Kimi K3
moonshotai/kimi-k3
Compare with Kimi K2.6, Kimi K2.7 Code, Kimi K2.5
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
BaseTenbaseten/fp8fp8 | Healthy | 100% | 93.04% | 1.49s | 38.8s | 46 tps | 1.0M | $3.00 / $15.00 |
Moonshot AImoonshotai/mxfp4mxfp4 | Healthy | 99.94% | 99.75% | 3.92s | 45.9s | 23 tps | 1.0M | $3.00 / $15.00 |
Modalmodal/mxfp4mxfp4 | Healthy | 99.68% | 99.40% | 2.63s | 26.0s | 53 tps | 1.0M | $3.00 / $15.00 |
Fireworksfireworks | Healthy | 99.22% | 98.83% | 4.91s | 83.0s | 29 tps | 1.0M | $3.00 / $15.00 |
Togethertogether | Healthy | 98.55% | 99.01% | 2.31s | 24.0s | 51 tps | 1.0M | $3.00 / $15.00 |
Sail Researchsail-research/fp4fp4 | Healthy | 97.22% | 98.38% | 3.43s | 75.9s | 34 tps | 975K | $2.60 / $13.00 |
DigitalOceandigitalocean | Healthy | 97.21% | 98.48% | 2.14s | 45.3s | 22 tps | 1.0M | $2.85 / $14.25 |
Chuteschutes/mxfp4mxfp4 | Down | 78.63% | 96.81% | 2.28s | 19.7s | 15 tps | 1.0M | $3.00 / $15.00 |
Phalaphala | Down | 62.87% | 95.01% | 4.52s | 64.6s | 26 tps | 1.0M | $3.00 / $15.00 |
Morphmorph/fp4fp4 | Down | 20.69% | 81.73% | 3.11s | 54.0s | 11 tps | 1.0M | $2.80 / $14.00 |
Morphmorph/fastfp4 | Down | 7.45% | 72.85% | 8.24s | 55.0s | 6.5 tps | 1.0M | $6.00 / $22.50 |
DeepInfradeepinfra/bf16bf16 | No data | — | 96.33% | 1.43s | 66.5s | 15 tps | 1.0M | $2.85 / $14.25 |
Waferwafer | Degraded | — | 95.66% | 7.19s | 124s | 20 tps | 1.0M | $3.00 / $15.00 |
- BaseTen100%Healthy24h 93.04%
- p50
- 1.49s
- p99
- 38.8s
- Throughput
- 46 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00
baseten/fp8fp8 - Moonshot AI99.94%Healthy24h 99.75%
- p50
- 3.92s
- p99
- 45.9s
- Throughput
- 23 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00
moonshotai/mxfp4mxfp4 - Modal99.68%Healthy24h 99.40%
- p50
- 2.63s
- p99
- 26.0s
- Throughput
- 53 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00
modal/mxfp4mxfp4 - Fireworks99.22%Healthy24h 98.83%
- p50
- 4.91s
- p99
- 83.0s
- Throughput
- 29 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00
fireworks - Together98.55%Healthy24h 99.01%
- p50
- 2.31s
- p99
- 24.0s
- Throughput
- 51 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00
together - Sail Research97.22%Healthy24h 98.38%
- p50
- 3.43s
- p99
- 75.9s
- Throughput
- 34 tps
- Context
- 975K
- $/Mtok
- $2.60 / $13.00
sail-research/fp4fp4 - DigitalOcean97.21%Healthy24h 98.48%
- p50
- 2.14s
- p99
- 45.3s
- Throughput
- 22 tps
- Context
- 1.0M
- $/Mtok
- $2.85 / $14.25
digitalocean - Chutes78.63%Down24h 96.81%
- p50
- 2.28s
- p99
- 19.7s
- Throughput
- 15 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00
chutes/mxfp4mxfp4 - Phala62.87%Down24h 95.01%
- p50
- 4.52s
- p99
- 64.6s
- Throughput
- 26 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00
phala - Morph20.69%Down24h 81.73%
- p50
- 3.11s
- p99
- 54.0s
- Throughput
- 11 tps
- Context
- 1.0M
- $/Mtok
- $2.80 / $14.00
morph/fp4fp4 - Morph7.45%Down24h 72.85%
- p50
- 8.24s
- p99
- 55.0s
- Throughput
- 6.5 tps
- Context
- 1.0M
- $/Mtok
- $6.00 / $22.50
morph/fastfp4 - DeepInfra—No data24h 96.33%
- p50
- 1.43s
- p99
- 66.5s
- Throughput
- 15 tps
- Context
- 1.0M
- $/Mtok
- $2.85 / $14.25
deepinfra/bf16bf16 - Wafer—Degraded24h 95.66%
- p50
- 7.19s
- p99
- 124s
- Throughput
- 20 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00
wafer
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.