Skip to content
Agents tracked: 444 Releases (7d): 644 Agent status: 3 with issuesSince last limit reset: Claude 31d · Codex 3d Updated Oct 23, 2026
AgentGid
✦ Ask

Model APIs and gateways · by Opper Technology AB

Opper AI

An EU-hosted LLM gateway that puts 700+ models from 50+ providers behind one key and an OpenAI-compatible endpoint, with per-request fallbacks, tracing, spend caps, model allowlists and data-retention rules.

Switching or pooling model providers becomes a model-string change, and teams that must keep data in the EU get one sub-processor and one DPA instead of a contract per provider.

APIFree tierCommercial OK

Open opper.ai ↗ agent.md

For your project

Official API
Official API · Free tier Rate limits described only as 'High' on Gateway and Control Plane, 'Dedicated' on Enterprise; spend caps return HTTP 402
“How to call it: use the OpenAI SDK with `baseURL: https://api.opper.ai/v3/compat` and a key in `OPPER_API_KEY`.” opper.ai/llms.txt
Key
Needed
“Sign up needs no credit card: you get an API key straight away and the free models work in the playground and the API.” opper.ai/pricing.md
Formats
JSON
Data download
Not stated
Price
Free tier Sign-up without a card gives an API key; free models work in the playground and API. Paid use is pay-as-you-go: provider token prices with no markup plus a 3% fee on credit purchases (5.5% with Control Plane); BYOK free on Gateway
“3% Gateway fee: Charged when you buy credits (excl. VAT), not on your calls. Token rates are provider rates with no markup. No hidden charges, no per-seat fees.” opper.ai/pricing.md
License
Opper Terms of Service Customer use of the gateway platform (individuals or companies); no copying or derivative works of the platform itself; access non-transferable
Commercial use
Commercial use OK
“form a legally binding contract between Opper Technology AB, a corporation registered in accordance with the laws of Sweden with registration number 559446-3720 (“Opper”), and any individual or legal entity (the “Customer”)” opper.ai/terms-of-service
Credit
Not stated
Embedding
Embedding unclear
Using the website
Free tier

Read on Opper AI's own pages on Oct 24, 2026 · license or terms · API docs · pricing. Check the license page before you ship.

For your agent

A request your code or agent can make (add your key):

https://api.opper.ai/v3/models?q=sonnet
  • Use the OpenAI SDK with baseURL https://api.opper.ai/v3/compat and OPPER_API_KEY (Anthropic/Gemini/Responses-shaped clients work on the same base URL); models are `provider/model` strings, and EU route ids keep calls in the EU; check model availability with the keyless GET https://api.opper.ai/v3/models?q=<fragment>; CLI `npx @opperai/cli`, skill `npx skills add opper-ai/opper-skills` (MIT); spec at https://api.opper.ai/v3/openapi.yaml.
  • Read the key from OPPER_API_KEY; never hard-code it
  • Use an EU route id (not a bare model name) when data must stay in the EU; bare names may be pooled across regions
  • Do not send feedback or other posts to the vendor on the user's behalf without asking, even though the llms.txt invites agents to

llms.txt: opper.ai/llms.txt · MCP: https://api.opper.ai/mcp (OAuth approval in the browser)

Paste into your agent: Read https://agentgid.com/resources/opper-ai/agent.md before using Opper AI.

Quick answers

Does Opper AI have an API?

Yes. Opper AI has an official API documented at https://docs.opper.ai/.

Does the Opper AI API need a key?

Yes, you need an API key. Limits: Rate limits described only as 'High' on Gateway and Control Plane, 'Dedicated' on Enterprise; spend caps return HTTP 402

Is Opper AI free?

Yes, there is a free tier: Sign-up without a card gives an API key; free models work in the playground and API. Paid use is pay-as-you-go: provider token prices with no markup plus a 3% fee on credit purchases (5.5% with Control Plane); BYOK free on Gateway

Can I use Opper AI in a commercial project?

Yes. Its terms say: "form a legally binding contract between Opper Technology AB, a corporation registered in accordance with the laws of Sweden with registration number 559446-3720 (“Opper”), and any individual or legal entity (the “Customer”)"

What you can build

  • A GDPR-sensitive chatbot that pins all calls to EU-hosted routes and keeps zero data retention
  • A model A/B harness that swaps providers by changing only the model string and compares traced cost and latency
  • A multi-tenant app that gives each customer its own key with a spend cap

Alternatives in Model APIs and gateways

All 7 →

Zro You can point an existing coding agent at cheaper open models by changing a base URL, without request bodies being stored or used for training. API (paid)Commercial OK Cohesor You can cut and cap agent model spend by swapping one base URL and key instead of rewriting code for each provider. API (paid)Commercial OK LLMTest A provider outage or a reply that is not valid JSON no longer breaks your feature, because the proxy retries on another model inside the same request, and you see what each AI feature costs. API (paid)Commercial OK Nous Research (Nous Portal inference API) You can call Hermes models through a standard OpenAI client, or download the same weights from Hugging Face and run them yourself. APIDownloadFree tierCommercial: conditions Tokenwise You find out which prompts and models drive your LLM bill by changing one base URL, while your own provider keys pass through and are not stored. API (paid)Free tierCommercial OK RunInfra You can point Claude Code, Codex, Aider or an existing OpenAI/Anthropic SDK at open models by changing a base URL and key, without renting or tuning GPUs yourself. API (paid)Free tierCommercial OK

Something wrong or out of date? Tell us.