modelstatus.dev

Grok 4.7

Grok 4.7: providers compared

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

  • xAI100% (best)
    Healthy24h 99.62%
    7d
    99.90%
    30d
    99.90%
    p50
    1.56s
    p99
    55.1s
    Throughput
    55 tps
    Context
    500K
    $/Mtok
    $1.60 / $4.80 (best)
    xai/zdr
  • xAI99.93%
    Healthy24h 99.31%
    7d
    99.79%
    30d
    99.79%
    p50
    2.32s
    p99
    84.7s
    Throughput
    53 tps
    Context
    500K
    $/Mtok
    $1.60 / $4.80 (best)
    xai
  • xAI
    No data24h 99.60%
    7d
    30d
    p50
    1.29s (best)
    p99
    12.3s
    Throughput
    61 tps (best)
    Context
    500K
    $/Mtok
    $3.20 / $9.60
    xai/priority
  • xAI
    No data24h 99.59%
    7d
    100% (best)
    30d
    100% (best)
    p50
    1.31s
    p99
    6.22s (best)
    Throughput
    48 tps
    Context
    500K
    $/Mtok
    $3.20 / $9.60
    xai/zdr/priority

Measured 4m 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.