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
Performance
Measured performance
Continuously sampled p50/p95 time-to-first-token (TTFT), time-to-first-byte (TTFB), throughput, and success rate for Meta: Llama 3.3 70B Instruct — 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 | Throughput | Uptime | Config excluded | Samples |
|---|---|---|---|---|---|---|---|
| novita | 596 ms | 596 ms | 594 ms | — | 25.00% | — | 4 |
| tinfoil | 927 ms | 1291 ms | 834 ms | — | 53.33% | — | 75 |
| parasail | 965 ms | 8330 ms | 944 ms | — | 69.23% | — | 13 |
| together | 1163 ms | 2596 ms | 1161 ms | — | 50.00% | — | 120 |
Full provider & model leaderboard.
9 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.