modelstatus.dev

Llama 4 Maverick

meta-llama/llama-4-maverick

Compare with Llama 4 Scout, Llama Guard 4 12B, Llama 3.3 70B Instruct

CompareLlama 4 Maverick
  • DeepInfra100%
    Healthy24h 99.06%
    p50
    338ms
    p99
    1.97s
    Throughput
    31 tps
    Context
    1.0M
    $/Mtok
    $0.200 / $0.800
    deepinfra/basefp8
  • Google100%
    Healthy24h 99.88%
    p50
    751ms
    p99
    1.98s
    Throughput
    76 tps
    Context
    524K
    $/Mtok
    $0.350 / $1.15
    google-vertex/us-east5
  • Novita100%
    Healthy24h 98.05%
    p50
    531ms
    p99
    1.45s
    Throughput
    28 tps
    Context
    1.0M
    $/Mtok
    $0.270 / $0.850
    novita/fp8fp8
  • Parasail100%
    Healthy24h 99.95%
    p50
    462ms
    p99
    2.36s
    Throughput
    38 tps
    Context
    524K
    $/Mtok
    $0.350 / $1.00
    parasail/fp8fp8
  • DigitalOcean97.87%
    Healthy24h 98.73%
    p50
    529ms
    p99
    3.33s
    Throughput
    9.0 tps
    Context
    128K
    $/Mtok
    $0.200 / $0.696
    digitalocean

Measured 3m 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 and p99 are OpenRouter's rolling 30-minute windows.

Throughput

Median tokens per second.