modelstatus.dev

Llama 3.3 70B Instruct

meta-llama/llama-3.3-70b-instruct

Compare with Llama 3.2 3B Instruct, Llama 3.2 1B Instruct, Llama 3.1 8B Instruct

Showing only the parasail/fp8 provider · show all 13

CompareLlama 3.3 70B Instruct
  • Parasail98.21%
    Healthy24h 98.12%
    7d
    97.85%
    30d
    97.85%
    p50
    665ms
    p99
    5.39s
    Throughput
    40 tps
    Context
    131K
    $/Mtok
    $0.220 / $0.500
    parasail/fp8fp8

Measured 1m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

Price changes

Availability

Axis starts at 90% so small differences stay visible; it expands to 0 when an endpoint falls below.

Time to first token

Logarithmic axis — the fleet spans two orders of magnitude. P50 is OpenRouter's rolling 30-minute window.

Throughput

Median tokens per second.