The Inference Directory
Explore directory

Scaleway

Verified

Scaleway is a France-based provider in the Cloud provider category with 17 listed models. 3 of 17 models publish a cached-input rate.

EU-owned EU hosting Cloud provider
Visit website API docs

At a glance

Record
Ownership
Scaleway SAS
Headquarters
Paris, France
Hosting region
EU (Paris (fr-par), Amsterdam (nl-ams))
Founded
Not published

Summary

Scope

Scaleway is a France-based provider in the Cloud provider category with 17 listed models. 3 of 17 models publish a cached-input rate.

KYC + card required to unlock official rate limits. Batch API discount. 17 models on the public price list.

Source: www.scaleway.com ↗ · Updated Nov 4, 2026

API access

OpenAI-compatible

Access

API

KYC

Business account

Compliance

GDPREU-ownedDPA

Key models

17 listed
GLM-5.3 , context · per 1M tokens Inference €1.8 / €5.5
GLM-5.2 , context · per 1M tokens Inference €1.8 / €5.5
DeepSeek V4.1 Flash , context · per 1M tokens Multimodal €0.6 / €1.8
DeepSeek V4 Flash 0731 , context · per 1M tokens Inference €0.4 / €0.8
Qwen3.8 27B , context · per 1M tokens Multimodal €0.6 / €3.3
Qwen3.6 35B A3B , context · per 1M tokens Multimodal €0.25 / €1.5
Qwen3.5 397B A17B , context · per 1M tokens Multimodal €0.6 / €3.6
Qwen3 235B A22B , context · per 1M tokens Inference €0.75 / €2.25
Gemma 4 26B A4B IT , context · per 1M tokens Multimodal €0.25 / €0.5
Mistral Medium 3.5 128B , context · per 1M tokens Multimodal €1.5 / €7.5
Mistral Small 3.2 24B , context · per 1M tokens Multimodal €0.15 / €0.35
Llama 3.3 70B Instruct , context · per 1M tokens Inference €0.9 / €0.9
GPT OSS 120B , context · per 1M tokens Inference €0.15 / €0.6
LightOn OCR 3 0.8B , context · per 1M tokens OCR €2.2 / €0
Whisper Large v3 , context · per minute Speech €0.003 / €0
Qwen3 Embedding 8B , context · per 1M tokens Embedding €0.1 / €0
BGE Multilingual Gemma2 , context · per 1M tokens Embedding €0.1 / €0

Pricing

List rates · EUR
Model Type Input price Caching price Output price
GLM-5.3, context · per 1M tokens Inference €1.8 - €5.5
GLM-5.2, context · per 1M tokens Inference €1.8 - €5.5
DeepSeek V4.1 Flash, context · per 1M tokens Multimodal €0.6 €0.12 €1.8
DeepSeek V4 Flash 0731, context · per 1M tokens Inference €0.4 €0.08 €0.8
Qwen3.8 27B, context · per 1M tokens Multimodal €0.6 €0.12 €3.3
Qwen3.6 35B A3B, context · per 1M tokens Multimodal €0.25 - €1.5
Qwen3.5 397B A17B, context · per 1M tokens Multimodal €0.6 - €3.6
Qwen3 235B A22B, context · per 1M tokens Inference €0.75 - €2.25
Gemma 4 26B A4B IT, context · per 1M tokens Multimodal €0.25 - €0.5
Mistral Medium 3.5 128B, context · per 1M tokens Multimodal €1.5 - €7.5
Mistral Small 3.2 24B, context · per 1M tokens Multimodal €0.15 - €0.35
Llama 3.3 70B Instruct, context · per 1M tokens Inference €0.9 - €0.9
GPT OSS 120B, context · per 1M tokens Inference €0.15 - €0.6
LightOn OCR 3 0.8B, context · per 1M tokens OCR €2.2 - €0
Whisper Large v3, context · per minute Speech €0.003 - €0
Qwen3 Embedding 8B, context · per 1M tokens Embedding €0.1 - €0
BGE Multilingual Gemma2, context · per 1M tokens Embedding €0.1 - €0

List rates. Cached input shown where published; "-" means the provider does not publish a cache rate. Units follow the source rate card.

Infrastructure

Hosting
RegionEU
CitiesParis (fr-par), Amsterdam (nl-ams)
Provider groupCloud provider
ZDRnot stated
DPAAvailable
Cached input policyCached input rate on 2 models only.

Access

API & payments
API shapeOpenAI-compatible
AccessAPI
KYCBusiness account
Cached input policyCached input rate on 2 models only.

Compliance

Source-backed
DPAAvailable
ZDRnot stated
RetentionZDR: not stated. DPA published.
Certifications
GDPREU-ownedDPA

Benchmarks

Coming soon

Coming soon.

Performance

Coming soon
Latency

Time to first token

Median and p95 response times for short and long prompts, measured from repeatable probes rather than vendor claims.

Coming soon
Throughput

Tokens per second

Streaming output rate and request throughput under steady load, with concurrency and context length recorded.

Coming soon
Efficiency

Cost per workload

Blended cost for a fixed workload, including cache reads and output tokens, so speed and price can be compared together.

Coming soon

Independent performance probes are being added. Vendor-reported numbers are not mixed into this section.