modelstatus.dev

← Mistral Nemo

Mistral Nemo: providers compared

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

  • DeepInfra100%◆ (best)
    Healthy24h 99.94%
    7d
    99.94%◆ (best)
    30d
    99.92%◆ (best)
    p50
    806ms
    p99
    3.45s
    Throughput
    22 tps
    Context
    131K
    $/Mtok
    $0.019 / $0.030
    deepinfra/fp8fp8
  • Io Net100%◆ (best)
    Healthy24h 99.86%
    7d
    99.71%
    30d
    99.16%
    p50
    374ms
    p99
    2.39s
    Throughput
    49 tps
    Context
    128K
    $/Mtok
    $0.023 / $0.030
    io-net/fp16fp16
  • Novita100%◆ (best)
    Healthy24h 78.00%
    7d
    85.45%
    30d
    82.95%
    p50
    436ms
    p99
    1.47s
    Throughput
    74 tps
    Context
    60K
    $/Mtok
    $0.040 / $0.170
    novita/fp8fp8
  • Parasail100%◆ (best)
    Healthy24h 99.97%
    7d
    99.20%
    30d
    96.35%
    p50
    296ms◆ (best)
    p99
    1.09s
    Throughput
    97 tps◆ (best)
    Context
    131K
    $/Mtok
    $0.030 / $0.030
    parasail/fp8fp8
  • DekaLLM99.23%
    Healthy24h 99.82%
    7d
    99.78%
    30d
    99.64%
    p50
    537ms
    p99
    3.62s
    Throughput
    26 tps
    Context
    131K
    $/Mtok
    $0.018 / $0.030◆ (best)
    dekallm/fp8fp8
  • No data24h 98.02%
    7d
    99.78%
    30d
    99.74%
    p50
    408ms
    p99
    938ms◆ (best)
    Throughput
    69 tps
    Context
    131K
    $/Mtok
    $0.150 / $0.150
    mistral/eu
  • No data24h —
    7d
    —
    30d
    —
    p50
    —
    p99
    —
    Throughput
    —
    Context
    131K
    $/Mtok
    $0.165 / $0.165
    mistral/zdr

Measured 4m ago. Latency and throughput are OpenRouter's rolling 30-minute windows. ◆ marks the best value in each column among these endpoints.

Price vs latency

One dot per endpoint at the latest round · further left = faster, lower = cheaper · hover a dot for its tag

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, averaged over the hour.

Throughput

Median tokens per second.