OpenAI compatible API · Attested · Public status
Scaleway performance
Review measured TTFT, effective throughput, uptime, and sampled model routes for Scaleway on TrustedRouter using metadata-only production probes.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
Scalewayscaleway
37 samples
Continuously sampled provider performance. TrustedRouter reports unsupported route and probe-configuration rows separately from provider downtime. Prompt and output content is not stored.
| p50 TTFT | 2262 ms |
|---|---|
| p95 TTFT | 4974 ms |
| Effective throughput | 80 tok/s n=2 |
| Uptime | 100.00% |
Measured model routes
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| qwen/qwen3-coder-30b-a3b-instruct | 1037 ms | — | 100.00% | — | 1 |
| meta-llama/llama-3.3-70b-instruct | 1557 ms | — | 100.00% | — | 5 |
| mistralai/pixtral-12b-2409 | 1690 ms | — | 100.00% | — | 3 |
| deepseek/deepseek-v4-flash-0731 | 1979 ms | — | 100.00% | — | 5 |
| google/gemma-4-26b-a4b-it | 2015 ms | — | 100.00% | — | 4 |
| openai/gpt-oss-120b | 2262 ms | 80 tok/s n=2 | 100.00% | — | 3 |
| qwen/qwen3.6-35b-a3b | 2402 ms | — | 100.00% | — | 4 |
| z-ai/glm-5.2 | 2513 ms | — | 100.00% | — | 2 |
| qwen/qwen3-235b-a22b-instruct-2507 | 2800 ms | — | 100.00% | — | 1 |
| mistralai/mistral-small-3.2-24b-instruct-2506 | 3012 ms | — | 100.00% | — | 2 |
| mistralai/mistral-medium-3.5-128b | 3107 ms | — | 100.00% | — | 3 |
| qwen/qwen3.5-397b-a17b | 3265 ms | — | 100.00% | — | 4 |