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

CompareLlama 3.3 70B Instruct
  • Google100%
    Healthy24h 99.99%
    7d
    100%
    30d
    100%
    p50
    315ms
    p99
    2.11s
    Throughput
    51 tps
    Context
    128K
    $/Mtok
    $0.720 / $0.720
    google-vertex/us-central1
  • Healthy24h 96.63%
    7d
    95.22%
    30d
    95.22%
    p50
    874ms
    p99
    5.31s
    Throughput
    51 tps
    Context
    131K
    $/Mtok
    $0.450 / $0.900
    sambanova-turbo
  • Crusoe99.78%
    Healthy24h 99.71%
    7d
    99.00%
    30d
    99.00%
    p50
    435ms
    p99
    1.87s
    Throughput
    28 tps
    Context
    131K
    $/Mtok
    $0.250 / $0.750
    crusoe/bf16bf16
  • Groq99.61%
    Healthy24h 99.91%
    7d
    99.58%
    30d
    99.58%
    p50
    239ms
    p99
    1.85s
    Throughput
    154 tps
    Context
    131K
    $/Mtok
    $0.590 / $0.790
    groq
  • CoreWeave99.29%
    Healthy24h 98.29%
    7d
    97.64%
    30d
    97.64%
    p50
    255ms
    p99
    801ms
    Throughput
    54 tps
    Context
    128K
    $/Mtok
    $0.710 / $0.710
    coreweave/fp16fp16
  • Parasail98.63%
    Healthy24h 98.11%
    7d
    97.85%
    30d
    97.85%
    p50
    678ms
    p99
    7.59s
    Throughput
    33 tps
    Context
    131K
    $/Mtok
    $0.220 / $0.500
    parasail/fp8fp8
  • Novita98.08%
    Healthy24h 95.21%
    7d
    94.51%
    30d
    94.51%
    p50
    704ms
    p99
    2.73s
    Throughput
    33 tps
    Context
    12K
    $/Mtok
    $0.135 / $0.400
    novita/bf16bf16
  • DeepInfra97.87%
    Healthy24h 96.70%
    7d
    96.45%
    30d
    96.45%
    p50
    700ms
    p99
    6.93s
    Throughput
    14 tps
    Context
    131K
    $/Mtok
    $0.100 / $0.320
    deepinfra/turbofp8
  • Healthy24h 95.87%
    7d
    94.29%
    30d
    94.29%
    p50
    702ms
    p99
    5.17s
    Throughput
    40 tps
    Context
    24K
    $/Mtok
    $0.293 / $2.25
    cloudflare/fp8fp8
  • AkashML96.13%
    Degraded24h 96.96%
    7d
    97.35%
    30d
    97.35%
    p50
    1.66s
    p99
    12.3s
    Throughput
    16 tps
    Context
    131K
    $/Mtok
    $0.200 / $0.520
    akashml/fp8fp8
  • No data24h 99.15%
    7d
    98.34%
    30d
    98.34%
    p50
    317ms
    p99
    1.60s
    Throughput
    47 tps
    Context
    128K
    $/Mtok
    $0.720 / $0.720
    google-vertex
  • Down24h 41.53%
    7d
    43.62%
    30d
    43.62%
    p50
    6.49s
    p99
    46.7s
    Throughput
    0.0 tps
    Context
    131K
    $/Mtok
    $0.130 / $0.400
    nebius/fp8fp8
  • No data24h 98.18%
    7d
    97.67%
    30d
    97.67%
    p50
    722ms
    p99
    5.68s
    Throughput
    42 tps
    Context
    131K
    $/Mtok
    $1.04 / $1.04
    together

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

Price changes

2 endpoints reporting no data are omitted from the charts.

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.