Mistral Small 4: providers compared
Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.
Current state
- Mistral100%◆ (best)Healthy24h 99.82%
- 7d
- 99.69%
- 30d
- 99.69%
- p50
- 486ms◆ (best)
- p99
- 7.15s
- Throughput
- 104 tps
- Context
- 262K
- $/Mtok
- $0.150 / $0.600◆ (best)
mistral - Venice100%◆ (best)Healthy24h 99.92%
- 7d
- 99.89%◆ (best)
- 30d
- 99.89%◆ (best)
- p50
- 570ms
- p99
- 6.37s◆ (best)
- Throughput
- 83 tps
- Context
- 256K
- $/Mtok
- $0.188 / $0.750
venice/fp8fp8 - Mistral0.00%Down24h 0.00%
- 7d
- 0.00%
- 30d
- 0.00%
- p50
- 3.14s
- p99
- 15.6s
- Throughput
- 160 tps◆ (best)
- Context
- 262K
- $/Mtok
- $0.165 / $0.660
mistral/zdr
Measured 47s 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.