Catalogue

Provider list prices in EUR, passed through at cost plus Model Pond's 2.5% markup.

Providers

Every model below is served by one of these five. Links go to the provider's own published terms.

Berget AI

Sweden · text, speech, embeddings, rerankers

Runs open models under Swedish jurisdiction with zero data retention, positioned against GDPR, NIS2 and Schrems II. Cached input tokens are billed at the same rate as uncached ones.

STACKIT

Germany · text, embeddings

Part of the Schwarz Group. Their FAQ states that no customer data from requests is stored and none is used to train models; shared models run in communal tenancy with no data exchange between projects or between customers. Billing follows named tiers rather than per-model rates.

Flagship models

The strongest models here, each with every provider that hosts it and their rates side by side.

Sources: Scaleway Generative APIs, IONOS AI Model Hub, OVHcloud AI Endpoints, Berget AI and STACKIT AI Model Serving, checked 22 September 2026. IONOS publishes in USD, converted here at the ECB reference rate of 0.87237. Whisper is billed per minute of audio, FLUX.1 schnell per image, FLUX.2 klein per output megapixel, and the NVIDIA Riva voices per input character. Embedding and reranking models are charged on input only; they return vectors or scores, not text. STACKIT bills by model tier, so their rows share rates; each row names its tier. Prices change: treat this page as a snapshot and confirm against the provider before you commit.