Community
Free self-hosted
- Gateway, console, providers and models
- Model and provider access
- QPS, rolling quotas, usage and request records
- Basic security checks
Don't let rogue keys and runaway bills stall your business. Open-source, self-hosted. Issue dedicated keys per team — access, security, and cost control all in one place.
A sample client request enters the BOS API gateway.
Check the key, organization, allowed models and providers, QPS, and rolling quota.
Inspect input before it leaves the gateway, applying configured detection and actions.
Select a configured, authorized upstream channel and model.
The upstream response returns to BOS API before output inspection.
Inspect the model output and review rule results and actual actions.
Return allowed content and link usage, request, and security event records.
Configure models and org permissions in one place. No more handing out upstream credentials to every application.
| Model ID | Channel | Access |
|---|---|---|
Cmodel-chat | cloud-primary | Engineering |
Dmodel-code | cloud-secondary | Engineering |
Lmodel-local | private-endpoint | Internal apps |
| Application / Key | Organization | Allowed model |
|---|---|---|
| workspace-appsk-demo-····a1b2 | Engineering | model-chat |
| code-assistantsk-demo-····c3d4 | Engineering | model-code |
| internal-toolsk-demo-····e5f6 | Platform | model-local |
| Request ID | Model | Investigation |
|---|---|---|
req_demo_01 | model-chat | Status & duration |
req_demo_02 | model-code | Access & channel |
req_demo_03 | model-local | Tokens & usage |
Upstream channel → Organization → API Key → Verification. All data is fictional; this demo never connects to a live gateway.
Configure a channel, protocol, and model in provider and model management. Check availability.
Read the guideCreate Demo Engineering and assign the configured channel and model. Unassigned resources remain outside its access scope.
Read the guideSelect that organization, set the name, model restriction, QPS, and rolling quota, then review connection parameters. These limits are sample settings.
Read the guideUse this key with the allowed model, then match the request ID, status, and tokens in usage and request records.
Read the guideIllustrative console structure and sample data. Follow your deployed console and its versioned documentation.
Check requests and responses at the gateway. Security events help you trace the source of risks.
If a request carries a password or key pattern, the gateway flags it. Your security team can review.
Check model replies for configured code markers and log match locations for review.
Connect rules, match locations, and request records in one place. No cross-system lookups to investigate a risk.
password=[REDACTED]<script [omitted]See the security guide for detection and action coverage, streaming support, and event retention.
Swap the base URL in your existing SDK. Add a key and model ID. Done.
Read the SDK and API guidecurl --fail-with-body "https://bosapi.example.com/v1/chat/completions" \
-H "Authorization: Bearer $BOS_GATEWAY_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "YOUR_MODEL_ID",
"messages": [
{"role": "user", "content": "Say hello in one sentence."}
]
}'# Install: python -m pip install openai
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["BOS_GATEWAY_KEY"],
base_url="https://bosapi.example.com/v1",
)
response = client.chat.completions.create(
model="YOUR_MODEL_ID",
messages=[
{"role": "user", "content": "Say hello in one sentence."}
],
)
print(response.choices[0].message.content)// Install: npm install openai
import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.BOS_GATEWAY_KEY,
baseURL: "https://bosapi.example.com/v1",
});
const response = await client.chat.completions.create({
model: "YOUR_MODEL_ID",
messages: [
{ role: "user", content: "Say hello in one sentence." }
],
});
console.log(response.choices[0].message.content);Base URL https://bosapi.example.com/v1
API Key YOUR_BOS_API_KEY
Model YOUR_MODEL_ID
Protocol OpenAI-compatible / Chat CompletionsOpenAI-compatible example. Inject your key via env, then replace the endpoint and model ID.
From self-hosting to enterprise controls, choose the plan that fits your team.
Free self-hosted
Organization isolation and enhanced security for your team.
More organizations and keys, with more timely technical support.
Tailored deployment topology, governance, and support.
CC Switch handles the import, Vary AI handles config management and local routing.
Use Discord for open-source discussion and feedback. For commercial plans, contact sales on the pricing page.
If external sites are unreachable, check your network or use the documentation and sales consultation.