Early access · API
Price your workload, then create your account.
Set your volumes and see our indicative early-access rates next to the public list prices of frontier APIs. An administrator reviews every account and grants access.
Unit prices
The rates behind the calculator
| Model | Provider | Input | Output |
|---|---|---|---|
| Iris 8B | Hellas Inference | €0.068 | €0.27 |
| Metis 12B | Hellas Inference | €0.35 | €1.40 |
| Gemini 3.8 Flash | €0.68 | €3.39 | |
| Claude Sonnet 5.5 | Anthropic | €1.81 | €9.05 |
| Gemini 4 Carbon | €1.81 | €9.05 | |
| Claude Opus 5.5 | Anthropic | €3.62 | €18.10 |
| GPT-6 Astra | OpenAI | €9.05 | €45.24 |
| Model | Provider | Per minute |
|---|---|---|
| Clio 1.5B | Hellas Inference | €0.0091 |
| Scribe v3 | ElevenLabs | €0.0030 |
| gpt-transcribe | OpenAI | €0.0041 |
| Nova-3 Multilingual | Deepgram | €0.0053 |
| Model | Provider | Per minute |
|---|---|---|
| Calliope 3B | Hellas Inference | €0.00069 |
| tts-1-hd | OpenAI | €0.0244 |
| Aura-2 | Deepgram | €0.0244 |
| v4 Turbo | ElevenLabs | €0.0326 |
| v4 | ElevenLabs | €0.0651 |
- Frontier prices are public list prices in US dollars, standard tier, read from each provider's pricing page on 15 November 2026 and converted at the ECB reference rate of 13 November 2026 (€1 = $1.1052). They change often; check the provider before you rely on them.
- Our rates are indicative early-access rates, derived from throughput we measured on one NVIDIA H200 (measurements). They are not a quotation and may change before general availability.
- Voice priced per character is converted at 900 characters per minute of speech. No batch, caching or volume discounts are applied on either side. Taxes are excluded. A month is 30 days.
- The models are not the same. Frontier models are large general-purpose models; ours are smaller open-weight models tuned for Greek business tasks. Price is one side of the comparison: measure quality on your own task before you choose.