docs(cloud-proxy): add OrcaRouter passthrough example

Document OrcaRouter as a first-class cloud-proxy upstream. It is an
OpenAI-compatible gateway, so it plugs into the existing passthrough
mode with provider: openai, mirroring the OpenAI/Anthropic examples.

Assisted-by: Claude:deepseek-v4-flash-0731
Signed-off-by: XiaoHuo888-hue <xiaohuo888hue@users.noreply.github.com>
(cherry picked from commit 329ee0ee89)
(cherry picked from commit 6b2d84294d0198bdaa2f27288993eb7cfad0b0b1)
This commit is contained in:
XiaoHuo888-hue authored and Ettore Di Giacinto committed 2026-11-03 19:20:44 +00:00
1 parent 9cc7b63d89
commit 48549f5701
1 file changed
+43 -1
+43 -1
View File
@@ -3,7 +3,7 @@ title = "Cloud passthrough proxy"
weight = 28
toc = true
url = "/features/cloud-proxy/"
description = "Forward requests to OpenAI, Anthropic, or any compatible provider"
description = "Forward requests to OpenAI, Anthropic, OrcaRouter, or any compatible provider"
tags = ["Proxy", "Cloud", "Routing", "Advanced"]
categories = ["Features"]
+++
@@ -144,6 +144,48 @@ pii:
Anthropic clients hit `http://localhost:8080/v1/messages` with
`"model": "claude-sonnet-proxy"`.
### OrcaRouter passthrough
[OrcaRouter](https://www.orcarouter.ai) is a unified OpenAI-compatible gateway
that routes to 150+ hosted models (Anthropic, OpenAI, DeepSeek, Gemini, Qwen,
…) under a single key. It also runs gateway-level, zero-trust security for AI
agents on the same endpoint — screening every prompt/response and governing
every tool call on a default-deny basis, with no application code changes.
OrcaRouter speaks the OpenAI chat-completions wire format, so point a
cloud-proxy model at it with `provider: openai`:
```yaml
name: orcarouter-auto
backend: cloud-proxy
proxy:
mode: passthrough
provider: openai
upstream_url: https://api.orcarouter.ai/v1/chat/completions
api_key_env: ORCAROUTER_API_KEY
upstream_model: orcarouter/auto
request_timeout_seconds: 300
pii:
enabled: true
```
Then start LocalAI with the key in the environment:
```bash
export ORCAROUTER_API_KEY=sk-orca-...
local-ai run
```
Clients hit `http://localhost:8080/v1/chat/completions` with `"model":
"orcarouter-auto"` and LocalAI forwards the request to OrcaRouter.
`orcarouter/auto` lets OrcaRouter pick the best model for each prompt. To pin
a specific model, set `upstream_model` to its OrcaRouter id — for example
`deepseek/deepseek-v4-pro` or `anthropic/claude-sonnet-4-6`. Leave
`upstream_model` empty to pass the client's `model` field through unchanged.
### Other OpenAI-compatible providers
Most third-party providers (Together, Groq, DeepInfra, OpenRouter, …) speak