modelstatus.dev
CompareQwen3 32B
  • Healthy24h 99.98%
    7d
    99.84%
    30d
    99.78%
    p50
    368ms
    p99
    2.14s
    Throughput
    29 tps
    Context
    41K
    $/Mtok
    $0.080 / $0.280
    deepinfra/fp8fp8
  • Healthy24h 99.66%
    7d
    98.35%
    30d
    97.63%
    p50
    1.16s
    p99
    2.01s
    Throughput
    39 tps
    Context
    131K
    $/Mtok
    $0.140 / $0.570
    siliconflow/fp8fp8
  • Healthy24h 98.69%
    7d
    99.03%
    30d
    99.03%
    p50
    446ms
    p99
    2.89s
    Throughput
    39 tps
    Context
    41K
    $/Mtok
    $0.140 / $0.400
    tenstorrent/fp8fp8
  • Groq—
    No data24h —
    7d
    —
    30d
    —
    p50
    —
    p99
    —
    Throughput
    —
    Context
    131K
    $/Mtok
    $0.290 / $0.590
    groq
  • No data24h —
    7d
    —
    30d
    —
    p50
    —
    p99
    —
    Throughput
    —
    Context
    41K
    $/Mtok
    $0.100 / $0.300
    nebius/basefp8
  • No data24h —
    7d
    95.56%
    30d
    95.56%
    p50
    —
    p99
    —
    Throughput
    —
    Context
    41K
    $/Mtok
    $0.070 / $0.200
    tenstorrent/bf16bf16

Measured 4m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

2 endpoints have 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, 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 · 47 days with data, 39 endpoint-days below 90%.

Price changes

  • Qwen3 32BTenstorrenttenstorrent/fp8$0.070 → $0.140 / $0.200 → $0.400cache read $0.045 → $0.0902026-10-03 20:51 UTC