modelstatus.dev

Llama 3.1 8B Instruct

meta-llama/llama-3.1-8b-instruct

Compare with Llama 3.1 70B Instruct, Llama 3.2 3B Instruct, Llama 3.2 1B Instruct

CompareLlama 3.1 8B Instruct
  • Healthy24h 99.91%
    7d
    99.90%
    30d
    99.90%
    p50
    499ms
    p99
    2.55s
    Throughput
    17 tps
    Context
    32K
    $/Mtok
    $0.152 / $0.287
    cloudflare/fp8fp8
  • Healthy24h 100%
    7d
    99.99%
    30d
    99.99%
    p50
    177ms
    p99
    507ms
    Throughput
    92 tps
    Context
    128K
    $/Mtok
    $0.220 / $0.220
    coreweave/bf16bf16
  • DeepInfra99.95%
    Healthy24h 99.88%
    7d
    99.36%
    30d
    99.36%
    p50
    487ms
    p99
    3.08s
    Throughput
    25 tps
    Context
    131K
    $/Mtok
    $0.020 / $0.040
    deepinfra/fp8fp8
  • Groq99.84%
    Healthy24h 99.93%
    7d
    99.90%
    30d
    99.90%
    p50
    246ms
    p99
    1.02s
    Throughput
    116 tps
    Context
    131K
    $/Mtok
    $0.050 / $0.080
    groq
  • Novita99.59%
    Healthy24h 99.78%
    7d
    99.77%
    30d
    99.77%
    p50
    491ms
    p99
    1.90s
    Throughput
    52 tps
    Context
    16K
    $/Mtok
    $0.020 / $0.050
    novita/fp8fp8

Measured 2m 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.

Throughput

Median tokens per second.