Kimi K3: 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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Alibabaalibaba | Healthy | 100%◆ (best) | 98.99% | 99.04% | 98.94% | 1.52s | 7.63s | 49 tps | 1.0M | $3.45 / $17.25 |
| Healthy | 100%◆ (best) | 97.32% | 94.39% | 97.42% | 2.56s | 8.76s | 24 tps | 1.0M | $3.00 / $15.00 | |
| Healthy | 100%◆ (best) | 99.36% | 99.46% | 99.46% | 794ms | 12.2s | 62 tps | 1.0M | $2.85 / $14.25 | |
Fireworksfireworks | Healthy | 100%◆ (best) | 99.93% | 99.61% | 99.80%◆ (best) | 1.37s | 6.18s | 29 tps | 1.0M | $3.00 / $15.00 |
Fireworksfireworks/fast | Healthy | 100%◆ (best) | 95.14% | 98.58% | 99.03% | 699ms | 4.48s | 99 tps◆ (best) | 1.0M | $4.50 / $22.50 |
Fireworksfireworks/us | Healthy | 100%◆ (best) | 99.35% | 99.45% | 99.21% | 2.95s | 13.2s | 49 tps | 1.0M | $4.50 / $22.50 |
| Healthy | 100%◆ (best) | 98.61% | 98.87% | 99.56% | 2.08s | 34.6s | 64 tps | 1.0M | $3.00 / $15.00 | |
| Healthy | 100%◆ (best) | 99.99% | 99.55% | 99.67% | 4.57s | 23.8s | 31 tps | 1.0M | $3.00 / $15.00 | |
| Healthy | 100%◆ (best) | 99.11% | 98.28% | 98.97% | 1.35s | 6.20s | 37 tps | 1.0M | $0.375 / $12.83 | |
| Healthy | 100%◆ (best) | 99.81% | 99.77% | 99.64% | 1.69s | 8.90s | 70 tps | 1.0M | $2.80 / $14.00 | |
| Healthy | 99.86% | 99.69% | 90.45% | 96.74% | 1.20s | 13.8s | 65 tps | 1.0M | $0.365 / $13.00◆ (best) | |
| Healthy | 99.84% | 99.90% | 99.68% | 99.13% | 893ms | 6.23s | 63 tps | 1.0M | $0.790 / $14.00 | |
| Healthy | 99.74% | 98.34% | 98.59% | 97.40% | 1.01s | 11.1s | 80 tps | 1.0M | $3.00 / $15.00 | |
Togethertogether | Healthy | 99.50% | 99.26% | 99.40% | 99.34% | 1.09s | 9.64s | 48 tps | 1.0M | $2.70 / $13.50 |
Makoramakora | Healthy | 99.03% | 95.85% | 97.78% | 97.06% | 1.31s | 24.1s | 52 tps | 1.0M | $1.53 / $12.75 |
| Healthy | 98.91% | 99.76% | 99.35% | 99.35% | 901ms | 4.20s | 74 tps | 250K | $3.50 / $15.00 | |
Waferwafer | Healthy | 97.11% | 99.41% | 99.79%◆ (best) | 99.55% | 957ms | 25.1s | 28 tps | 1.0M | $0.790 / $14.00 |
Phalaphala | Degraded | 93.36% | 96.49% | 98.08% | 98.84% | 4.27s | 57.8s | 22 tps | 1.0M | $1.95 / $9.75 |
Waferwafer/us | Degraded | 92.22% | 98.67% | 99.55% | 99.55% | 777ms | 29.5s | 36 tps | 1.0M | $2.80 / $14.00 |
Amazon Bedrockamazon-bedrock/us-east-2 | Down | 89.06% | 94.61% | 96.02% | 96.02% | 2.24s | 36.2s | 70 tps | 1.0M | $3.00 / $15.00 |
| No data | — | 98.52% | 99.73% | 99.73% | 650ms◆ (best) | 3.03s◆ (best) | 72 tps | 1.0M | $1.30 / $14.00 | |
| Degraded | — | 97.56% | 98.39% | 98.59% | 2.63s | 23.4s | 56 tps | 1.0M | $3.00 / $15.00 | |
| No data | — | 70.49% | 90.36% | 90.32% | 1.78s | 10.1s | 50 tps | 1.0M | $2.52 / $12.60 | |
| No data | — | — | 98.78% | 98.06% | — | — | — | 1.0M | $2.85 / $14.25 | |
DigitalOceandigitalocean | No data | — | 99.94% | 99.51% | 99.41% | 1.13s | 9.34s | 37 tps | 1.0M | $2.55 / $12.95 |
InferenceNetinference-net | No data | — | — | — | 96.45% | — | — | — | 1.0M | $2.10 / $10.95 |
Morphmorph | No data | — | — | — | 99.41% | — | — | — | 1.0M | $2.10 / $11.74 |
Morphmorph/fast | No data | — | — | — | 97.50% | — | — | — | 1.0M | $6.00 / $22.50 |
| No data | — | — | — | 98.41% | — | — | — | 1.0M | $2.50 / $14.00 |
- Alibaba100%◆ (best)Healthy24h 98.99%
- 7d
- 99.04%
- 30d
- 98.94%
- p50
- 1.52s
- p99
- 7.63s
- Throughput
- 49 tps
- Context
- 1.0M
- $/Mtok
- $3.45 / $17.25
alibaba - Chutes100%◆ (best)Healthy24h 97.32%
- 7d
- 94.39%
- 30d
- 97.42%
- p50
- 2.56s
- p99
- 8.76s
- Throughput
- 24 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00
chutes/mxfp4mxfp4 - DeepInfra100%◆ (best)Healthy24h 99.36%
- 7d
- 99.46%
- 30d
- 99.46%
- p50
- 794ms
- p99
- 12.2s
- Throughput
- 62 tps
- Context
- 1.0M
- $/Mtok
- $2.85 / $14.25
deepinfra/mxfp4mxfp4 - Fireworks100%◆ (best)Healthy24h 99.93%
- 7d
- 99.61%
- 30d
- 99.80%◆ (best)
- p50
- 1.37s
- p99
- 6.18s
- Throughput
- 29 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00
fireworks - Fireworks100%◆ (best)Healthy24h 95.14%
- 7d
- 98.58%
- 30d
- 99.03%
- p50
- 699ms
- p99
- 4.48s
- Throughput
- 99 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $4.50 / $22.50
fireworks/fast - Fireworks100%◆ (best)Healthy24h 99.35%
- 7d
- 99.45%
- 30d
- 99.21%
- p50
- 2.95s
- p99
- 13.2s
- Throughput
- 49 tps
- Context
- 1.0M
- $/Mtok
- $4.50 / $22.50
fireworks/us - Modal100%◆ (best)Healthy24h 98.61%
- 7d
- 98.87%
- 30d
- 99.56%
- p50
- 2.08s
- p99
- 34.6s
- Throughput
- 64 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00
modal/mxfp4mxfp4 - Moonshot AI100%◆ (best)Healthy24h 99.99%
- 7d
- 99.55%
- 30d
- 99.67%
- p50
- 4.57s
- p99
- 23.8s
- Throughput
- 31 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00
moonshotai/mxfp4mxfp4 - Morph100%◆ (best)Healthy24h 99.11%
- 7d
- 98.28%
- 30d
- 98.97%
- p50
- 1.35s
- p99
- 6.20s
- Throughput
- 37 tps
- Context
- 1.0M
- $/Mtok
- $0.375 / $12.83
morph/fp8fp8 - Sail Research100%◆ (best)Healthy24h 99.81%
- 7d
- 99.77%
- 30d
- 99.64%
- p50
- 1.69s
- p99
- 8.90s
- Throughput
- 70 tps
- Context
- 1.0M
- $/Mtok
- $2.80 / $14.00
sail-research/fp4fp4 - Relace99.86%Healthy24h 99.69%
- 7d
- 90.45%
- 30d
- 96.74%
- p50
- 1.20s
- p99
- 13.8s
- Throughput
- 65 tps
- Context
- 1.0M
- $/Mtok
- $0.365 / $13.00◆ (best)
relace/fp4fp4 - InferenceNet99.84%Healthy24h 99.90%
- 7d
- 99.68%
- 30d
- 99.13%
- p50
- 893ms
- p99
- 6.23s
- Throughput
- 63 tps
- Context
- 1.0M
- $/Mtok
- $0.790 / $14.00
inference-net/fp4fp4 - Parasail99.74%Healthy24h 98.34%
- 7d
- 98.59%
- 30d
- 97.40%
- p50
- 1.01s
- p99
- 11.1s
- Throughput
- 80 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00
parasail/fp4fp4 - Together99.50%Healthy24h 99.26%
- 7d
- 99.40%
- 30d
- 99.34%
- p50
- 1.09s
- p99
- 9.64s
- Throughput
- 48 tps
- Context
- 1.0M
- $/Mtok
- $2.70 / $13.50
together - Makora99.03%Healthy24h 95.85%
- 7d
- 97.78%
- 30d
- 97.06%
- p50
- 1.31s
- p99
- 24.1s
- Throughput
- 52 tps
- Context
- 1.0M
- $/Mtok
- $1.53 / $12.75
makora - InferenceNet98.91%Healthy24h 99.76%
- 7d
- 99.35%
- 30d
- 99.35%
- p50
- 901ms
- p99
- 4.20s
- Throughput
- 74 tps
- Context
- 250K
- $/Mtok
- $3.50 / $15.00
inference-net/fastfp4 - Wafer97.11%Healthy24h 99.41%
- 7d
- 99.79%◆ (best)
- 30d
- 99.55%
- p50
- 957ms
- p99
- 25.1s
- Throughput
- 28 tps
- Context
- 1.0M
- $/Mtok
- $0.790 / $14.00
wafer - Phala93.36%Degraded24h 96.49%
- 7d
- 98.08%
- 30d
- 98.84%
- p50
- 4.27s
- p99
- 57.8s
- Throughput
- 22 tps
- Context
- 1.0M
- $/Mtok
- $1.95 / $9.75
phala - Wafer92.22%Degraded24h 98.67%
- 7d
- 99.55%
- 30d
- 99.55%
- p50
- 777ms
- p99
- 29.5s
- Throughput
- 36 tps
- Context
- 1.0M
- $/Mtok
- $2.80 / $14.00
wafer/us - Amazon Bedrock89.06%Down24h 94.61%
- 7d
- 96.02%
- 30d
- 96.02%
- p50
- 2.24s
- p99
- 36.2s
- Throughput
- 70 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00
amazon-bedrock/us-east-2 - No data24h 98.52%
- 7d
- 99.73%
- 30d
- 99.73%
- p50
- 650ms◆ (best)
- p99
- 3.03s◆ (best)
- Throughput
- 72 tps
- Context
- 1.0M
- $/Mtok
- $1.30 / $14.00
akashml/fp4fp4 - Degraded24h 97.56%
- 7d
- 98.39%
- 30d
- 98.59%
- p50
- 2.63s
- p99
- 23.4s
- Throughput
- 56 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00
baseten/fp8fp8 - No data24h 70.49%
- 7d
- 90.36%
- 30d
- 90.32%
- p50
- 1.78s
- p99
- 10.1s
- Throughput
- 50 tps
- Context
- 1.0M
- $/Mtok
- $2.52 / $12.60
decart/mxfp4mxfp4 - No data24h —
- 7d
- 98.78%
- 30d
- 98.06%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $2.85 / $14.25
deepinfra/bf16bf16 - No data24h 99.94%
- 7d
- 99.51%
- 30d
- 99.41%
- p50
- 1.13s
- p99
- 9.34s
- Throughput
- 37 tps
- Context
- 1.0M
- $/Mtok
- $2.55 / $12.95
digitalocean - No data24h —
- 7d
- —
- 30d
- 96.45%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $2.10 / $10.95
inference-net - No data24h —
- 7d
- —
- 30d
- 99.41%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $2.10 / $11.74
morph - No data24h —
- 7d
- —
- 30d
- 97.50%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $6.00 / $22.50
morph/fast - No data24h —
- 7d
- —
- 30d
- 98.41%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $2.50 / $14.00
morph/fp4fp4
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, averaged over the hour.
Throughput
Median tokens per second.