Is SBproxy a reverse proxy, an AI gateway, or a model server?

All three, from one binary. It terminates TLS and handles HTTP/1.1, HTTP/2, WebSocket, and gRPC like nginx or Envoy. It routes LLM traffic to 200+ hosted models across 72 providers with guardrails, budgets, and MCP federation. And it serves open-weight models on your own GPUs by supervising vLLM or llama.cpp underneath. One config file drives all of it, and the AI features sit on a runtime that was already a production-grade proxy.

SBproxy is the open-source enterprise gateway for API, MCP, and AI model traffic. Outbound, it routes to 200+ hosted models across 72 providers through one OpenAI-compatible endpoint, picking models by prompt difficulty and rerouting on live cost-per-success, and serves open-weight models on your own GPUs. Inbound, it gates the crawlers, signed agents, and MCP clients that hit your APIs, with controls like Pay Per Crawl and Web Bot Auth. Both directions share one policy of virtual keys, budgets, and guardrails. Underneath sits a production-grade reverse proxy running auth, TLS, WAF, rate limiting, transforms, and caching. Single static binary, Apache License 2.0.

Can SBproxy serve models on my own GPUs?

Yes, on any GPU. A provider whose entire body is a serve: block boots to a first token: SBproxy resolves the weights, fits an engine and quantization to your card (bigger cards take FP8, smaller ones fall back to an int4 GGUF), runs vLLM or llama.cpp as a supervised subprocess, and routes to it. Run sbproxy doctor first and it reports what the host can serve. Every governance plane, meaning virtual keys, budgets, guardrails, and the usage ledger, applies to the local model unchanged, and a hosted provider placed after the local lane catches overflow under policy.

How is SBproxy different from vLLM or Ollama?

vLLM and Ollama serve a model. SBproxy stands up the environment around it: the governed OpenAI-compatible endpoint, virtual keys, budgets, guardrails on prompt and response, failover to hosted providers, and a verifiable usage ledger. It runs vLLM or llama.cpp underneath as supervised engines, so you keep the engine and gain the gateway.

How is SBproxy different from Cloudflare Pay Per Crawl?

Cloudflare runs at its own edge. SBproxy runs in your VPC, region, Kubernetes cluster, or air-gapped environment. Pricing is tier-aware, per route, per shape, and per agent rather than domain-wide. Inbound monetization, agent identity, content negotiation, and outbound AI governance live on one policy graph instead of separate Cloudflare products. Settlement supports both x402 and Stripe MPP, and you can act as your own Merchant of Record.

How is SBproxy different from other AI gateways like LiteLLM, Helicone, Portkey, or Kong AI Gateway?

Most AI gateways stop at routing calls to hosted providers. SBproxy also serves the weights: the same binary runs open models on your GPUs and applies the same keys, budgets, and guardrails to local and hosted traffic alike. It is also a real reverse proxy underneath, so auth, WAF, and rate limiting ride along instead of needing a second gateway. Helicone is excellent for LLM observability. LiteLLM is a Python library that grew a server, and sbproxy config import-litellm converts its config in an afternoon. Kong is a traditional API gateway with AI bolt-ons. None of them serve the model.

Where does SBproxy sit in my stack?

At the network hop between your apps or agents and the models they call, and between inbound AI traffic and your APIs. SDK gateways live inside one app's code, hosted edges govern from someone else's network, and agent platforms ask you to build on them; SBproxy is standalone infrastructure that deploys like nginx, works under any agent framework or platform, and fronts any hosted provider or your own GPUs. It terminates TLS with certificates it issues and renews from Let's Encrypt, so the governed endpoint can face the public internet behind virtual keys you mint and revoke at runtime.

How does SBproxy handle API keys and state across a fleet of instances?

SBproxy ships a dynamic key plane. Mint, rotate, and revoke virtual keys at runtime through the admin API with no reload, and a revoke takes effect on the next request. Keys are hashed at rest with HMAC-SHA256 and a server pepper, and upstream provider credentials are sealed with AES-256-GCM. Across a fleet of replicas, a built-in mesh keeps the keys, budgets, and per-key rate counters coherent using SWIM gossip and CRDT counters, so the cluster coordinates itself without an external Redis. LiteLLM and most AI gateways need a separate Redis to share that state across instances.

Where does SBproxy deploy?

Single binary on a server, Kubernetes operator on a fleet, or air-gapped install on a regulated network. Same policy graph in every shape. No phone-home. No SaaS edge. Bring your own Stripe, your own SSO, your own observability, and your own audit sink. Suitable for EU, India, Saudi Arabia, US public sector, defense, healthcare, and finance workloads with sovereignty requirements.

Is SBproxy open source?

SBproxy is open source under the Apache License 2.0. Free for any use, including production and commercial, with no field-of-use restriction. Read every line on GitHub. Verify every binary.

What is Pay Per Crawl and how does SBproxy support it?

Pay Per Crawl is the pattern of charging AI crawlers for access to content using HTTP 402 Payment Required. SBproxy ships the ai_crawl_control policy: AI crawlers that arrive without a valid payment token receive a 402 response with a JSON challenge. The crawler retries with the issued token and the proxy validates it through a pluggable ledger. Settlement supports x402 stablecoin and Stripe MPP. Tokens can be priced per route, per shape, and per agent.

What is Web Bot Auth and how does SBproxy verify AI agents?

Web Bot Auth is the IETF pattern for verifying signed AI crawlers and agents. SBproxy implements it through the bot_auth provider. Agents sign each request with an Ed25519 key under RFC 9421 HTTP Message Signatures and advertise their key id in the Signature-Input header. The gateway looks up the matching public key in its directory and verifies the signature. Agents that pass come through. Everything else gets 401.

Does SBproxy support MCP?

Yes. SBproxy ships an MCP gateway that federates internal tools under one identity model. Authentication supports OAuth2 with DPoP, PKCE, and DCR. Federated servers can be wrapped from any OpenAPI service, with per-server prefix and RBAC. The same policy graph that governs API and AI traffic also governs MCP tool invocations.

What does SBproxy replace?

A hosted model router (OpenRouter), an LLM proxy (LiteLLM, Portkey, Helicone), the hand-rolled shim in front of vLLM or Ollama, a traditional API gateway (Kong, nginx, Envoy), a guardrails service, a bot management product, and a payment rail for crawlers (TollBit, Skyfire). One runtime instead of six vendors stitched together, one policy plane instead of six control planes, one audit log instead of six disconnected feeds.

How many AI providers does SBproxy support?

SBproxy reaches 200+ models behind one OpenAI-compatible API through 72 native providers, including OpenAI, Anthropic, Google Gemini, AWS Bedrock, Azure OpenAI, Azure AI Foundry, Groq, Mistral, Cohere, Together AI, Fireworks, xAI Grok, OpenRouter, Cerebras, NVIDIA NIM, Databricks, Snowflake Cortex, IBM watsonx, and Oracle GenAI, plus the models it serves itself on your GPUs via vLLM or llama.cpp and external self-hosted runtimes like Ollama and TGI. Routing supports fallback chains, weighted, round-robin, latency-based, cost-optimized, and outcome-aware strategies.

Is SBproxy safe to run in front of production traffic?

SBproxy ships as a single static Rust binary. Releases are cut from tagged commits in a public repository on GitHub. Dependencies are pinned and checksummed in Cargo.lock. The runtime does not fetch code from a public package registry when it starts. The deployment shape matches nginx, HAProxy, and Envoy. Hot reload is supported without dropping connections.

Dynamic Model Management

Zero-downtime model changes, per-key aliases, and runtime weight tuning

Overview

SBproxy lets you control which models are available, how traffic is distributed across them, and what model names your clients see, all without redeploying or restarting your gateway. Changes take effect on the next request.

Capabilities

Enable and disable models at runtime - Remove a model from rotation instantly when a provider has an outage or when you want to sunset a model version. No config change or restart needed.
Weight tuning - Shift traffic between models in real time. Gradually ramp up a new model from 10% to 100% while monitoring quality and cost.
Per-key model aliases - Give each API key its own mapping of friendly names to actual models. Clients use stable names like fast or smart while you swap underlying models transparently.
Workspace scoping - Each workspace controls its own model availability. A staging workspace can test new models while production stays on proven ones.
Distributed cache management - Flush cached responses by model, namespace, or globally across all gateway instances when you change model configurations.

Runtime Model Control

Disable a model across your gateway without touching the configuration:

features:
  ai.models.gpt-4-turbo.enabled: false

Disabled models are removed from the /v1/models response and are no longer eligible for routing. Re-enable by setting the flag back to true or removing it.

Traffic Weight Tuning

Override provider weights at runtime to shift traffic between models:

features:
  ai.models.gpt-4o.weight: 80
  ai.models.gpt-4o-mini.weight: 20

Weight overrides apply on top of your routing configuration. Use this for gradual rollouts, cost optimization experiments, or responding to provider performance changes in real time.

Per-Key Model Aliases

Each API key can define its own model alias map. Clients use stable, friendly names while you control which actual model is called:

model_aliases:
  fast: gpt-4o-mini
  smart: claude-sonnet-4-20250514
  balanced: gpt-4o

When a client sends "model": "fast", the gateway resolves it to the actual model before routing. The resolved model appears in response headers and analytics.

Use Cases

Model comparison - Point the smart alias to different models for different keys and compare quality metrics side by side.
Cost optimization - Redirect the default alias to a cheaper model for low-priority keys without any client-side changes.
Drop-in migration - When a provider releases a new model, update the alias target and existing clients pick it up on the next request.
Tiered access - Free-tier keys map smart to a smaller model. Premium keys map it to the most capable model available.

Cache Invalidation

When you change model configurations, you can flush cached responses to ensure clients get fresh results. Cache operations are distributed across all gateway instances automatically:

Flush by model - Clear all cached responses for a specific model after changing its routing or disabling it.
Flush by namespace - Clear cache for a specific workspace or prompt configuration.
Flush all - Clear the entire cache globally or for a single workspace.
Delete single entry - Remove a specific cached response by key.

← PreviousGuardrails Next →Predictive Budgets