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
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Mistralmistral | Healthy | 100%◆ (best) | 99.98% | 99.97% | 99.93% | 535ms | 9.11s | 84 tps | 262K | $0.150 / $0.600◆ (best) |
Mistralmistral/us | Healthy | 100%◆ (best) | 99.95% | 100%◆ (best) | 99.99%◆ (best) | 468ms◆ (best) | 1.23s◆ (best) | 99 tps◆ (best) | 262K | $0.165 / $0.660 |
Mistralmistral/zdr | Healthy | 100%◆ (best) | 99.96% | 99.96% | 99.93% | 508ms | 9.00s | 79 tps | 262K | $0.150 / $0.600◆ (best) |
Mistralmistral/eu | No data | — | 99.97% | 99.97% | 99.97% | 724ms | 23.7s | 98 tps | 262K | $0.165 / $0.660 |
| No data | — | — | — | 99.85% | — | — | — | 256K | $0.188 / $0.750 |
- Mistral100%◆ (best)Healthy24h 99.98%
- 7d
- 99.97%
- 30d
- 99.93%
- p50
- 535ms
- p99
- 9.11s
- Throughput
- 84 tps
- Context
- 262K
- $/Mtok
- $0.150 / $0.600◆ (best)
mistral - Mistral100%◆ (best)Healthy24h 99.95%
- 7d
- 100%◆ (best)
- 30d
- 99.99%◆ (best)
- p50
- 468ms◆ (best)
- p99
- 1.23s◆ (best)
- Throughput
- 99 tps◆ (best)
- Context
- 262K
- $/Mtok
- $0.165 / $0.660
mistral/us - Mistral100%◆ (best)Healthy24h 99.96%
- 7d
- 99.96%
- 30d
- 99.93%
- p50
- 508ms
- p99
- 9.00s
- Throughput
- 79 tps
- Context
- 262K
- $/Mtok
- $0.150 / $0.600◆ (best)
mistral/zdr - No data24h 99.97%
- 7d
- 99.97%
- 30d
- 99.97%
- p50
- 724ms
- p99
- 23.7s
- Throughput
- 98 tps
- Context
- 262K
- $/Mtok
- $0.165 / $0.660
mistral/eu - No data24h —
- 7d
- —
- 30d
- 99.85%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 256K
- $/Mtok
- $0.188 / $0.750
venice/fp8fp8
Measured 2m 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.