Mistral Nemo
mistralai/mistral-nemo
Compare with Mistral Small 3.2 24B, Mistral Small 4, Mistral Large
CompareMistral Nemo
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Io Netio-net/fp16fp16 | Healthy | 100% | 97.70% | 598ms | 5.49s | 10 tps | 128K | $0.042 / $0.160 |
Parasailparasail/fp8fp8 | Healthy | 99.87% | 99.91% | 526ms | 2.26s | 30 tps | 131K | $0.030 / $0.030 |
DeepInfradeepinfra/fp8fp8 | Healthy | 97.94% | 98.35% | 451ms | 6.50s | 29 tps | 131K | $0.019 / $0.030 |
Novitanovita/fp8fp8 | Down | 85.22% | 59.07% | 13.0s | 62.5s | 6.0 tps | 60K | $0.040 / $0.170 |
- Io Net100%Healthy24h 97.70%
- p50
- 598ms
- p99
- 5.49s
- Throughput
- 10 tps
- Context
- 128K
- $/Mtok
- $0.042 / $0.160
io-net/fp16fp16 - Parasail99.87%Healthy24h 99.91%
- p50
- 526ms
- p99
- 2.26s
- Throughput
- 30 tps
- Context
- 131K
- $/Mtok
- $0.030 / $0.030
parasail/fp8fp8 - DeepInfra97.94%Healthy24h 98.35%
- p50
- 451ms
- p99
- 6.50s
- Throughput
- 29 tps
- Context
- 131K
- $/Mtok
- $0.019 / $0.030
deepinfra/fp8fp8 - Novita85.22%Down24h 59.07%
- p50
- 13.0s
- p99
- 62.5s
- Throughput
- 6.0 tps
- Context
- 60K
- $/Mtok
- $0.040 / $0.170
novita/fp8fp8
Measured 3m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
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 and p99 are OpenRouter's rolling 30-minute windows.
Throughput
Median tokens per second.