Kimi K2.5: 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) | 99.37% | 99.37% | 99.37% | 1.36s | 9.72s | 35 tps | 262K | $0.490 / $2.50 | |
| Healthy | 100%◆ (best) | 99.92% | 99.65% | 99.65% | 706ms◆ (best) | 25.0s | 23 tps | 262K | $0.450 / $2.25◆ (best) | |
DigitalOceandigitalocean | Healthy | 100%◆ (best) | 99.74% | 99.37% | 99.37% | 923ms | 4.88s◆ (best) | 13 tps | 262K | $0.500 / $2.70 |
| Healthy | 100%◆ (best) | 99.95% | 99.97% | 99.97% | 1.36s | 11.3s | 43 tps | 262K | $0.600 / $3.00 | |
Novitanovita | Healthy | 100%◆ (best) | 99.06% | 99.11% | 99.11% | 1.09s | 11.5s | 39 tps | 262K | $0.570 / $2.85 |
| Healthy | 100%◆ (best) | 99.98% | 99.98%◆ (best) | 99.98%◆ (best) | 1.85s | 49.6s | 37 tps | 262K | $0.450 / $2.25◆ (best) | |
| Healthy | 100%◆ (best) | 99.34% | 99.61% | 99.61% | 1.28s | 7.46s | 45 tps | 256K | $0.540 / $2.70 | |
Venicevenice | Healthy | 99.67% | 97.78% | 98.71% | 98.71% | 2.02s | 10.9s | 104 tps◆ (best) | 256K | $0.532 / $3.32 |
Amazon Bedrockamazon-bedrock/us-east-2 | No data | — | 99.05% | 98.72% | 98.72% | 821ms | 9.70s | 45 tps | 262K | $0.600 / $3.00 |
Phalaphala | No data | — | 80.68% | 94.12% | 94.12% | 1.62s | 6.66s | 45 tps | 262K | $0.600 / $3.00 |
- AtlasCloud100%◆ (best)Healthy24h 99.37%
- 7d
- 99.37%
- 30d
- 99.37%
- p50
- 1.36s
- p99
- 9.72s
- Throughput
- 35 tps
- Context
- 262K
- $/Mtok
- $0.490 / $2.50
atlas-cloud/int4int4 - DeepInfra100%◆ (best)Healthy24h 99.92%
- 7d
- 99.65%
- 30d
- 99.65%
- p50
- 706ms◆ (best)
- p99
- 25.0s
- Throughput
- 23 tps
- Context
- 262K
- $/Mtok
- $0.450 / $2.25◆ (best)
deepinfra/fp4fp4 - DigitalOcean100%◆ (best)Healthy24h 99.74%
- 7d
- 99.37%
- 30d
- 99.37%
- p50
- 923ms
- p99
- 4.88s◆ (best)
- Throughput
- 13 tps
- Context
- 262K
- $/Mtok
- $0.500 / $2.70
digitalocean - Moonshot AI100%◆ (best)Healthy24h 99.95%
- 7d
- 99.97%
- 30d
- 99.97%
- p50
- 1.36s
- p99
- 11.3s
- Throughput
- 43 tps
- Context
- 262K
- $/Mtok
- $0.600 / $3.00
moonshotai/int4int4 - Novita100%◆ (best)Healthy24h 99.06%
- 7d
- 99.11%
- 30d
- 99.11%
- p50
- 1.09s
- p99
- 11.5s
- Throughput
- 39 tps
- Context
- 262K
- $/Mtok
- $0.570 / $2.85
novita - SiliconFlow100%◆ (best)Healthy24h 99.98%
- 7d
- 99.98%◆ (best)
- 30d
- 99.98%◆ (best)
- p50
- 1.85s
- p99
- 49.6s
- Throughput
- 37 tps
- Context
- 262K
- $/Mtok
- $0.450 / $2.25◆ (best)
siliconflow/int4int4 - StreamLake100%◆ (best)Healthy24h 99.34%
- 7d
- 99.61%
- 30d
- 99.61%
- p50
- 1.28s
- p99
- 7.46s
- Throughput
- 45 tps
- Context
- 256K
- $/Mtok
- $0.540 / $2.70
streamlake/fp8fp8 - Venice99.67%Healthy24h 97.78%
- 7d
- 98.71%
- 30d
- 98.71%
- p50
- 2.02s
- p99
- 10.9s
- Throughput
- 104 tps◆ (best)
- Context
- 256K
- $/Mtok
- $0.532 / $3.32
venice - No data24h 99.05%
- 7d
- 98.72%
- 30d
- 98.72%
- p50
- 821ms
- p99
- 9.70s
- Throughput
- 45 tps
- Context
- 262K
- $/Mtok
- $0.600 / $3.00
amazon-bedrock/us-east-2 - No data24h 80.68%
- 7d
- 94.12%
- 30d
- 94.12%
- p50
- 1.62s
- p99
- 6.66s
- Throughput
- 45 tps
- Context
- 262K
- $/Mtok
- $0.600 / $3.00
phala
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, averaged over the hour.
Throughput
Median tokens per second.