modelstatus.dev

GPT-5.6 Luna

GPT-5.6 Luna: providers compared

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

  • Amazon Bedrock100% (best)
    Healthy24h 100%
    7d
    100% (best)
    30d
    100% (best)
    p50
    1.27s
    p99
    6.41s
    Throughput
    90 tps (best)
    Context
    1.1M
    $/Mtok
    $0.220 / $1.32
    amazon-bedrock/us-east-1
  • Azure100% (best)
    Healthy24h 100%
    7d
    99.92%
    30d
    99.92%
    p50
    1.48s
    p99
    9.55s
    Throughput
    42 tps
    Context
    1.1M
    $/Mtok
    $0.220 / $1.32
    azure/eu
  • Azure99.94%
    Healthy24h 94.55%
    7d
    95.62%
    30d
    95.62%
    p50
    3.60s
    p99
    25.5s
    Throughput
    44 tps
    Context
    1.1M
    $/Mtok
    $0.200 / $1.20
    azure
  • OpenAI99.59%
    Healthy24h 99.53%
    7d
    99.70%
    30d
    99.70%
    p50
    2.41s
    p99
    16.0s
    Throughput
    61 tps
    Context
    1.1M
    $/Mtok
    $0.200 / $1.20
    openai
  • OpenAI99.59%
    Healthy24h 99.53%
    7d
    99.70%
    30d
    99.70%
    p50
    3.68s
    p99
    41.3s
    Throughput
    50 tps
    Context
    1.1M
    $/Mtok
    $0.100 / $0.600 (best)
    openai/flex
  • OpenAI99.59%
    Healthy24h 99.53%
    7d
    99.70%
    30d
    99.70%
    p50
    1.06s (best)
    p99
    6.02s (best)
    Throughput
    29 tps
    Context
    1.1M
    $/Mtok
    $0.400 / $2.40
    openai/priority
  • No data24h 89.76%
    7d
    95.11%
    30d
    95.11%
    p50
    4.14s
    p99
    47.5s
    Throughput
    25 tps
    Context
    1.1M
    $/Mtok
    $0.220 / $1.32
    azure/us

Measured 3m 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.