modelstatus.dev

Llama 4 Maverick

Llama 4 Maverick: providers compared

Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.

  • DigitalOcean100% (best)
    Healthy24h 99.73%
    7d
    99.71%
    30d
    99.71%
    p50
    648ms
    p99
    3.81s
    Throughput
    12 tps
    Context
    128K
    $/Mtok
    $0.200 / $0.696 (best)
    digitalocean
  • Google100% (best)
    Degraded24h 99.70%
    7d
    99.59%
    30d
    99.59%
    p50
    765ms
    p99
    50.5s
    Throughput
    100 tps (best)
    Context
    524K
    $/Mtok
    $0.350 / $1.15
    google-vertex/us-east5
  • Novita100% (best)
    Healthy24h 99.71%
    7d
    99.26%
    30d
    99.26%
    p50
    546ms
    p99
    4.45s
    Throughput
    73 tps
    Context
    1.0M
    $/Mtok
    $0.270 / $0.850
    novita/fp8fp8
  • DeepInfra98.97%
    Degraded24h 99.72%
    7d
    99.30%
    30d
    99.30%
    p50
    375ms (best)
    p99
    2.56s
    Throughput
    71 tps
    Context
    1.0M
    $/Mtok
    $0.200 / $0.800 (best)
    deepinfra/basefp8
  • Parasail90.19%
    Degraded24h 99.78%
    7d
    99.96% (best)
    30d
    99.96% (best)
    p50
    503ms
    p99
    2.34s (best)
    Throughput
    64 tps
    Context
    524K
    $/Mtok
    $0.350 / $1.00
    parasail/fp8fp8

Measured 5m ago. Latency and throughput are OpenRouter's rolling 30-minute windows. ◆ marks the best value in each column among these endpoints.

Price vs latency

One dot per endpoint at the latest round · further left = faster, lower = cheaper · hover a dot for its tag

History

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.