modelstatus.dev

GPT-5.6 Luna

openai/gpt-5.6-luna

Compare with GPT-5.6 Sol, GPT-5.6 Terra, GPT-5.6 Luna Pro

CompareGPT-5.6 Luna
  • Healthy24h 100%
    7d
    100%
    30d
    100%
    p50
    1.42s
    p99
    12.0s
    Throughput
    104 tps
    Context
    1.1M
    $/Mtok
    $0.220 / $1.32
    amazon-bedrock/us-east-1
  • Azure100%
    Healthy24h 100%
    7d
    99.91%
    30d
    99.91%
    p50
    1.23s
    p99
    15.1s
    Throughput
    50 tps
    Context
    1.1M
    $/Mtok
    $0.220 / $1.32
    azure/eu
  • OpenAI99.45%
    Healthy24h 99.86%
    7d
    99.74%
    30d
    99.74%
    p50
    1.94s
    p99
    14.9s
    Throughput
    63 tps
    Context
    1.1M
    $/Mtok
    $0.200 / $1.20
    openai
  • OpenAI99.45%
    Healthy24h 99.86%
    7d
    99.74%
    30d
    99.74%
    p50
    2.07s
    p99
    25.2s
    Throughput
    69 tps
    Context
    1.1M
    $/Mtok
    $0.100 / $0.600
    openai/flex
  • OpenAI99.45%
    Healthy24h 99.86%
    7d
    99.74%
    30d
    99.74%
    p50
    1.19s
    p99
    4.95s
    Throughput
    50 tps
    Context
    1.1M
    $/Mtok
    $0.400 / $2.40
    openai/priority
  • Azure85.60%
    Down24h 90.73%
    7d
    95.26%
    30d
    95.26%
    p50
    3.39s
    p99
    25.5s
    Throughput
    34 tps
    Context
    1.1M
    $/Mtok
    $0.220 / $1.32
    azure/us
  • Azure82.13%
    Down24h 94.36%
    7d
    95.73%
    30d
    95.73%
    p50
    3.41s
    p99
    25.5s
    Throughput
    33 tps
    Context
    1.1M
    $/Mtok
    $0.200 / $1.20
    azure

Measured 4m 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 is OpenRouter's rolling 30-minute window.

Throughput

Median tokens per second.