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 |
|---|---|---|---|---|---|---|---|---|
Morphmorph/fastfp4 | Down | 100% | 68.56% | 14.3s | 117s | 9.0 tps | 1.0M | $6.00 / $22.50 |
Waferwafer | Degraded | 100% | 95.15% | 51.6s | 256s | 4.0 tps | 1.0M | $3.00 / $15.00 |
Moonshot AImoonshotai/mxfp4mxfp4 | Healthy | 99.91% | 99.74% | 3.88s | 64.6s | 23 tps | 1.0M | $3.00 / $15.00 |
Modalmodal/mxfp4mxfp4 | Healthy | 99.75% | 99.42% | 2.29s | 26.9s | 52 tps | 1.0M | $3.00 / $15.00 |
Morphmorph/fp4fp4 | Down | 99.14% | 78.62% | 8.12s | 106s | 12 tps | 1.0M | $2.80 / $14.00 |
DigitalOceandigitalocean | Healthy | 98.20% | 98.39% | 2.55s | 108s | 13 tps | 1.0M | $2.85 / $14.25 |
Togethertogether | Healthy | 97.88% | 98.93% | 3.78s | 61.4s | 33 tps | 1.0M | $3.00 / $15.00 |
Sail Researchsail-research/fp4fp4 | Healthy | 97.46% | 98.26% | 5.83s | 85.7s | 22 tps | 975K | $2.60 / $13.00 |
Fireworksfireworks | Healthy | 96.52% | 98.80% | 3.24s | 76.0s | 35 tps | 1.0M | $3.00 / $15.00 |
DeepInfradeepinfra/bf16bf16 | Degraded | 95.87% | 94.98% | 1.64s | 95.3s | 16 tps | 1.0M | $2.85 / $14.25 |
Phalaphala | Down | 95.16% | 94.25% | 3.44s | 33.4s | 36 tps | 1.0M | $3.00 / $15.00 |
BaseTenbaseten/fp8fp8 | No data | — | 93.24% | 1.80s | 64.0s | 35 tps | 1.0M | $3.00 / $15.00 |
Chuteschutes/mxfp4mxfp4 | Down | — | 96.85% | 2.55s | 27.6s | 8.0 tps | 1.0M | $3.00 / $15.00 |
- Morph100%Down24h 68.56%
- p50
- 14.3s
- p99
- 117s
- Throughput
- 9.0 tps
- Context
- 1.0M
- $/Mtok
- $6.00 / $22.50
morph/fastfp4 - Wafer100%Degraded24h 95.15%
- p50
- 51.6s
- p99
- 256s
- Throughput
- 4.0 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00
wafer - Moonshot AI99.91%Healthy24h 99.74%
- p50
- 3.88s
- p99
- 64.6s
- Throughput
- 23 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00
moonshotai/mxfp4mxfp4 - Modal99.75%Healthy24h 99.42%
- p50
- 2.29s
- p99
- 26.9s
- Throughput
- 52 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00
modal/mxfp4mxfp4 - Morph99.14%Down24h 78.62%
- p50
- 8.12s
- p99
- 106s
- Throughput
- 12 tps
- Context
- 1.0M
- $/Mtok
- $2.80 / $14.00
morph/fp4fp4 - DigitalOcean98.20%Healthy24h 98.39%
- p50
- 2.55s
- p99
- 108s
- Throughput
- 13 tps
- Context
- 1.0M
- $/Mtok
- $2.85 / $14.25
digitalocean - Together97.88%Healthy24h 98.93%
- p50
- 3.78s
- p99
- 61.4s
- Throughput
- 33 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00
together - Sail Research97.46%Healthy24h 98.26%
- p50
- 5.83s
- p99
- 85.7s
- Throughput
- 22 tps
- Context
- 975K
- $/Mtok
- $2.60 / $13.00
sail-research/fp4fp4 - Fireworks96.52%Healthy24h 98.80%
- p50
- 3.24s
- p99
- 76.0s
- Throughput
- 35 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00
fireworks - DeepInfra95.87%Degraded24h 94.98%
- p50
- 1.64s
- p99
- 95.3s
- Throughput
- 16 tps
- Context
- 1.0M
- $/Mtok
- $2.85 / $14.25
deepinfra/bf16bf16 - Phala95.16%Down24h 94.25%
- p50
- 3.44s
- p99
- 33.4s
- Throughput
- 36 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00
phala - BaseTen—No data24h 93.24%
- p50
- 1.80s
- p99
- 64.0s
- Throughput
- 35 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00
baseten/fp8fp8 - Chutes—Down24h 96.85%
- p50
- 2.55s
- p99
- 27.6s
- Throughput
- 8.0 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00
chutes/mxfp4mxfp4
Measured 1m 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.