Kimi K2.7 Code: 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) | 99.96% | 99.92% | 99.92% | 877ms | 12.2s | 120 tps | 262K | $0.710 / $3.50 | |
| Healthy | 100%◆ (best) | 99.82% | 99.82% | 99.82% | 817ms | 85.3s | 65 tps | 262K | $0.670 / $3.40◆ (best) | |
| No data | — | 99.79% | 100%◆ (best) | 100%◆ (best) | 3.75s | 8.12s | 29 tps | 262K | $0.950 / $4.00 | |
Ambientambient | No data | — | 99.73% | 100%◆ (best) | 100%◆ (best) | 821ms | 2.47s◆ (best) | 98 tps | 262K | $0.690 / $3.49 |
| No data | — | — | 100%◆ (best) | 100%◆ (best) | — | — | — | 262K | $0.950 / $4.00 | |
Cloudflarecloudflare | No data | — | 100% | 100%◆ (best) | 100%◆ (best) | 920ms | 7.72s | 47 tps | 262K | $0.950 / $4.00 |
| No data | — | 99.95% | 99.48% | 99.48% | 720ms | 8.49s | 32 tps | 262K | $0.680 / $3.40 | |
| No data | — | 96.29% | — | — | 3.35s | 33.0s | 36 tps | 262K | $0.950 / $4.00 | |
| Down | — | 45.99% | 83.84% | 83.84% | 386ms◆ (best) | 15.9s | 182 tps◆ (best) | 262K | $0.850 / $3.75 | |
| No data | — | 99.85% | 99.91% | 99.91% | 2.14s | 7.07s | 92 tps | 262K | $1.90 / $8.00 | |
| No data | — | 99.92% | 99.71% | 99.71% | 1.47s | 35.9s | 52 tps | 262K | $0.950 / $4.00 | |
| No data | — | 99.80% | 99.22% | 99.22% | 1.68s | 25.4s | 36 tps | 262K | $0.912 / $3.84 | |
| No data | — | 99.12% | 99.31% | 99.31% | 776ms | 7.50s | 65 tps | 262K | $0.760 / $3.50 | |
| No data | — | 99.94% | 99.98% | 99.98% | 1.60s | 6.55s | 43 tps | 262K | $0.859 / $3.80 | |
Togethertogether | Down | — | 18.32% | 78.83% | 78.83% | 708ms | 10.7s | 177 tps | 262K | $0.950 / $4.00 |
| No data | — | 97.64% | 97.52% | 97.52% | 1.06s | 4.57s | 32 tps | 256K | $0.750 / $3.50 |
- CoreWeave100%◆ (best)Healthy24h 99.96%
- 7d
- 99.92%
- 30d
- 99.92%
- p50
- 877ms
- p99
- 12.2s
- Throughput
- 120 tps
- Context
- 262K
- $/Mtok
- $0.710 / $3.50
coreweave/int4int4 - Inceptron100%◆ (best)Healthy24h 99.82%
- 7d
- 99.82%
- 30d
- 99.82%
- p50
- 817ms
- p99
- 85.3s
- Throughput
- 65 tps
- Context
- 262K
- $/Mtok
- $0.670 / $3.40◆ (best)
inceptron/int4int4 - No data24h 99.79%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 3.75s
- p99
- 8.12s
- Throughput
- 29 tps
- Context
- 262K
- $/Mtok
- $0.950 / $4.00
alibaba/fp8fp8 - No data24h 99.73%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 821ms
- p99
- 2.47s◆ (best)
- Throughput
- 98 tps
- Context
- 262K
- $/Mtok
- $0.690 / $3.49
ambient - No data24h —
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.950 / $4.00
atlas-cloud/int4int4 - No data24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 920ms
- p99
- 7.72s
- Throughput
- 47 tps
- Context
- 262K
- $/Mtok
- $0.950 / $4.00
cloudflare - No data24h 99.95%
- 7d
- 99.48%
- 30d
- 99.48%
- p50
- 720ms
- p99
- 8.49s
- Throughput
- 32 tps
- Context
- 262K
- $/Mtok
- $0.680 / $3.40
deepinfra/fp4fp4 - No data24h 96.29%
- 7d
- —
- 30d
- —
- p50
- 3.35s
- p99
- 33.0s
- Throughput
- 36 tps
- Context
- 262K
- $/Mtok
- $0.950 / $4.00
gmicloud/fp8fp8 - Down24h 45.99%
- 7d
- 83.84%
- 30d
- 83.84%
- p50
- 386ms◆ (best)
- p99
- 15.9s
- Throughput
- 182 tps◆ (best)
- Context
- 262K
- $/Mtok
- $0.850 / $3.75
modelrun/fp4fp4 - No data24h 99.85%
- 7d
- 99.91%
- 30d
- 99.91%
- p50
- 2.14s
- p99
- 7.07s
- Throughput
- 92 tps
- Context
- 262K
- $/Mtok
- $1.90 / $8.00
moonshotai/highspeedint4 - No data24h 99.92%
- 7d
- 99.71%
- 30d
- 99.71%
- p50
- 1.47s
- p99
- 35.9s
- Throughput
- 52 tps
- Context
- 262K
- $/Mtok
- $0.950 / $4.00
moonshotai/int4int4 - No data24h 99.80%
- 7d
- 99.22%
- 30d
- 99.22%
- p50
- 1.68s
- p99
- 25.4s
- Throughput
- 36 tps
- Context
- 262K
- $/Mtok
- $0.912 / $3.84
novita/int4int4 - No data24h 99.12%
- 7d
- 99.31%
- 30d
- 99.31%
- p50
- 776ms
- p99
- 7.50s
- Throughput
- 65 tps
- Context
- 262K
- $/Mtok
- $0.760 / $3.50
parasail/int4int4 - No data24h 99.94%
- 7d
- 99.98%
- 30d
- 99.98%
- p50
- 1.60s
- p99
- 6.55s
- Throughput
- 43 tps
- Context
- 262K
- $/Mtok
- $0.859 / $3.80
siliconflow/fp8fp8 - Down24h 18.32%
- 7d
- 78.83%
- 30d
- 78.83%
- p50
- 708ms
- p99
- 10.7s
- Throughput
- 177 tps
- Context
- 262K
- $/Mtok
- $0.950 / $4.00
together - No data24h 97.64%
- 7d
- 97.52%
- 30d
- 97.52%
- p50
- 1.06s
- p99
- 4.57s
- Throughput
- 32 tps
- Context
- 256K
- $/Mtok
- $0.750 / $3.50
venice/int4int4
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.