Scaleway
Explore Scaleway models on TrustedRouter with current routes, token pricing, policy sources, privacy posture, regional availability, and API support.
Scalewayscaleway
These privacy labels describe Scaleway, the upstream model provider. Confidential requires all three: verified provider compute, end-to-end encryption and explicit zero data retention. Account and billing metadata are outside the content-retention claim.
| Provider | Scaleway |
|---|---|
| API operator country | FR Legal home of the API operator, not an inference-location guarantee. |
| Headquarters | Not verified |
| Routing status | Active |
| Provider website | https://www.scaleway.com/ |
| Models | 10 public models |
| Credits routes | 10 |
| Zero data retention | not claimed |
| Verified confidential inference | Not verified |
| Policy note | Scaleway routes are discovered from its authenticated Model as a Service catalog and priced from Scaleway's first-party EUR price feed with a bounded FX reserve. No contractual ZDR, confidential-compute, or E2EE claim is tracked for this account, so these routes are Standard. Policy source |
Inference locations
Provider API declarations are also available on each model's endpoint API. Direct chat and Responses replies separate advertised availability from serving location in usage.inference_location; the actual serving region remains unknown when not reported.
Where the upstream GPUs execute the model, not the provider's headquarters, API ingress, or data storage. ZDR and confidential inference do not by themselves restrict geography.
- Declared countries or regions
- France (Paris)
Scaleway's FAQ places its current Serverless inference fleet in Paris. Dedicated deployments are a separate product. - Can locations change?
- Scaleway may expand Serverless hosting within Europe, with notification; France-only is not a permanent commitment.
- Provider region pinning
- Scaleway recommends Dedicated Deployment for single-region processing.
- Pinning through TrustedRouter
- Not supported by the current TrustedRouter integration.
- Infrastructure declaration
- Serverless: currently Paris, France, provider-declared; future expansion within Europe possible.
- Evidence
- Public Serverless FAQ; not a per-request location receipt. Reviewed .
Provider selection alone is not a region pin. TrustedRouter's US provider filter selects company jurisdiction, not GPU location. A regional gateway hostname does not pin a downstream GPU. For a binding residency requirement, confirm the model, region, failover scope and enforced controls before sending sensitive data.
Measured performance
20 samplesContinuously sampled across Scaleway's routed models: p50 TTFT, effective throughput, and success rate. Effective throughput uses provider-reported output tokens over complete request time. Unsupported route and probe-configuration rows are separated from provider downtime. No prompt or output content stored.
| p50 TTFT | 1494 ms |
|---|---|
| Effective throughput | 104 tok/s n=1 |
| Uptime | 100.00% |
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| google/gemma-4-26b-a4b-it | 840 ms | — | 100.00% | — | 2 |
| mistralai/mistral-small-3.2-24b-instruct-2506 | 901 ms | — | 100.00% | — | 2 |
| qwen/qwen3-235b-a22b-instruct-2507 | 1375 ms | — | 100.00% | — | 3 |
| qwen/qwen3.6-35b-a3b | 1380 ms | — | 100.00% | — | 1 |
| z-ai/glm-5.2 | 1494 ms | 104 tok/s n=1 | 100.00% | — | 2 |
| meta-llama/llama-3.3-70b-instruct | 1692 ms | — | 100.00% | — | 4 |
| qwen/qwen3.5-397b-a17b | 2022 ms | — | 100.00% | — | 3 |
| openai/gpt-oss-120b | 2038 ms | — | 100.00% | — | 1 |
| mistralai/mistral-medium-3.5-128b | 2370 ms | — | 100.00% | — | 2 |
Scaleway performance history · Full provider & model leaderboard.
Models served by Scaleway.
Each row links to pricing, provider, benchmark, and API pages for the model.
| Model | AI IQ | Context | Input | Cached input | Output |
|---|---|---|---|---|---|
deepseek/deepseek-v4-flash-0731DeepSeek: DeepSeek V4 Flash 0731 |
— | 1,048,576 | $0.495741/1M | $0.099149/1M | $0.991481/1M |
google/gemma-4-26b-a4b-itGoogle: Gemma 4 26B A4B |
IQ 100#113 | 262,144 | $0.309838/1M | Not published | $0.619676/1M |
meta-llama/llama-3.3-70b-instructMeta: Llama 3.3 70B Instruct |
— | 131,072 | $1.115416/1M | Not published | $1.115416/1M |
mistralai/mistral-medium-3.5-128bmistral-medium-3.5-128b |
— | 0 | $1.859027/1M | Not published | $9.295131/1M |
mistralai/mistral-small-3.2-24b-instruct-2506mistralai/Mistral-Small-3.2-24B-Instruct-2506 |
— | 128,000 | $0.185903/1M | Not published | $0.433773/1M |
openai/gpt-oss-120bOpenAI: gpt-oss-120b |
IQ 98#126 | 131,072 | $0.185903/1M | Not published | $0.743611/1M |
qwen/qwen3-235b-a22b-instruct-2507Qwen/Qwen3-235B-A22B-Instruct-2507 |
— | 262,144 | $0.929514/1M | Not published | $2.78854/1M |
qwen/qwen3.5-397b-a17bQwen: Qwen3.5 397B A17B |
— | 262,144 | $0.743611/1M | Not published | $4.461663/1M |
qwen/qwen3.6-35b-a3bQwen: Qwen3.6 35B A3B |
IQ 104#100 | 262,144 | $0.309838/1M | Not published | $1.859027/1M |
z-ai/glm-5.2Z.ai: GLM 5.2 |
IQ 119#45 | 1,048,576 | $2.230832/1M | Not published | $6.816429/1M |
Questions
Does Scaleway have zero data retention?
TrustedRouter does not currently mark Scaleway as provider-level zero data retention. Use trustedrouter/zdr or provider.min_privacy=zdr to select a different eligible route, and review the linked policy source for changes.
Is Scaleway end-to-end encrypted?
TrustedRouter does not currently mark Scaleway as end-to-end encrypted at the provider boundary. The TrustedRouter gateway is still attested, but the selected provider normally receives the request in order to run the model. Use trustedrouter/e2e for the stronger route requirement.
Which Scaleway models are available through TrustedRouter?
This page currently lists 10 public Scaleway models, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.