modelstatus.dev

Llama 3.1 8B Instruct

meta-llama/llama-3.1-8b-instructInputtextOutputtext

Compare its 5 providersIncident RSSCompare with Llama 3.1 70B Instruct, Llama 3.2 3B Instruct, Llama 3.2 1B Instruct

CompareLlama 3.1 8B Instruct
  • Healthy24h 99.58%
    7d
    99.09%
    30d
    98.66%
    p50
    439ms
    p99
    1.13s
    Throughput
    20 tps
    Context
    32K
    $/Mtok
    $0.152 / $0.287
    cloudflare/fp8fp8
  • Healthy24h 100%
    7d
    100%
    30d
    99.96%
    p50
    310ms
    p99
    2.05s
    Throughput
    124 tps
    Context
    131K
    $/Mtok
    $0.220 / $0.220
    coreweave/bf16bf16
  • Healthy24h 99.93%
    7d
    99.62%
    30d
    99.27%
    p50
    605ms
    p99
    3.56s
    Throughput
    22 tps
    Context
    131K
    $/Mtok
    $0.020 / $0.040
    deepinfra/fp8fp8
  • Novita100%
    Healthy24h 99.76%
    7d
    99.26%
    30d
    98.54%
    p50
    516ms
    p99
    2.62s
    Throughput
    98 tps
    Context
    16K
    $/Mtok
    $0.020 / $0.050
    novita/fp8fp8
  • Groq99.47%
    Healthy24h 99.80%
    7d
    99.72%
    30d
    99.66%
    p50
    134ms
    p99
    1.06s
    Throughput
    358 tps
    Context
    131K
    $/Mtok
    $0.050 / $0.080
    groq

Measured 4m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

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, averaged over the hour.

Throughput

Median tokens per second.

Daily availability

One row per endpoint · one dot per day · last 90 days.

worst hour ≥ 95%90–95%< 90%no data

Colour by each endpoint's worst hour of each UTC day · 5 endpoints · 47 days with data, 20 endpoint-days below 90%.