MiniMax M3.1 Flash: 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) | 100% | — | — | 2.84s | 38.6s | 14 tps | 1.0M | $0.100 / $0.500◆ (best) | |
Minimaxminimax | Healthy | 100%◆ (best) | 99.67% | — | — | 1.56s | 8.62s | 57 tps | 1.0M | $0.150 / $0.600 |
| Healthy | 100%◆ (best) | 100% | — | — | 470ms◆ (best) | 8.34s | 112 tps◆ (best) | 1.0M | $0.150 / $0.600 | |
Togethertogether | Healthy | 100%◆ (best) | 100% | — | — | 758ms | 8.94s | 80 tps | 1.0M | $0.150 / $0.600 |
Waferwafer | No data | — | 100% | — | — | 1.68s | 6.70s◆ (best) | 41 tps | 1.0M | $0.150 / $0.600 |
- InferenceNet100%◆ (best)Healthy24h 100%
- 7d
- —
- 30d
- —
- p50
- 2.84s
- p99
- 38.6s
- Throughput
- 14 tps
- Context
- 1.0M
- $/Mtok
- $0.100 / $0.500◆ (best)
inference-net/fp4fp4 - Minimax100%◆ (best)Healthy24h 99.67%
- 7d
- —
- 30d
- —
- p50
- 1.56s
- p99
- 8.62s
- Throughput
- 57 tps
- Context
- 1.0M
- $/Mtok
- $0.150 / $0.600
minimax - Parasail100%◆ (best)Healthy24h 100%
- 7d
- —
- 30d
- —
- p50
- 470ms◆ (best)
- p99
- 8.34s
- Throughput
- 112 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $0.150 / $0.600
parasail/fp8fp8 - Together100%◆ (best)Healthy24h 100%
- 7d
- —
- 30d
- —
- p50
- 758ms
- p99
- 8.94s
- Throughput
- 80 tps
- Context
- 1.0M
- $/Mtok
- $0.150 / $0.600
together - No data24h 100%
- 7d
- —
- 30d
- —
- p50
- 1.68s
- p99
- 6.70s◆ (best)
- Throughput
- 41 tps
- Context
- 1.0M
- $/Mtok
- $0.150 / $0.600
wafer
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.
Throughput
Median tokens per second.