Skip to main content
Opper supports 700+ models from 50+ providers through one gateway and key. Browse the full, always-current catalog — with pricing, context windows, capabilities, and EU-hosted models marked — at opper.ai/models.

Browse all models

The complete model catalog. Copy a model id to use it from the SDK or any drop-in client.
Call generation models by their provider-prefixed name (openai/gpt-5.5, anthropic/claude-sonnet-4-6, gemini/gemini-3.1-pro-preview) through the compatible SDKs. See Drop-in SDKs. Models for other tasks use their dedicated endpoints.

Decision models

Decision models provide yes/no probabilities, category choices, and ordered scores. Discover them with GET /v3/models?type=evaluation, then call POST /v3/compat/decisions (OpenAI’s Decisions format) or POST /v3/compat/v1/systemone (TypeSafe’s System One format) with your project API key. Every decision model answers on both; see Decision models. They also decide which way a classifier node routes a request. Decision models cannot be called through Chat Completions.

Multimodal models

Beyond text, the catalog includes models that accept images, audio, and video, and models that generate images, speech, and video. Filter the catalog by capability — vision, audio, video, image gen — to see what each model supports. For the modality-specific endpoints, a discovery call returns the usable models and their capabilities at runtime, so you don’t have to hardcode a list: For sending images and PDFs into a text model, see Vision & PDFs.

Models available on request

A few models are listed for everyone but enabled for an organization only after Opper reviews its use case. Today these are the abliterated models: open-weight models whose refusal behavior has been removed. They are used for red teaming, penetration testing, and other security work, where a refusal would end the task.
  • Find them. GET /v3/models marks them with "access_group": "abliterated", and with ?include=policy they show "blocked_by": "entitlement" until your organization has access. The model catalog in the platform hides them unless you search for one, turn on Show restricted, or use the Abliterated filter.
  • Before access. A call returns 403 with the code entitlement_required and the message Model "…" is restricted. To access this model, contact hello@opper.ai.
  • Ask for access. Select Request access on the model in the model catalog and say what you will use it for, or email hello@opper.ai. One approval enables every abliterated model for your organization.
Use them only on systems you own or have written permission to test. Misuse ends access. This approval is separate from the agreement some provider routes need, described in Routes that require an agreement. That agreement covers how a provider handles your data; this approval covers the model itself.

Fallbacks and backup chains

There are two ways to get a fallback chain. Per request, on Chat Completions. Send the primary in model and the rest in models, the same shape OpenRouter uses:
Entries are tried in order when the one before fails for any reason. An entry can be a pinned id, a bare pool name (its providers are tried in turn) or a legacy alias. A compliance rule that blocks an entry removes it from the chain without an error. meta.routing.attempts lists every attempt with its status and meta.routing.served names the model that answered. Only /v3/compat/chat/completions reads models. Managed on the gateway, for every endpoint. Build a dynamic route, give it the models you want to try, deploy it, and call the route’s name as model from any SDK, on every endpoint. This is the option to reach for when the chain should live in one place, with ranking, a version history and rollback. The gateway tries the models in the route and the first one that answers wins; a model that is down or rate-limited is passed over, and in a Pool so is one that a compliance rule blocks for your organization — neither comes back as an error.
Two nodes answer a request:
  • A Pool holds several models and re-ranks them on every request on live numbers — cheapest, fastest, highest throughput, or a blend. Use it when any of the models is acceptable and you want the gateway to pick.
  • A Model node calls one model, with fallbacks in the fixed order you wrote down. Use it when the order matters — “this model, and only if it fails, that one”.
Either can sit on the other’s fallback edge, so a route can say “try this pool, then that model”. Every attempt is recorded on the trace, so you can see which model actually answered and why the others were passed over. Two things this buys you:
  • Resilience. If the primary provider is down or rate-limited — or, in a Pool, a compliance rule takes it out of play — the call continues to the next model instead of failing.
  • Swap models without touching code. Point your app at the route name, then reorder or repoint the route in the platform — no deploy.
Routes are part of the Control Plane. To put your own provider deployments into a route, register them as custom models first.
Model aliases (Settings → Models), a stable name mapping to an ordered list of models, still resolve on every call for organizations that use them. New fallback chains should be built as dynamic routes: they give you ranking, per-attempt traces, and the same skip-on-compliance behavior.

What’s next

Dynamic routes

Pick the model per request: pools, branches, splits, classifiers.

Custom models

Register your own model deployments and API keys.

Apps

Use Opper as the provider for your editor, agent, or CLI.
Last modified on November 10, 2026