Meta: Llama 3.3 70B Instruct Performance
TrustedRouter performance signals and provider route posture for Meta: Llama 3.3 70B Instruct.
meta-llama/llama-3.3-70b-instruct
Measured performance
Continuously sampled p50/p95 time-to-first-token (TTFT), time-to-first-byte (TTFB), effective throughput, and success rate for Meta: Llama 3.3 70B Instruct. Effective throughput uses provider-reported output tokens over complete request time. Unsupported route and probe-configuration rows are separated from provider downtime, and no prompt or output content is stored.
| Provider | p50 TTFT | p95 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|---|
| crusoe | 1424 ms | 1563 ms | 1424 ms | 42 tok/s n=1 | 100.00% | — | 2 |
| digitalocean | 1689 ms | 5313 ms | 1689 ms | — | 100.00% | — | 2 |
| parasail | 1789 ms | 4506 ms | 1789 ms | 106 tok/s n=1 | 100.00% | — | 3 |
| together | 2412 ms | 2632 ms | 2412 ms | 68 tok/s n=1 | 100.00% | — | 2 |
| telnyx | 2791 ms | 3158 ms | 2790 ms | 30 tok/s n=1 | 100.00% | — | 8 |
| tinfoil | 1856 ms | 4547 ms | 1855 ms | 43 tok/s n=1 | 84.62% | — | 13 |
| novita | — | — | — | 37 tok/s n=1 | — | — | 0 |
Full provider & model leaderboard.
14 routes.
More routes give the auto router more room to fail over around provider 429 and 5xx responses.
Gateway overhead is measured separately.
Public status separates TLS/health overhead from full model latency so slow LLMs do not inflate the router metric.
Metadata rollups.
Status samples store latency, outcome, provider, model, route, cost, and region metadata only.
View public status or inspect provider routes.