Mistral Nemo
mistralai/mistral-nemo
Compare with Mistral Small 3.2 24B, Mistral Small 4, Mistral Large
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Parasailparasail/fp8fp8 | Healthy | 99.77% | 99.91% | 467ms | 2.31s | 39 tps | 131K | $0.030 / $0.030 |
Io Netio-net/fp16fp16 | Healthy | 99.66% | 97.70% | 521ms | 5.24s | 10 tps | 128K | $0.042 / $0.160 |
DeepInfradeepinfra/fp8fp8 | Healthy | 99.45% | 98.37% | 319ms | 2.54s | 29 tps | 131K | $0.019 / $0.030 |
Novitanovita/fp8fp8 | Down | 89.57% | 59.42% | 3.56s | 61.2s | 6.0 tps | 60K | $0.040 / $0.170 |
- Parasail99.77%Healthy24h 99.91%
- p50
- 467ms
- p99
- 2.31s
- Throughput
- 39 tps
- Context
- 131K
- $/Mtok
- $0.030 / $0.030
parasail/fp8fp8 - Io Net99.66%Healthy24h 97.70%
- p50
- 521ms
- p99
- 5.24s
- Throughput
- 10 tps
- Context
- 128K
- $/Mtok
- $0.042 / $0.160
io-net/fp16fp16 - DeepInfra99.45%Healthy24h 98.37%
- p50
- 319ms
- p99
- 2.54s
- Throughput
- 29 tps
- Context
- 131K
- $/Mtok
- $0.019 / $0.030
deepinfra/fp8fp8 - Novita89.57%Down24h 59.42%
- p50
- 3.56s
- p99
- 61.2s
- 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.