OpenAI compatible API · Attested · Public status
Telnyx performance
Review measured TTFT, effective throughput, uptime, and sampled model routes for Telnyx on TrustedRouter using metadata-only production probes.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
Telnyxtelnyx
17 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 | 1210 ms |
|---|---|
| p95 TTFT | 5275 ms |
| Effective throughput | 192 tok/s n=8 |
| Uptime | 100.00% |
Measured model routes
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| deepseek/deepseek-v4.1-flash | 702 ms | — | 100.00% | — | 1 |
| meta-llama/llama-3.1-8b-instruct | 865 ms | — | 100.00% | — | 2 |
| moonshotai/kimi-k3 | 1052 ms | 139 tok/s n=2 | 100.00% | — | 1 |
| qwen/qwen3.8-27b | 1070 ms | — | 100.00% | — | 2 |
| minimax/minimax-m2.7 | 1101 ms | — | 100.00% | — | 2 |
| moonshotai/kimi-k2.5 | 1210 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v4-flash-0731 | 1258 ms | — | 100.00% | 1 provider_error |
2 |
| qwen/qwen3-235b-a22b | 1265 ms | — | 100.00% | 3 provider_error |
1 |
| meta-llama/llama-3.3-70b-instruct | 1517 ms | — | 100.00% | — | 1 |
| meta-llama/llama-3.1-70b-instruct | 1948 ms | — | 100.00% | — | 1 |
| minimax/minimax-m3 | 2058 ms | 233 tok/s n=2 | 100.00% | — | 2 |
| z-ai/glm-5.2 | 5275 ms | 192 tok/s n=2 | 100.00% | — | 1 |
| moonshotai/kimi-k2.6 | — | 54 tok/s n=1 | — | — | 0 |
| poolside/laguna-s-2.1 | — | — | — | 1 provider_error |
0 |
| z-ai/glm-5.3 | — | 248 tok/s n=1 | — | — | 0 |