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 | Healthy | 100% | 69.26% | 4.05s | 52.3s | 20 tps | 1.0M | $6.00 / $22.50 |
DigitalOceandigitalocean | Healthy | 99.87% | 98.47% | 2.31s | 37.8s | 29 tps | 1.0M | $2.85 / $14.25 |
Moonshot AImoonshotai/mxfp4mxfp4 | Healthy | 99.49% | 99.74% | 4.48s | 70.2s | 23 tps | 1.0M | $3.00 / $15.00 |
Togethertogether | Healthy | 99.41% | 98.91% | 2.79s | 35.2s | 45 tps | 1.0M | $3.00 / $15.00 |
Modalmodal/mxfp4mxfp4 | Healthy | 98.68% | 99.40% | 2.56s | 34.4s | 53 tps | 1.0M | $3.00 / $15.00 |
Sail Researchsail-research/fp4fp4 | Healthy | 98.10% | 98.21% | 3.79s | 90.1s | 34 tps | 975K | $2.60 / $13.00 |
Phalaphala | Healthy | 97.54% | 94.30% | 3.16s | 18.9s | 36 tps | 1.0M | $3.00 / $15.00 |
Waferwafer | Healthy | 97.14% | 95.24% | 9.06s | 95.7s | 21 tps | 1.0M | $3.00 / $15.00 |
Fireworksfireworks | Healthy | 95.65% | 98.80% | 3.68s | 74.7s | 35 tps | 1.0M | $3.00 / $15.00 |
BaseTenbaseten/fp8fp8 | No data | — | 94.15% | 1.83s | 22.0s | 44 tps | 1.0M | $3.00 / $15.00 |
Chuteschutes/mxfp4mxfp4 | No data | — | 97.07% | 1.64s | 97.8s | 14 tps | 1.0M | $3.00 / $15.00 |
DeepInfradeepinfra/bf16bf16 | No data | — | 94.63% | 788ms | 103s | 41 tps | 1.0M | $2.85 / $14.25 |
Morphmorph/fp4fp4 | Degraded | — | 78.23% | 1.83s | 34.6s | 22 tps | 1.0M | $2.80 / $14.00 |
- Morph100%Healthy24h 69.26%
- p50
- 4.05s
- p99
- 52.3s
- Throughput
- 20 tps
- Context
- 1.0M
- $/Mtok
- $6.00 / $22.50
morph/fastfp4 - DigitalOcean99.87%Healthy24h 98.47%
- p50
- 2.31s
- p99
- 37.8s
- Throughput
- 29 tps
- Context
- 1.0M
- $/Mtok
- $2.85 / $14.25
digitalocean - Moonshot AI99.49%Healthy24h 99.74%
- p50
- 4.48s
- p99
- 70.2s
- Throughput
- 23 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00
moonshotai/mxfp4mxfp4 - Together99.41%Healthy24h 98.91%
- p50
- 2.79s
- p99
- 35.2s
- Throughput
- 45 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00
together - Modal98.68%Healthy24h 99.40%
- p50
- 2.56s
- p99
- 34.4s
- Throughput
- 53 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00
modal/mxfp4mxfp4 - Sail Research98.10%Healthy24h 98.21%
- p50
- 3.79s
- p99
- 90.1s
- Throughput
- 34 tps
- Context
- 975K
- $/Mtok
- $2.60 / $13.00
sail-research/fp4fp4 - Phala97.54%Healthy24h 94.30%
- p50
- 3.16s
- p99
- 18.9s
- Throughput
- 36 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00
phala - Wafer97.14%Healthy24h 95.24%
- p50
- 9.06s
- p99
- 95.7s
- Throughput
- 21 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00
wafer - Fireworks95.65%Healthy24h 98.80%
- p50
- 3.68s
- p99
- 74.7s
- Throughput
- 35 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00
fireworks - BaseTen—No data24h 94.15%
- p50
- 1.83s
- p99
- 22.0s
- Throughput
- 44 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00
baseten/fp8fp8 - Chutes—No data24h 97.07%
- p50
- 1.64s
- p99
- 97.8s
- Throughput
- 14 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00
chutes/mxfp4mxfp4 - DeepInfra—No data24h 94.63%
- p50
- 788ms
- p99
- 103s
- Throughput
- 41 tps
- Context
- 1.0M
- $/Mtok
- $2.85 / $14.25
deepinfra/bf16bf16 - Morph—Degraded24h 78.23%
- p50
- 1.83s
- p99
- 34.6s
- Throughput
- 22 tps
- Context
- 1.0M
- $/Mtok
- $2.80 / $14.00
morph/fp4fp4
Measured 2m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
3 endpoints reporting no data are 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, averaged over the hour.
Throughput
Median tokens per second.