Kimi K3
moonshotai/kimi-k3
Compare with Kimi K2.7 Code, Kimi K2.6, Kimi K2.5
CompareKimi K3
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Fireworksfireworks | Healthy | 100% | 98.81% | 3.30s | 62.4s | 37 tps | 1.0M | $3.00 / $15.00 |
Waferwafer | Healthy | 100% | 95.37% | 9.52s | 155s | 14 tps | 1.0M | $3.00 / $15.00 |
Modalmodal/mxfp4mxfp4 | Healthy | 99.83% | 99.40% | 2.40s | 22.2s | 53 tps | 1.0M | $3.00 / $15.00 |
Moonshot AImoonshotai/mxfp4mxfp4 | Healthy | 99.66% | 99.74% | 4.91s | 63.2s | 22 tps | 1.0M | $3.00 / $15.00 |
Morphmorph/fp4fp4 | Degraded | 99.41% | 79.28% | 2.65s | 56.1s | 24 tps | 1.0M | $2.80 / $14.00 |
Togethertogether | Healthy | 99.40% | 98.97% | 2.30s | 22.3s | 49 tps | 1.0M | $3.00 / $15.00 |
DigitalOceandigitalocean | Healthy | 99.34% | 98.39% | 2.09s | 46.9s | 23 tps | 1.0M | $2.85 / $14.25 |
Sail Researchsail-research/fp4fp4 | Healthy | 98.46% | 98.32% | 4.89s | 77.1s | 31 tps | 975K | $2.60 / $13.00 |
Chuteschutes/mxfp4mxfp4 | Healthy | 97.56% | 96.78% | 2.09s | 40.6s | 16 tps | 1.0M | $3.00 / $15.00 |
Phalaphala | Healthy | 96.09% | 94.81% | 3.48s | 15.4s | 37 tps | 1.0M | $3.00 / $15.00 |
BaseTenbaseten/fp8fp8 | No data | — | 92.90% | 1.67s | 50.4s | 41 tps | 1.0M | $3.00 / $15.00 |
DeepInfradeepinfra/bf16bf16 | Degraded | — | 95.48% | 2.79s | 118s | 15 tps | 1.0M | $2.85 / $14.25 |
Morphmorph/fastfp4 | Down | — | 68.78% | 2.72s | 85.4s | 22 tps | 1.0M | $6.00 / $22.50 |
- Fireworks100%Healthy24h 98.81%
- p50
- 3.30s
- p99
- 62.4s
- Throughput
- 37 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00
fireworks - Wafer100%Healthy24h 95.37%
- p50
- 9.52s
- p99
- 155s
- Throughput
- 14 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00
wafer - Modal99.83%Healthy24h 99.40%
- p50
- 2.40s
- p99
- 22.2s
- Throughput
- 53 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00
modal/mxfp4mxfp4 - Moonshot AI99.66%Healthy24h 99.74%
- p50
- 4.91s
- p99
- 63.2s
- Throughput
- 22 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00
moonshotai/mxfp4mxfp4 - Morph99.41%Degraded24h 79.28%
- p50
- 2.65s
- p99
- 56.1s
- Throughput
- 24 tps
- Context
- 1.0M
- $/Mtok
- $2.80 / $14.00
morph/fp4fp4 - Together99.40%Healthy24h 98.97%
- p50
- 2.30s
- p99
- 22.3s
- Throughput
- 49 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00
together - DigitalOcean99.34%Healthy24h 98.39%
- p50
- 2.09s
- p99
- 46.9s
- Throughput
- 23 tps
- Context
- 1.0M
- $/Mtok
- $2.85 / $14.25
digitalocean - Sail Research98.46%Healthy24h 98.32%
- p50
- 4.89s
- p99
- 77.1s
- Throughput
- 31 tps
- Context
- 975K
- $/Mtok
- $2.60 / $13.00
sail-research/fp4fp4 - Chutes97.56%Healthy24h 96.78%
- p50
- 2.09s
- p99
- 40.6s
- Throughput
- 16 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00
chutes/mxfp4mxfp4 - Phala96.09%Healthy24h 94.81%
- p50
- 3.48s
- p99
- 15.4s
- Throughput
- 37 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00
phala - BaseTen—No data24h 92.90%
- p50
- 1.67s
- p99
- 50.4s
- Throughput
- 41 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00
baseten/fp8fp8 - DeepInfra—Degraded24h 95.48%
- p50
- 2.79s
- p99
- 118s
- Throughput
- 15 tps
- Context
- 1.0M
- $/Mtok
- $2.85 / $14.25
deepinfra/bf16bf16 - Morph—Down24h 68.78%
- p50
- 2.72s
- p99
- 85.4s
- Throughput
- 22 tps
- Context
- 1.0M
- $/Mtok
- $6.00 / $22.50
morph/fastfp4
Measured 2m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
1 endpoint reporting no data is 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 and p99 are OpenRouter's rolling 30-minute windows.
Throughput
Median tokens per second.