open models, EU-hosted, no retention.
your app talks to one endpoint. ozeye picks the provider, retries on failure, and never routes outside the EU.
smart routing
automatic failover with one endpoint. always routes requests dynamically by cost, latency, or availability.
zero retention
no prompt or completion is ever stored. zero-retention rules are strictly enforced instantly at our API gateway.
EU-only infrastructure
your data never leaves European borders. requests are strictly limited to EU-hosted providers, with zero non-EU fallback.
per-model pricing.
these are the prices you pay on ozeye. no subscription fees, no hidden platform charge.
| model | input / 1Min | cached / 1Mcached | output / 1Mout |
|---|---|---|---|
| DeepSeek V4 Flash 0731deepseek-v4-flash-0731 | €0.1245to €0.4480 | €0.0287to €0.0896 | €0.2682to €0.8960 |
| GLM 5.2glm-5.2 | €1.150to €2.016 | €0.2491to €2.016 | €4.023to €6.160 |
| GLM 5.3glm-5.3 | €1.341to €1.676 | €0.1341to €0.4191 | €4.215to €4.311 |
| GLM 5.3 Flashglm-5.3-flash | €0.1437to €0.1916 | €0.0479to €0.0671 | €0.4790 |
| Kimi K3kimi-k3 | €2.874 | €0.7185 | €14.370 |
| MiniMax M3minimax-m3 | €0.3832 | €0.0958 | €1.916 |
| DeepSeek V4.1 Flashdeepseek-v4.1-flash | €0.4790 | €0.1245 | €1.437 |
prices excl. VAT. you pay the rate of the provider that serves your request, shown from cheapest to most expensive. each model page lists every provider's price. a dash for cached input means it costs the same as input.
all 58 modelsmore than an API.
- private chataccess all models through a secure, built-in chat interface. no logs, no prompt persistence, and no tracking or advertising cookies: only the essential login cookies.
- hosted notebookswrite code and inspect responses in stateful, private python environments. perform direct validation and evaluation inside your secure browser session.
- configurable presetssave model, system prompt, temperature, and parameters as reusable presets. reload a full configuration in one click. switch tasks without retyping settings.
privacy by architecture.
your data flows strictly inside the European boundary. ozeye secures your path with validated zero data retention across all active endpoints.
frequently asked questions.
exclusively in the EU. requests route only through EU-hosted providers (Mistral, Scaleway, OVHcloud, Inceptron, TensorX) with no non-EU fallback.
no. ozeye never writes prompts or completions to logs or storage, and never uses them for training. the providers we route to process requests without keeping them under their published terms, which the subprocessors page lists provider by provider, together with what we have in writing. some providers briefly hold cache state derived from a prompt so that repeated prefixes cost less; the subprocessors page explains exactly what that means.
we track metadata only: model, token counts, and cost. no message content is ever stored.
all listed on /models, with automatic failover across EU providers.
prepaid credits, pay per token. no subscription, no card required to start. top up when you need.
there is nothing to cancel. pay only for what you use. credits are prepaid and never expire. stop anytime; consumers can withdraw from a top-up within 14 days, see the terms.
change your base URL and API key. the API is OpenAI-compatible, so existing code works. see /docs.
US providers route through global server networks with non-EU fallback, store prompts for safety or abuse review, and sit under US jurisdiction (CLOUD Act, FISA). ozeye routes EU-only with no non-EU fallback, enforces zero retention at the gateway, operates under EU GDPR jurisdiction, and bills prepaid per token with no subscription or seat minimums.