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
    1.29s
    p99
    7.50s (best)
    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
    1.33s
    p99
    11.6s
    Throughput
    46 tps
    Context
    1.1M
    $/Mtok
    $0.220 / $1.32
    azure/eu
  • Azure99.79%
    Healthy24h 94.19%
    7d
    95.55%
    30d
    95.55%
    p50
    3.53s
    p99
    20.9s
    Throughput
    51 tps
    Context
    1.1M
    $/Mtok
    $0.200 / $1.20
    azure
  • OpenAI99.58%
    Healthy24h 99.64%
    7d
    99.70%
    30d
    99.70%
    p50
    2.44s
    p99
    15.2s
    Throughput
    62 tps
    Context
    1.1M
    $/Mtok
    $0.200 / $1.20
    openai
  • OpenAI99.58%
    Healthy24h 99.64%
    7d
    99.70%
    30d
    99.70%
    p50
    5.80s
    p99
    76.2s
    Throughput
    34 tps
    Context
    1.1M
    $/Mtok
    $0.100 / $0.600 (best)
    openai/flex
  • OpenAI99.58%
    Healthy24h 99.64%
    7d
    99.70%
    30d
    99.70%
    p50
    1.25s (best)
    p99
    8.05s
    Throughput
    33 tps
    Context
    1.1M
    $/Mtok
    $0.400 / $2.40
    openai/priority
  • Azure96.43%
    Healthy24h 89.66%
    7d
    95.03%
    30d
    95.03%
    p50
    4.44s
    p99
    30.9s
    Throughput
    46 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.