modelstatus.dev

GPT-5.6 Terra

GPT-5.6 Terra: providers compared

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

  • Azure100% (best)
    Healthy24h 99.92%
    7d
    99.95%
    30d
    99.95%
    p50
    2.99s
    p99
    29.8s
    Throughput
    46 tps
    Context
    1.1M
    $/Mtok
    $2.00 / $12.00
    azure
  • Azure100% (best)
    Healthy24h 99.91%
    7d
    99.35%
    30d
    99.35%
    p50
    1.78s
    p99
    12.3s
    Throughput
    39 tps
    Context
    1.1M
    $/Mtok
    $2.20 / $13.20
    azure/us
  • OpenAI99.74%
    Healthy24h 99.87%
    7d
    99.91%
    30d
    99.91%
    p50
    2.34s
    p99
    50.5s
    Throughput
    48 tps
    Context
    1.1M
    $/Mtok
    $2.00 / $12.00
    openai
  • OpenAI99.74%
    Healthy24h 99.87%
    7d
    99.91%
    30d
    99.91%
    p50
    1.36s (best)
    p99
    7.90s
    Throughput
    111 tps (best)
    Context
    1.1M
    $/Mtok
    $1.00 / $6.00 (best)
    openai/flex
  • OpenAI99.74%
    Healthy24h 99.87%
    7d
    99.91%
    30d
    99.91%
    p50
    1.86s
    p99
    44.1s
    Throughput
    73 tps
    Context
    1.1M
    $/Mtok
    $4.00 / $24.00
    openai/priority
  • No data24h 100%
    7d
    100% (best)
    30d
    100% (best)
    p50
    p99
    Throughput
    Context
    1.1M
    $/Mtok
    $2.20 / $13.20
    amazon-bedrock/us-east-1
  • No data24h 100%
    7d
    99.99%
    30d
    99.99%
    p50
    1.90s
    p99
    7.27s (best)
    Throughput
    52 tps
    Context
    1.1M
    $/Mtok
    $2.20 / $13.20
    azure/eu

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, averaged over the hour.

Throughput

Median tokens per second.