Mistral Small 3.2 24B
mistralai/mistral-small-3.2-24b-instruct
Compare with Mistral Nemo, Mistral Large, Saba
CompareMistral Small 3.2 24B
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Parasailparasail/bf16bf16 | Healthy | 100% | 98.96% | 914ms | 11.1s | 16 tps | 131K | $0.090 / $0.300 |
Venicevenice/fp8fp8 | Healthy | 96.43% | 98.74% | 588ms | 5.03s | 23 tps | 256K | $0.094 / $0.250 |
DeepInfradeepinfra/fp8fp8 | Healthy | 96.05% | 97.72% | 383ms | 7.92s | 25 tps | 128K | $0.075 / $0.200 |
- Parasail100%Healthy24h 98.96%
- p50
- 914ms
- p99
- 11.1s
- Throughput
- 16 tps
- Context
- 131K
- $/Mtok
- $0.090 / $0.300
parasail/bf16bf16 - Venice96.43%Healthy24h 98.74%
- p50
- 588ms
- p99
- 5.03s
- Throughput
- 23 tps
- Context
- 256K
- $/Mtok
- $0.094 / $0.250
venice/fp8fp8 - DeepInfra96.05%Healthy24h 97.72%
- p50
- 383ms
- p99
- 7.92s
- Throughput
- 25 tps
- Context
- 128K
- $/Mtok
- $0.075 / $0.200
deepinfra/fp8fp8
Measured 2m 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, averaged over the hour.
Throughput
Median tokens per second.