoint URLs must be pub To route through a model running on your own machine (for example, Ollama, LM Studio, vLLM, or llama.cpp), expose it through a tunneling service like [ngrok](https://ngrok.com/) and use the public tunnel URL as the base URL in your endpoint configuration. -For example, with a default Ollama install listening on port `11434`, run `ngrok http 11434` and use the resulting `https://*.ngrok-free.app` URL as your endpoint. Other tunneling services that produce a publicly reachable HTTPS URL (Cloudflare Tunnel, Tailscale Funnel, and similar) work the same way. +For example, with a default Ollama install listening on port `11434`, run `ngrok http 11434` and use the resulting `https://*.ngrok-free.app/v1` URL as your endpoint. Other tunneling services that produce a publicly reachable HTTPS URL (Cloudflare Tunnel, Tailscale Funnel, and similar) work the same way. ## Billing behavior