Loading catalog…
Product briefing
ArcoreLLMProxy
ProductionData & Intelligence
ArcoreLLMProxy is an enterprise LLM gateway that exposes a unified OpenAI-compatible surface while routing requests across multiple upstream providers. It centralizes provider credentials, policy enforcement, rate limiting, and observability behind a single consistent interface.
API: Available
Endpoints
5
Key features
5
Stack components
8
Controls noted
5
What changed
May 15, 2026: Added governance-aligned copy, compare tooling support, and transparency notes.
Key Features
- 1OpenAI-compatible chat and responses endpoints
- 2Model alias registry and multi-provider routing
- 3Fallback chains, RPM budgets, and circuit breaking
- 4Tenant-scoped API key and JWT auth with policy enforcement
- 5Streaming passthrough plus admin/debug configuration APIs
API Endpoints
| Method | Path | Description |
|---|---|---|
| GET | /v1/models | List available routed models and aliases |
| POST | /v1/chat/completions | OpenAI-compatible chat completions |
| POST | /v1/responses | OpenAI-compatible responses API |
| GET | /health | Health check for proxy and dependencies |
| GET | /debug/routes | Inspect configured routes and policy state |
Usage Example
python
import requests
# Example interaction
response = requests.post(
url="https://api.arcore.internal/v1/chat/completions",
headers={"Authorization": "Bearer <token>"}
)
print(response.json())Recommended next products
Tech Stack
PythonFastAPIPostgreSQLRedis/CeleryOpenTelemetrystructloghttpxDocker
Authentication
- •**Header:** `Authorization: Bearer <token>` or `x-api-key: <key>`
- •**Scopes:** Tenant, route, alias, IP, and key-based policies can all be enforced
- •**Credential Storage:** Provider secrets are encrypted at rest in PostgreSQL
Compliance & Security
Compliance
- ✓Policy: Allow/deny controls can be enforced per tenant, route, and alias
- ✓Secrets: Provider credentials are encrypted and removed from the request hot path
- ✓Resilience: Circuit breaker and fallback chains reduce upstream provider failures
- ✓Observability: OpenTelemetry and structured logging capture gateway behavior without blocking inference
Security
- ✓Secrets: Provider credentials are encrypted and removed from the request hot path
Related Products
Arcore Maestro
Arcore Maestro is an AI workflow orchestration platform that routes tasks through LangGraph-based workflows, local or remote LLMs, and sandboxed worker services. It provides a unified control plane for defining, executing, and monitoring multi-step AI pipelines across the Arcore ecosystem.
Graph-based workflow orchestration with conditional branching
CRUD management for services, models, workflows, graphs, and templates
PythonFastAPIReact
6 endpointsOpen
local-llm-server
A production-ready local model serving platform with an OpenAI-compatible API, orchestration endpoints for model lifecycle management, deep performance telemetry, and an optional Vector-Tester companion UI for staged testing and crash-log capture.
Model registry with load and unload orchestration
OpenAI-compatible and native streaming inference endpoints
PythonFastAPISQLModel
6 endpointsOpen
Chapterize
An intelligent PDF processing platform that converts unstructured books and documents into structured chapters with rich HTML, text, and images. Chapterize combines a Django + React web application with a Python CLI toolkit for batch processing and downstream RAG-friendly exports.
TOC-first chapter detection with regex fallback
Layout-aware extraction of text, images, and tabular regions
PythonDjangoReact
5 endpointsOpen