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% | 98.93% | 694ms | 11.1s | 20 tps | 131K | $0.090 / $0.300 |
DeepInfradeepinfra/fp8fp8 | Healthy | 99.71% | 98.03% | 359ms | 7.50s | 30 tps | 128K | $0.075 / $0.200 |
Venicevenice/fp8fp8 | Healthy | 99.61% | 98.80% | 542ms | 8.09s | 28 tps | 256K | $0.094 / $0.250 |
- Parasail100%Healthy24h 98.93%
- p50
- 694ms
- p99
- 11.1s
- Throughput
- 20 tps
- Context
- 131K
- $/Mtok
- $0.090 / $0.300
parasail/bf16bf16 - DeepInfra99.71%Healthy24h 98.03%
- p50
- 359ms
- p99
- 7.50s
- Throughput
- 30 tps
- Context
- 128K
- $/Mtok
- $0.075 / $0.200
deepinfra/fp8fp8 - Venice99.61%Healthy24h 98.80%
- p50
- 542ms
- p99
- 8.09s
- Throughput
- 28 tps
- Context
- 256K
- $/Mtok
- $0.094 / $0.250
venice/fp8fp8
Measured 4m 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.