llama-3.3-70b-instruct API pricing
llama-3.3-70b-instruct by Scaleway costs €0.90 per 1M input tokens and €0.90 per 1M output tokens (1M in + 1M out = €1.80).
- API model id
llama-3.3-70b-instruct- Input / 1M
- €0.90
- Output / 1M
- €0.90
- Cached input / 1M
- —
- Context window
- —
- Notes
- Priced in EUR (not converted).
- Source
- https://www.scaleway.com/en/pricing/model-as-a-service/
- Provider type
- Cloud (HQ: France)
- Regions
- EU
- EU data residency
- yes — All Serverless models are hosted in Paris, France, and Scaleway commits to keeping api.scaleway.ai hosting in Europe.
- Currency
- EUR (as published, not converted)
- Last verified
- 2026-10-15
Cost estimate
| Provider | Model | Cost |
|---|---|---|
| Scaleway | llama-3.3-70b-instruct | €1.13 |
Uses standard list prices (no caching, batch or off-peak discounts). € and CHF rows are priced in that currency by the provider and not converted, so compare them with care.
Other Scaleway models
- glm-5.3: €1.80 / €5.50
- deepseek-v4.1-flash: €0.60 / €1.80
- qwen3.8-27b: €0.60 / €3.30
- gemma-4-26b-a4b-it: €0.25 / €0.50
- mistral-medium-3.5-128b: €1.50 / €7.50
- gpt-oss-120b: €0.15 / €0.60
- mistral-small-3.2-24b-instruct-2506: €0.15 / €0.35
- qwen3.5-397b-a17b: €0.60 / €3.60