modelstatus.dev

Qwen3 235B A22B Instruct 2507

Qwen3 235B A22B Instruct 2507: providers compared

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

  • No data24h
    7d
    99.98% (best)
    30d
    99.98% (best)
    p50
    p99
    Throughput
    Context
    131K
    $/Mtok
    $0.150 / $0.598
    alibaba
  • No data24h
    7d
    99.81%
    30d
    99.81%
    p50
    p99
    Throughput
    Context
    131K
    $/Mtok
    $0.200 / $0.880
    atlas-cloud/fp8fp8
  • No data24h
    7d
    96.46%
    30d
    96.46%
    p50
    p99
    Throughput
    Context
    262K
    $/Mtok
    $0.090 / $0.550 (best)
    deepinfra/fp8fp8
  • No data24h
    7d
    99.75%
    30d
    99.75%
    p50
    p99
    Throughput
    Context
    262K
    $/Mtok
    $0.350 / $1.40
    gmicloud/fp8fp8
  • No data24h
    7d
    98.75%
    30d
    98.75%
    p50
    p99
    Throughput
    Context
    262K
    $/Mtok
    $0.250 / $1.00
    google-vertex/us-south1
  • No data24h
    7d
    95.24%
    30d
    95.24%
    p50
    p99
    Throughput
    Context
    262K
    $/Mtok
    $0.200 / $0.600
    nebius/fp8fp8
  • No data24h
    7d
    98.76%
    30d
    98.76%
    p50
    p99
    Throughput
    Context
    131K
    $/Mtok
    $0.090 / $0.580 (best)
    novita/fp8fp8
  • No data24h
    7d
    99.28%
    30d
    99.28%
    p50
    p99
    Throughput
    Context
    131K
    $/Mtok
    $0.140 / $0.800
    parasail/fp8fp8
  • No data24h
    7d
    99.84%
    30d
    99.84%
    p50
    p99
    Throughput
    Context
    128K
    $/Mtok
    $0.210 / $0.840
    streamlake
  • No data24h
    7d
    95.96%
    30d
    95.96%
    p50
    p99
    Throughput
    Context
    128K
    $/Mtok
    $0.150 / $0.750
    venice/fp8fp8

No recent measurement. ◆ marks the best value in each column among these endpoints.

Price vs latency

No endpoint currently reports both a price and a latency.

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.