modelstatus.dev

GPT-6 Luna

openai/gpt-6-lunaInputfileimagetextOutputtext

Compare its 7 providersIncident RSSCompare with GPT-6 Sol, GPT-6 Astra, GPT-6 Luna Pro

CompareGPT-6 Luna
  • Healthy24h 100%
    7d
    100%
    30d
    100%
    p50
    931ms
    p99
    11.2s
    Throughput
    44 tps
    Context
    1.1M
    $/Mtok
    $0.110 / $0.550
    amazon-bedrock/us-east-1
  • Azure100%
    Healthy24h 100%
    7d
    100%
    30d
    100%
    p50
    3.55s
    p99
    89.6s
    Throughput
    158 tps
    Context
    1.1M
    $/Mtok
    $0.110 / $0.550
    azure/eu
  • OpenAI100%
    Healthy24h 99.99%
    7d
    100%
    30d
    100%
    p50
    2.00s
    p99
    237s
    Throughput
    59 tps
    Context
    1.1M
    $/Mtok
    $0.200 / $1.00
    openai/fast
  • OpenAI100%
    Healthy24h 100%
    7d
    100%
    30d
    100%
    p50
    3.64s
    p99
    40.8s
    Throughput
    118 tps
    Context
    1.1M
    $/Mtok
    $0.050 / $0.250
    openai/flex
  • OpenAI100%
    Healthy24h 99.99%
    7d
    99.95%
    30d
    99.95%
    p50
    1.72s
    p99
    14.2s
    Throughput
    65 tps
    Context
    1.1M
    $/Mtok
    $0.100 / $0.500
    openai
  • Azure99.68%
    Healthy24h 92.20%
    7d
    91.93%
    30d
    91.93%
    p50
    3.97s
    p99
    34.4s
    Throughput
    95 tps
    Context
    1.1M
    $/Mtok
    $0.100 / $0.500
    azure
  • No data24h 100%
    7d
    30d
    p50
    1.35s
    p99
    25.4s
    Throughput
    76 tps
    Context
    1.1M
    $/Mtok
    $0.110 / $0.550
    azure/us

Measured 5m 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.

Daily availability

One row per endpoint · one dot per day · last 90 days.

worst hour ≥ 95%90–95%< 90%no data

Colour by each endpoint's worst hour of each UTC day · 7 endpoints · 1 day with data, 1 endpoint-day below 90%.