Kimi K2.5
moonshotai/kimi-k2.5
Compare with Kimi K2.6, Kimi K2.7 Code, Kimi K3
CompareKimi K2.5
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 99.20% | 99.33% | 99.33% | 1.91s | 16.1s | 29 tps | 262K | $0.490 / $2.50 | |
| Healthy | 100% | 99.95% | 99.62% | 99.62% | 861ms | 5.38s | 20 tps | 262K | $0.450 / $2.25 | |
DigitalOceandigitalocean | Healthy | 100% | 99.64% | 99.36% | 99.36% | 1.12s | 5.76s | 11 tps | 262K | $0.500 / $2.70 |
| Healthy | 100% | 99.94% | 99.97% | 99.97% | 1.68s | 13.0s | 27 tps | 262K | $0.600 / $3.00 | |
Novitanovita | Healthy | 100% | 98.97% | 99.08% | 99.08% | 1.14s | 12.6s | 32 tps | 262K | $0.570 / $2.85 |
| Healthy | 100% | 99.97% | 99.97% | 99.97% | 1.74s | 8.00s | 41 tps | 262K | $0.450 / $2.25 | |
| Healthy | 100% | 99.41% | 99.72% | 99.72% | 1.68s | 4.15s | 29 tps | 256K | $0.540 / $2.70 | |
Venicevenice | Healthy | 100% | 96.19% | 98.79% | 98.79% | 1.86s | 11.3s | 131 tps | 256K | $0.532 / $3.32 |
Amazon Bedrockamazon-bedrock/us-east-2 | No data | — | 99.00% | 98.59% | 98.59% | 935ms | 3.48s | 46 tps | 262K | $0.600 / $3.00 |
Phalaphala | No data | — | 76.56% | 94.12% | 94.12% | 2.03s | 7.59s | 38 tps | 262K | $0.600 / $3.00 |
- AtlasCloud100%Healthy24h 99.20%
- 7d
- 99.33%
- 30d
- 99.33%
- p50
- 1.91s
- p99
- 16.1s
- Throughput
- 29 tps
- Context
- 262K
- $/Mtok
- $0.490 / $2.50
atlas-cloud/int4int4 - DeepInfra100%Healthy24h 99.95%
- 7d
- 99.62%
- 30d
- 99.62%
- p50
- 861ms
- p99
- 5.38s
- Throughput
- 20 tps
- Context
- 262K
- $/Mtok
- $0.450 / $2.25
deepinfra/fp4fp4 - DigitalOcean100%Healthy24h 99.64%
- 7d
- 99.36%
- 30d
- 99.36%
- p50
- 1.12s
- p99
- 5.76s
- Throughput
- 11 tps
- Context
- 262K
- $/Mtok
- $0.500 / $2.70
digitalocean - Moonshot AI100%Healthy24h 99.94%
- 7d
- 99.97%
- 30d
- 99.97%
- p50
- 1.68s
- p99
- 13.0s
- Throughput
- 27 tps
- Context
- 262K
- $/Mtok
- $0.600 / $3.00
moonshotai/int4int4 - Novita100%Healthy24h 98.97%
- 7d
- 99.08%
- 30d
- 99.08%
- p50
- 1.14s
- p99
- 12.6s
- Throughput
- 32 tps
- Context
- 262K
- $/Mtok
- $0.570 / $2.85
novita - SiliconFlow100%Healthy24h 99.97%
- 7d
- 99.97%
- 30d
- 99.97%
- p50
- 1.74s
- p99
- 8.00s
- Throughput
- 41 tps
- Context
- 262K
- $/Mtok
- $0.450 / $2.25
siliconflow/int4int4 - StreamLake100%Healthy24h 99.41%
- 7d
- 99.72%
- 30d
- 99.72%
- p50
- 1.68s
- p99
- 4.15s
- Throughput
- 29 tps
- Context
- 256K
- $/Mtok
- $0.540 / $2.70
streamlake/fp8fp8 - Venice100%Healthy24h 96.19%
- 7d
- 98.79%
- 30d
- 98.79%
- p50
- 1.86s
- p99
- 11.3s
- Throughput
- 131 tps
- Context
- 256K
- $/Mtok
- $0.532 / $3.32
venice - No data24h 99.00%
- 7d
- 98.59%
- 30d
- 98.59%
- p50
- 935ms
- p99
- 3.48s
- Throughput
- 46 tps
- Context
- 262K
- $/Mtok
- $0.600 / $3.00
amazon-bedrock/us-east-2 - No data24h 76.56%
- 7d
- 94.12%
- 30d
- 94.12%
- p50
- 2.03s
- p99
- 7.59s
- Throughput
- 38 tps
- Context
- 262K
- $/Mtok
- $0.600 / $3.00
phala
Measured 4m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
Price changes
- Kimi K2.5DigitalOceandigitalocean$0.375 / $2.02 → $0.500 / $2.702026-08-21 03:30 UTC
History
2 endpoints reporting no data are omitted from the charts.
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.