Meta: Llama 3.3 70B Instruct Performance
Compare measured TTFT, throughput, uptime, and route health for Meta: Llama 3.3 70B Instruct across TrustedRouter providers using metadata-only production probes.
meta-llama/llama-3.3-70b-instruct
Measured performance
Continuously sampled p50/p95 time-to-first-token (TTFT), 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 | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| together | 797 ms | 3910 ms | — | 100.00% | — | 2 |
| sambanova | 810 ms | 1061 ms | — | 100.00% | — | 2 |
| databricks | 1046 ms | 1051 ms | — | 100.00% | — | 2 |
| parasail | 1123 ms | 3856 ms | — | 100.00% | — | 2 |
| tinfoil | 1397 ms | 27709 ms | — | 100.00% | — | 8 |
| regolo | 1512 ms | 3320 ms | — | 100.00% | — | 3 |
| scaleway | 1525 ms | 3053 ms | — | 100.00% | — | 8 |
| wandb | 2767 ms | 2767 ms | — | 100.00% | — | 1 |
| io-net | 3224 ms | 3224 ms | — | 100.00% | — | 1 |
| akashml | 3381 ms | 3381 ms | — | 100.00% | — | 1 |
Full provider & model leaderboard.
12 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.