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) | 98.98% | 98.21% | 98.21% | 840ms | 6.11s◆ (best) | 15 tps | 256K | $0.094 / $0.250 | |
| Healthy | 98.14% | 99.14% | 99.06%◆ (best) | 99.06%◆ (best) | 803ms | 16.1s | 14 tps | 131K | $0.090 / $0.300 | |
| No data | — | 99.44% | 97.37% | 97.37% | 484ms◆ (best) | 8.11s | 16 tps◆ (best) | 128K | $0.075 / $0.200◆ (best) |
- Venice100%◆ (best)Healthy24h 98.98%
- 7d
- 98.21%
- 30d
- 98.21%
- p50
- 840ms
- p99
- 6.11s◆ (best)
- Throughput
- 15 tps
- Context
- 256K
- $/Mtok
- $0.094 / $0.250
venice/fp8fp8 - Parasail98.14%Healthy24h 99.14%
- 7d
- 99.06%◆ (best)
- 30d
- 99.06%◆ (best)
- p50
- 803ms
- p99
- 16.1s
- Throughput
- 14 tps
- Context
- 131K
- $/Mtok
- $0.090 / $0.300
parasail/bf16bf16 - No data24h 99.44%
- 7d
- 97.37%
- 30d
- 97.37%
- p50
- 484ms◆ (best)
- p99
- 8.11s
- Throughput
- 16 tps◆ (best)
- Context
- 128K
- $/Mtok
- $0.075 / $0.200◆ (best)
deepinfra/fp8fp8
Measured 1m 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, averaged over the hour.
Throughput
Median tokens per second.