AI Gateway

The AI Gateway is the request path. Your app sends a call, the gateway picks a model, runs it, and returns the result. One gateway and API key, with 300+ models behind it. The gateway is hosted in the EU; provider inference locations depend on the selected model. It replaces wiring up each provider yourself, so there are no per-provider SDKs, keys, billing, or rate limits to manage. To swap a model, change a string.

What the gateway gives you

One API, every model

Reach OpenAI, Anthropic, Google, Mistral, and 300+ more through a single endpoint and key.

Every modality

Not just text — generate images, speech, and video, transcribe audio, and run realtime voice.

Drop-in SDKs

Keep the OpenAI, Anthropic, or Google AI SDK you already use. Change the base URL, nothing else.

Switch models without code

Set a default model per project with a Route rule. Change it from the platform, no deploy.

Bring your own keys

EU by default

Restrict calls to EU-only or zero-retention providers. Enforced at the gateway.

One bill, every provider

Every response carries its cost. Spend across all providers in one place.

Observability built in

Every call is metered: cost, latency, and tokens. Turn on retention for full traces.

One API, every model

Address any model as provider/model. The same call works whether you point it at OpenAI, Anthropic, or a model hosted in the EU.

openai/gpt-5            # OpenAI
anthropic/claude-opus-4-7   # Anthropic
mistral/mistral-large-2512   # Mistral, EU-hosted

Some models are served by more than one provider (for example the same Claude model via Anthropic, Azure, or Bedrock). Opper balances across them for you, so a single name keeps working even when one provider is busy. To call a model, point your SDK at https://api.opper.ai/v3/compat — see Drop-in SDKs. The same endpoint covers text, structured output, tool calling, and multimodal input, with the same routing, governance, and tracing on every call. The gateway isn’t text-only. Dedicated endpoints generate images (POST /v3/images), speech and transcripts (POST /v3/audio/*), and video (POST /v3/videos), and realtime voice runs over a WebSocket — all behind the same key and governance. See Multimodality. For classification and scoring, TypeSafe System One provides a native compatibility endpoint at POST /v3/compat/v1/systemone, returning probabilities, categories, and scores through the same project key.

Pin and switch models without touching code

Keep model names out of your application. Set a default once and change it from the platform:

Route pins a default model per organization or project. Edit one rule to move a project to a different model.
Custom models let you register your own provider deployments and call them like any other model in the catalog.

Callers can still pass an explicit model for per-call trade-offs, as long as model access allows it.

Bring your own keys

You can go beyond Opper’s hosted models. Register your own provider deployments and API keys (for example a private Azure OpenAI deployment), and they show up in the catalog alongside built-in models with the same routing, governance, and tracing.

curl -X POST https://api.opper.ai/v2/custom-models \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPPER_API_KEY" \
  -d '{
    "name": "example/my-gpt",
    "provider": "azure",
    "model_id": "gpt-production",
    "api_key": "your-provider-key",
    "params": {"api_base": "https://your-deployment.openai.azure.com/", "api_version": "2024-06-01"}
  }'

Call it like any other model: example/my-gpt. See Custom models for the full setup.

Keep data in the EU

The gateway is hosted exclusively in the EU. The only thing that leaves is the model call itself, and you control where that goes. With a model access rule you can restrict every call to:

EU-only providers (Mistral, Azure EU, and others)
Specific regions or countries
Providers that meet your data requirements, including the Zero data retention policy

Opper storage is configured separately. To stop storing new traces across the organization, switch tracing off in Opper retention so an enabled 0-day retention rule applies. Usage records are still kept, and existing traces keep their original expiry dates. See that page for the effects on files and response caching. If you also need provider data restrictions, configure the provider data policy in Model access. Set both controls to meet both requirements: turning Opper tracing off does not restrict providers, and selecting a provider data policy does not turn Opper tracing off. Anything that breaks a rule is rejected at the gateway before it reaches a provider. See Security for more.

One bill, full visibility

Every response includes its cost, computed the same way across all 300+ models. The gateway aggregates spend and usage across providers, so you get one bill and one place to watch it. Every call is metered (cost, latency, tokens) and shows up in Analytics for spend over time. Turn on a retention rule and you also get the full trace for each call, with inputs, outputs, and every step.

How the Gateway and Rules work together

The Gateway runs your requests. Rules defines the boundaries it enforces.

	AI Gateway	Rules
Role	Runs every request	Defines what requests may do
You use it by	Making model calls	Configuring policies in the platform
Examples	Routing, provider access, usage metering	Retention, spend limits, model access, checks

Configure a rule once; the Gateway applies it to every matching call.

Security

The gateway also enforces data residency. The next page covers how Opper is hosted and protected.

Security

EU hosting, sub-processors, encryption, and deletion.

Models

The full catalog. EU-hosted models marked.

Build on Opper

Ready to build? Text, multimodal, and voice.

Drop-in SDKs

Use the OpenAI, Anthropic, or Google AI SDK you already have.

Get started

Platform

Build

Observe & Control

Integrations

Tutorials

Tooling

What the gateway gives you

One API, every model

Every modality

Drop-in SDKs

Switch models without code

Bring your own keys

EU by default

One bill, every provider

Observability built in

One API, every model

Pin and switch models without touching code

Bring your own keys

Keep data in the EU

One bill, full visibility

How the Gateway and Rules work together

Security

Security

Models

Build on Opper

Drop-in SDKs

​What the gateway gives you

One API, every model

Every modality

Drop-in SDKs

Switch models without code

Bring your own keys

EU by default

One bill, every provider

Observability built in

​One API, every model

​Pin and switch models without touching code

​Bring your own keys

​Keep data in the EU

​One bill, full visibility

​How the Gateway and Rules work together

​Security

Security

Models

Build on Opper

Drop-in SDKs

What the gateway gives you

One API, every model

Pin and switch models without touching code

Bring your own keys

Keep data in the EU

One bill, full visibility

How the Gateway and Rules work together

Security