Mistral Small 3.2 24B: providers compared
Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.
Current state
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100%◆ (best) | 98.90% | 98.19% | 98.19% | 758ms | 6.79s◆ (best) | 14 tps◆ (best) | 256K | $0.094 / $0.250 | |
| Healthy | 99.83% | 99.36% | 97.33% | 97.33% | 402ms◆ (best) | 10.0s | 10 tps | 128K | $0.075 / $0.200◆ (best) | |
| Healthy | 98.60% | 99.21% | 99.07%◆ (best) | 99.07%◆ (best) | 592ms | 10.4s | 11 tps | 131K | $0.090 / $0.300 |
- Venice100%◆ (best)Healthy24h 98.90%
- 7d
- 98.19%
- 30d
- 98.19%
- p50
- 758ms
- p99
- 6.79s◆ (best)
- Throughput
- 14 tps◆ (best)
- Context
- 256K
- $/Mtok
- $0.094 / $0.250
venice/fp8fp8 - DeepInfra99.83%Healthy24h 99.36%
- 7d
- 97.33%
- 30d
- 97.33%
- p50
- 402ms◆ (best)
- p99
- 10.0s
- Throughput
- 10 tps
- Context
- 128K
- $/Mtok
- $0.075 / $0.200◆ (best)
deepinfra/fp8fp8 - Parasail98.60%Healthy24h 99.21%
- 7d
- 99.07%◆ (best)
- 30d
- 99.07%◆ (best)
- p50
- 592ms
- p99
- 10.4s
- Throughput
- 11 tps
- Context
- 131K
- $/Mtok
- $0.090 / $0.300
parasail/bf16bf16
Measured 5m 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.
Throughput
Median tokens per second.