modelstatus.dev

Qwen3 Coder 30B A3B Instruct

qwen/qwen3-coder-30b-a3b-instructInputtextOutputtext

Compare its 4 providersIncident RSSCompare with Qwen3 235B A22B Instruct 2507, Qwen3 30B A3B Instruct 2507, Qwen3 Coder 480B A35B

CompareQwen3 Coder 30B A3B Instruct
  • Healthy24h 98.63%
    7d
    98.74%
    30d
    98.50%
    p50
    1.25s
    p99
    4.12s
    Throughput
    25 tps
    Context
    262K
    $/Mtok
    $0.070 / $0.280
    siliconflow/fp8fp8
  • Novita98.70%
    Healthy24h 97.29%
    7d
    98.46%
    30d
    97.56%
    p50
    990ms
    p99
    7.92s
    Throughput
    48 tps
    Context
    160K
    $/Mtok
    $0.070 / $0.270
    novita/fp8fp8
  • No data24h 99.97%
    7d
    100%
    30d
    100%
    p50
    971ms
    p99
    6.87s
    Throughput
    55 tps
    Context
    262K
    $/Mtok
    $0.292 / $1.46
    alibaba
  • No data24h —
    7d
    —
    30d
    —
    p50
    —
    p99
    —
    Throughput
    —
    Context
    0
    $/Mtok
    $0.150 / $0.600
    amazon-bedrock

Measured 2m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

1 endpoint has no chartable data in this range.

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 · 4 endpoints · 46 days with data, 46 endpoint-days below 90%.