Kimi K3.1 Pro: 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% | 100%◆ (best) | 100%◆ (best) | 5.37s | 12.9s◆ (best) | 59 tps◆ (best) | 1.0M | $4.00 / $20.00 | |
| Healthy | 100%◆ (best) | 100% | 100%◆ (best) | 100%◆ (best) | 4.46s◆ (best) | 12.9s | 37 tps | 1.0M | $2.00 / $10.00◆ (best) |
- Moonshot AI100%◆ (best)Healthy24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 5.37s
- p99
- 12.9s◆ (best)
- Throughput
- 59 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $4.00 / $20.00
moonshotai/highspeedmxfp4 - Moonshot AI100%◆ (best)Healthy24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 4.46s◆ (best)
- p99
- 12.9s
- Throughput
- 37 tps
- Context
- 1.0M
- $/Mtok
- $2.00 / $10.00◆ (best)
moonshotai/mxfp4mxfp4
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.