OpenAI compatible API · Attested · Public status
Atlas Cloud performance
Review measured TTFT, effective throughput, uptime, and sampled model routes for Atlas Cloud on TrustedRouter using metadata-only production probes.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
Atlas Cloudatlas-cloud
24 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 | 2240 ms |
|---|---|
| p95 TTFT | 25004 ms |
| Effective throughput | 78 tok/s n=15 |
| Uptime | 95.83% |
Measured model routes
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| moonshotai/kimi-k2.5 | 936 ms | — | 100.00% | — | 2 |
| qwen/qwen3.5-35b-a3b | 1405 ms | — | 100.00% | — | 1 |
| z-ai/glm-5.3-flash | 1503 ms | — | 100.00% | — | 1 |
| x-ai/grok-build-0.1 | 1546 ms | — | 100.00% | — | 1 |
| qwen/qwen3.6-plus | 1809 ms | — | 100.00% | — | 1 |
| tencent/hy3 | 2007 ms | — | 100.00% | — | 1 |
| x-ai/grok-4.5 | 2036 ms | — | 100.00% | — | 1 |
| qwen/qwen3.5-27b | 2041 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-ocr | 2240 ms | — | 100.00% | — | 1 |
| x-ai/grok-4.6 | 2314 ms | — | 100.00% | — | 1 |
| qwen/qwen3.8-27b | 2318 ms | — | 100.00% | — | 1 |
| openai/gpt-5.6-sol-codex | 2423 ms | — | 100.00% | — | 2 |
| deepseek/deepseek-v3.2-exp | 2492 ms | — | 100.00% | — | 1 |
| bytedance/doubao-seed-2.0-lite-260428 | 3115 ms | — | 100.00% | — | 1 |
| google/gemini-3.8-flash | 3138 ms | — | 100.00% | — | 1 |
| meituan-longcat/longcat-2.0 | 3210 ms | — | 100.00% | — | 1 |
| google/gemini-3-flash-preview | 3296 ms | — | 100.00% | — | 1 |
| google/gemini-3.1-pro-preview | — | 24 tok/s n=2 | 100.00% | — | 4 |
| google/gemini-2.5-flash-lite | — | — | 0.00% | — | 1 |
| google/gemini-3.5-flash | — | 90 tok/s n=2 | — | — | 0 |
| kwaipilot/kat-coder-air-v2.5 | — | — | — | 2 provider_error |
0 |
| minimax/minimax-m3 | — | 95 tok/s n=2 | — | — | 0 |
| moonshotai/kimi-k2.6 | — | 75 tok/s n=2 | — | — | 0 |
| moonshotai/kimi-k2.7-code | — | 78 tok/s n=1 | — | — | 0 |
| moonshotai/kimi-k3 | — | 35 tok/s n=1 | — | — | 0 |
| openai/gpt-5.5 | — | 55 tok/s n=1 | — | — | 0 |
| xiaomi/mimo-v2.5-pro | — | 79 tok/s n=1 | — | — | 0 |
| z-ai/glm-5.2 | — | 77 tok/s n=1 | — | — | 0 |
| z-ai/glm-5.3 | — | 103 tok/s n=2 | — | — | 0 |