modelstatus.dev

Qwen3 30B A3B Instruct 2507

qwen/qwen3-30b-a3b-instruct-2507InputtextOutputtext

Compare its 6 providersIncident RSSCompare with Qwen3 235B A22B Instruct 2507, Qwen3 Coder 480B A35B, Qwen3 Next 80B A3B Instruct

CompareQwen3 30B A3B Instruct 2507
  • Healthy24h 99.95%
    7d
    99.96%
    30d
    99.96%
    p50
    328ms
    p99
    828ms
    Throughput
    40 tps
    Context
    131K
    $/Mtok
    $0.130 / $0.520
    alibaba
  • DekaLLM99.34%
    Healthy24h 99.15%
    7d
    99.06%
    30d
    99.06%
    p50
    398ms
    p99
    2.19s
    Throughput
    61 tps
    Context
    262K
    $/Mtok
    $0.090 / $0.300
    dekallm
  • Healthy24h 98.42%
    7d
    98.58%
    30d
    99.34%
    p50
    858ms
    p99
    3.65s
    Throughput
    69 tps
    Context
    128K
    $/Mtok
    $0.048 / $0.193
    streamlake
  • Nebius95.52%
    Healthy24h 95.78%
    7d
    93.47%
    30d
    95.75%
    p50
    295ms
    p99
    4.78s
    Throughput
    32 tps
    Context
    262K
    $/Mtok
    $0.100 / $0.300
    nebius/fp8fp8
  • Down24h 98.30%
    7d
    96.93%
    30d
    97.44%
    p50
    1.25s
    p99
    8.03s
    Throughput
    18 tps
    Context
    262K
    $/Mtok
    $0.090 / $0.300
    siliconflow/fp8fp8
  • No data24h
    7d
    30d
    99.45%
    p50
    p99
    Throughput
    Context
    262K
    $/Mtok
    $0.100 / $0.300
    coreweave/bf16bf16

Measured 2m 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, averaged over the hour.

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 · 6 endpoints · 30 days with data, 36 endpoint-days below 90%.