OpenAI compatible API · Attested · Public status
Telnyx performance
Measured TTFT, TTFB, effective throughput, uptime, and sampled model routes for Telnyx.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
telnyx
46 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 | 2582 ms |
|---|---|
| p95 TTFT | 3900 ms |
| p50 TTFB | 2581 ms |
| Effective throughput | 50 tok/s n=4 |
| Uptime | 100.00% |
Measured model routes
| Model | p50 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| google/gemma-2b-it | 845 ms | 845 ms | — | 100.00% | — | 4 |
| minimax/minimax-m3 | 968 ms | 968 ms | 53 tok/s n=1 | 100.00% | — | 6 |
| z-ai/glm-5.1 | 1590 ms | 1590 ms | — | 100.00% | — | 2 |
| meta-llama/llama-3.1-8b-instruct | 1695 ms | 1695 ms | — | 100.00% | — | 5 |
| moonshotai/kimi-k2.6 | 2393 ms | 2392 ms | — | 100.00% | — | 3 |
| moonshotai/kimi-k3 | 2582 ms | 2581 ms | 46 tok/s n=2 | 100.00% | — | 6 |
| moonshotai/kimi-k2.5 | 2712 ms | 2711 ms | — | 100.00% | — | 6 |
| meta-llama/llama-3.3-70b-instruct | 2859 ms | 2859 ms | — | 100.00% | — | 6 |
| z-ai/glm-5.2 | 2950 ms | 2950 ms | 138 tok/s n=1 | 100.00% | — | 5 |
| meta-llama/llama-3.1-70b-instruct | 3008 ms | 3008 ms | — | 100.00% | — | 3 |