Ministral 3 8B 2512: providers compared
Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.
Current state
- Mistral98.25%◆ (best)Healthy24h 99.21%
- 7d
- 98.89%
- 30d
- 98.84%
- p50
- 284ms
- p99
- 2.43s◆ (best)
- Throughput
- 93 tps
- Context
- 262K
- $/Mtok
- $0.150 / $0.150◆ (best)
mistral/zdr - Mistral96.14%Healthy24h 99.26%
- 7d
- 98.97%
- 30d
- 98.81%
- p50
- 280ms◆ (best)
- p99
- 3.81s
- Throughput
- 104 tps◆ (best)
- Context
- 262K
- $/Mtok
- $0.150 / $0.150◆ (best)
mistral - No data24h 100%
- 7d
- 99.99%◆ (best)
- 30d
- 100%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.165 / $0.165
mistral/eu
Measured 3m 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.