modelstatus.dev

Gemma 4 26B A4B

google/gemma-4-26b-a4b-itInputimagetextvideoOutputtext

Compare its 16 providersIncident RSSCompare with Gemma 4 31B, Gemma 4 26B A4B (free), Gemma 4 31B (free)

CompareGemma 4 26B A4B
  • Healthy24h 100%
    7d
    99.67%
    30d
    99.67%
    p50
    451ms
    p99
    1.94s
    Throughput
    131 tps
    Context
    131K
    $/Mtok
    $0.070 / $0.240
    akashml/fp4fp4
  • Healthy24h 100%
    7d
    100%
    30d
    99.92%
    p50
    351ms
    p99
    5.30s
    Throughput
    41 tps
    Context
    256K
    $/Mtok
    $0.100 / $0.300
    cloudflare
  • Healthy24h 100%
    7d
    100%
    30d
    99.92%
    p50
    274ms
    p99
    2.22s
    Throughput
    96 tps
    Context
    262K
    $/Mtok
    $0.100 / $0.300
    coreweave/bf16bf16
  • Healthy24h 100%
    7d
    99.09%
    30d
    99.65%
    p50
    559ms
    p99
    3.28s
    Throughput
    50 tps
    Context
    131K
    $/Mtok
    $0.024 / $0.100
    darkbloom
  • Healthy24h 100%
    7d
    99.93%
    30d
    99.78%
    p50
    219ms
    p99
    1.53s
    Throughput
    75 tps
    Context
    262K
    $/Mtok
    $0.070 / $0.340
    deepinfra/fp8fp8
  • Healthy24h 100%
    7d
    99.75%
    30d
    99.88%
    p50
    457ms
    p99
    2.44s
    Throughput
    88 tps
    Context
    262K
    $/Mtok
    $0.060 / $0.330
    dekallm/bf16bf16
  • Google100%
    Healthy24h 98.74%
    7d
    93.15%
    30d
    92.11%
    p50
    2.02s
    p99
    9.60s
    Throughput
    29 tps
    Context
    262K
    $/Mtok
    $0.150 / $0.600
    google-vertex/global
  • Io Net100%
    Healthy24h 100%
    7d
    100%
    30d
    99.83%
    p50
    474ms
    p99
    2.28s
    Throughput
    114 tps
    Context
    262K
    $/Mtok
    $0.090 / $0.310
    io-net/bf16bf16
  • Makora100%
    Healthy24h 99.51%
    7d
    99.90%
    30d
    99.32%
    p50
    157ms
    p99
    1.91s
    Throughput
    232 tps
    Context
    256K
    $/Mtok
    $0.070 / $0.240
    makora
  • Healthy24h 100%
    7d
    99.96%
    30d
    99.86%
    p50
    327ms
    p99
    1.71s
    Throughput
    78 tps
    Context
    262K
    $/Mtok
    $0.068 / $0.225
    nextbit/bf16bf16
  • Novita100%
    Healthy24h 100%
    7d
    100%
    30d
    99.48%
    p50
    964ms
    p99
    2.76s
    Throughput
    103 tps
    Context
    262K
    $/Mtok
    $0.130 / $0.400
    novita/bf16bf16
  • Healthy24h 100%
    7d
    99.98%
    30d
    99.43%
    p50
    451ms
    p99
    2.82s
    Throughput
    97 tps
    Context
    262K
    $/Mtok
    $0.130 / $0.400
    parasail/bf16bf16
  • Healthy24h 100%
    7d
    99.98%
    30d
    99.98%
    p50
    675ms
    p99
    7.58s
    Throughput
    51 tps
    Context
    262K
    $/Mtok
    $0.024 / $0.071
    primeintellect/bf16bf16
  • Venice100%
    Healthy24h 99.65%
    7d
    99.90%
    30d
    99.71%
    p50
    712ms
    p99
    1.90s
    Throughput
    80 tps
    Context
    256K
    $/Mtok
    $0.130 / $0.400
    venice/bf16bf16
  • Down24h 96.50%
    7d
    92.13%
    30d
    94.51%
    p50
    1.86s
    p99
    5.03s
    Throughput
    44 tps
    Context
    262K
    $/Mtok
    $0.140 / $0.400
    siliconflow/fp8fp8
  • Reka—
    No data24h —
    7d
    —
    30d
    —
    p50
    —
    p99
    —
    Throughput
    —
    Context
    262K
    $/Mtok
    $0.060 / $0.200
    reka

Measured 3m 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 · 16 endpoints · 76 days with data, 167 endpoint-days below 90%.

Price changes