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
29 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 | 952 ms |
|---|---|
| p95 TTFT | 2652 ms |
| Effective throughput | 88 tok/s n=6 |
| Uptime | 100.00% |
Measured model routes
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| minimax/minimax-m3 | 823 ms | 85 tok/s n=2 | 100.00% | — | 1 |
| qwen/qwen3-235b-a22b | 869 ms | — | 100.00% | — | 2 |
| z-ai/glm-5.3 | 880 ms | 113 tok/s n=1 | 100.00% | — | 5 |
| z-ai/glm-5.3-flash | 906 ms | — | 100.00% | — | 3 |
| meta-llama/llama-3.1-70b-instruct | 950 ms | — | 100.00% | — | 1 |
| moonshotai/kimi-k2.5 | 952 ms | — | 100.00% | — | 4 |
| meta-llama/llama-3.3-70b-instruct | 981 ms | — | 100.00% | — | 2 |
| moonshotai/kimi-k2.6 | 983 ms | 91 tok/s n=1 | 100.00% | — | 1 |
| qwen/qwen3.8-27b | 1022 ms | — | 100.00% | — | 1 |
| minimax/minimax-m2.7 | 1511 ms | — | 100.00% | — | 3 |
| deepseek/deepseek-v4-flash-0731 | 1679 ms | — | 100.00% | — | 1 |
| meta-llama/llama-3.1-8b-instruct | 2150 ms | — | 100.00% | — | 3 |
| z-ai/glm-5.1 | 2262 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v4.1-flash | 2743 ms | — | 100.00% | — | 1 |
| moonshotai/kimi-k3 | — | 104 tok/s n=1 | — | — | 0 |
| z-ai/glm-5.2 | — | 24 tok/s n=1 | — | — | 0 |