DeepSeek V4.1 Flash: 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) | 100% | 99.71% | 99.14% | 718ms | 3.75s | 107 tps | 1.0M | $0.330 / $1.32 |
| Healthy | 100%◆ (best) | 100% | 99.74% | 99.77% | 711ms | 1.67s | 69 tps | 1.0M | $0.135 / $0.540 | |
| Healthy | 100%◆ (best) | 100% | 99.68% | 99.50% | 754ms | 3.68s | 115 tps | 1.0M | $0.300 / $1.20 | |
BaseTenbaseten | Healthy | 100%◆ (best) | 100% | 99.96% | 99.87% | 259ms | 4.42s | 185 tps | 1.0M | $0.300 / $1.20 |
BaseTenbaseten/us | Healthy | 100%◆ (best) | 99.80% | 99.81% | 99.82% | 418ms | 13.7s | 192 tps | 1.0M | $0.300 / $1.20 |
Coherecohere | Healthy | 100%◆ (best) | 100% | 99.88% | 99.79% | 224ms◆ (best) | 3.06s | 188 tps | 1.0M | $0.300 / $1.20 |
| Healthy | 100%◆ (best) | 100% | 98.99% | 98.63% | 481ms | 2.06s | 260 tps◆ (best) | 1.0M | $0.130 / $0.650 | |
| Healthy | 100%◆ (best) | 100% | 99.93% | 99.74% | 516ms | 2.54s | 146 tps | 1.0M | $0.290 / $1.20 | |
| Healthy | 100%◆ (best) | 99.13% | 83.92% | 95.94% | 776ms | 2.93s | 100 tps | 1.0M | $0.090 / $0.180 | |
| Healthy | 100%◆ (best) | 100% | 100%◆ (best) | 99.99% | 683ms | 4.04s | 100 tps | 1.0M | $0.140 / $0.420 | |
| Healthy | 100%◆ (best) | 100% | 99.00% | 96.11% | 2.55s | 8.39s | 79 tps | 1.0M | $0.112 / $0.336 | |
| Healthy | 100%◆ (best) | 100% | 71.43% | 73.10% | 1.18s | 4.74s | 69 tps | 1.0M | $0.210 / $0.630 | |
DigitalOceandigitalocean | Healthy | 100%◆ (best) | 100% | 100%◆ (best) | 99.88% | 643ms | 4.99s | 158 tps | 1.0M | $0.225 / $0.900 |
Fireworksfireworks | Healthy | 100%◆ (best) | 96.26% | 97.69% | 94.60% | 785ms | 5.52s | 126 tps | 1.0M | $0.300 / $1.20 |
Fireworksfireworks/spot | Healthy | 100%◆ (best) | 99.51% | 99.82% | 99.88% | 432ms | 3.47s | 173 tps | 1.0M | $0.210 / $0.840 |
Fireworksfireworks/us | Healthy | 100%◆ (best) | 100% | 100%◆ (best) | 99.37% | 328ms | 1.27s◆ (best) | 249 tps | 1.0M | $0.450 / $1.80 |
| Healthy | 100%◆ (best) | 98.90% | 96.36% | 98.84% | 2.63s | 11.0s | 68 tps | 1.0M | $0.180 / $0.720 | |
Googlegoogle-vertex/global | Healthy | 100%◆ (best) | 97.26% | 98.52% | 97.53% | 782ms | 8.61s | 102 tps | 1.0M | $0.300 / $1.20 |
| Healthy | 100%◆ (best) | 100% | 100%◆ (best) | 99.97% | 239ms | 2.12s | 120 tps | 1.0M | $0.103 / $0.600 | |
| Healthy | 100%◆ (best) | 100% | 100%◆ (best) | 99.97% | 252ms | 2.07s | 104 tps | 1.0M | $0.103 / $0.600 | |
| Healthy | 100%◆ (best) | 99.15% | 99.60% | 99.44% | 638ms | 7.37s | 112 tps | 1.0M | $0.260 / $1.17 | |
| Healthy | 100%◆ (best) | 99.84% | 98.91% | 95.37% | 621ms | 4.04s | 58 tps | 1.0M | $0.150 / $0.750 | |
Modalmodal | Healthy | 100%◆ (best) | 100% | 99.80% | 99.94% | 335ms | 1.55s | 120 tps | 1.0M | $0.300 / $1.20 |
| Healthy | 100%◆ (best) | 99.86% | 99.92% | 99.15% | 420ms | 5.77s | 74 tps | 1.0M | $0.050 / $0.192 | |
| Healthy | 100%◆ (best) | 100% | 99.02% | 99.02% | 697ms | 2.91s | 142 tps | 1.0M | $0.300 / $1.20 | |
| Healthy | 100%◆ (best) | 100% | 100%◆ (best) | 99.26% | 881ms | 4.40s | 100 tps | 1.0M | $0.195 / $0.780 | |
| Healthy | 100%◆ (best) | 99.86% | 99.91% | 98.54% | 560ms | 18.8s | 110 tps | 1.0M | $0.035 / $0.500◆ (best) | |
| Healthy | 100%◆ (best) | 100% | 100%◆ (best) | 98.85% | 296ms | 12.0s | 167 tps | 1.0M | $0.300 / $1.20 | |
Phalaphala | Healthy | 100%◆ (best) | 99.62% | 96.79% | 98.51% | 915ms | 3.52s | 57 tps | 1.0M | $0.210 / $0.840 |
PrimeIntellectprimeintellect | Healthy | 100%◆ (best) | 100% | 99.99% | 97.65% | 1.09s | 5.77s | 135 tps | 1.0M | $0.156 / $1.20 |
Rekareka | Healthy | 100%◆ (best) | 99.03% | 99.15% | 97.52% | 334ms | 4.14s | 74 tps | 1.0M | $0.105 / $0.840 |
| Healthy | 100%◆ (best) | 100% | 100%◆ (best) | 100%◆ (best) | 224ms | 3.10s | 204 tps | 1.0M | $0.300 / $0.900 | |
| Healthy | 100%◆ (best) | 99.86% | 99.95% | 99.95% | 1.53s | 45.1s | 87 tps | 1.0M | $0.035 / $0.500◆ (best) | |
| Healthy | 100%◆ (best) | 100% | 99.95% | 99.83% | 1.44s | 3.51s | 89 tps | 1.0M | $0.300 / $1.20 | |
| Healthy | 100%◆ (best) | 100% | 99.98% | 99.87% | 1.53s | 6.71s | 67 tps | 1.0M | $0.147 / $0.588 | |
Togethertogether | Healthy | 100%◆ (best) | 100% | 100%◆ (best) | 99.59% | 262ms | 4.95s | 203 tps | 1.0M | $0.300 / $1.20 |
| Healthy | 100%◆ (best) | 99.86% | 99.83% | 99.71% | 266ms | 4.05s | 139 tps | 1.0M | $0.300 / $1.20 | |
| Healthy | 100%◆ (best) | 100% | 100%◆ (best) | 99.98% | 247ms | 3.04s | 176 tps | 1.0M | $0.190 / $0.650 | |
| Healthy | 100%◆ (best) | 100% | 100%◆ (best) | 100%◆ (best) | 316ms | 3.71s | 169 tps | 1.0M | $0.045 / $0.500 | |
BaseTenbaseten/fast | No data | — | — | 31.84% | 83.80% | — | — | — | 1.0M | $0.600 / $2.40 |
| No data | — | — | — | 99.84% | — | — | — | 1.0M | $0.300 / $1.20 | |
| No data | — | — | — | 99.94% | — | — | — | 1.0M | $0.300 / $1.20 | |
| No data | — | — | — | 100%◆ (best) | — | — | — | 1.0M | $0.300 / $1.20 | |
Cloudflarecloudflare | No data | — | — | — | 99.63% | — | — | — | 1.0M | $0.100 / $0.900 |
| No data | — | — | — | — | — | — | — | 1.0M | $0.300 / $1.20 | |
DeepSeekdeepseek | No data | — | — | — | 99.24% | — | — | — | 1.0M | $0.150 / $0.600 |
DekaLLMdekallm | No data | — | — | — | 98.04% | — | — | — | 1.0M | $0.120 / $1.20 |
Fireworksfireworks/flex | No data | — | — | — | 100%◆ (best) | — | — | — | 1.0M | $0.210 / $0.840 |
InferenceNetinference-net | No data | — | — | — | 99.61% | — | — | — | 1.0M | $0.070 / $0.300 |
| No data | — | — | — | — | — | — | — | 1.0M | $0.110 / $0.410 | |
Ionstreamionstream | No data | — | — | — | 99.16% | — | — | — | 1.0M | $0.220 / $0.600 |
| No data | — | — | — | — | — | — | — | 1.0M | $0.225 / $0.900 | |
Makoramakora | No data | — | — | — | — | — | — | — | 1.0M | $0.300 / $1.20 |
| No data | — | — | 100%◆ (best) | 96.25% | — | — | — | 1.0M | $0.170 / $0.670 | |
Morphmorph | No data | — | — | — | — | — | — | — | 1.0M | $0.079 / $0.317 |
| No data | — | — | — | 99.96% | — | — | — | 1.0M | $0.210 / $0.840 | |
| No data | — | — | — | — | — | — | — | 262K | $0.290 / $1.16 | |
Relacerelace | No data | — | — | 99.98% | 99.82% | — | — | — | 1.0M | $0.070 / $0.500 |
| No data | — | — | 65.00% | 65.00% | — | — | — | 1.0M | $0.070 / $0.500 | |
| No data | — | 100% | 100%◆ (best) | 99.10% | — | — | — | 1.0M | $0.090 / $0.250 | |
| No data | — | 100% | 100%◆ (best) | 100%◆ (best) | — | — | — | 1.0M | $0.090 / $0.250 | |
StreamLakestreamlake | No data | — | — | — | — | — | — | — | 1.0M | $0.300 / $1.20 |
Waferwafer | No data | — | — | — | 99.82% | — | — | — | 1.0M | $0.100 / $0.650 |
- Alibaba100%◆ (best)Healthy24h 100%
- 7d
- 99.71%
- 30d
- 99.14%
- p50
- 718ms
- p99
- 3.75s
- Throughput
- 107 tps
- Context
- 1.0M
- $/Mtok
- $0.330 / $1.32
alibaba - AtlasCloud100%◆ (best)Healthy24h 100%
- 7d
- 99.74%
- 30d
- 99.77%
- p50
- 711ms
- p99
- 1.67s
- Throughput
- 69 tps
- Context
- 1.0M
- $/Mtok
- $0.135 / $0.540
atlas-cloud/fp8fp8 - Baidu100%◆ (best)Healthy24h 100%
- 7d
- 99.68%
- 30d
- 99.50%
- p50
- 754ms
- p99
- 3.68s
- Throughput
- 115 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $1.20
baidu/fp8fp8 - BaseTen100%◆ (best)Healthy24h 100%
- 7d
- 99.96%
- 30d
- 99.87%
- p50
- 259ms
- p99
- 4.42s
- Throughput
- 185 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $1.20
baseten - BaseTen100%◆ (best)Healthy24h 99.80%
- 7d
- 99.81%
- 30d
- 99.82%
- p50
- 418ms
- p99
- 13.7s
- Throughput
- 192 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $1.20
baseten/us - Cohere100%◆ (best)Healthy24h 100%
- 7d
- 99.88%
- 30d
- 99.79%
- p50
- 224ms◆ (best)
- p99
- 3.06s
- Throughput
- 188 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $1.20
cohere - CoreWeave100%◆ (best)Healthy24h 100%
- 7d
- 98.99%
- 30d
- 98.63%
- p50
- 481ms
- p99
- 2.06s
- Throughput
- 260 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $0.130 / $0.650
coreweave/fp8fp8 - Crusoe100%◆ (best)Healthy24h 100%
- 7d
- 99.93%
- 30d
- 99.74%
- p50
- 516ms
- p99
- 2.54s
- Throughput
- 146 tps
- Context
- 1.0M
- $/Mtok
- $0.290 / $1.20
crusoe/fp8fp8 - Decart100%◆ (best)Healthy24h 99.13%
- 7d
- 83.92%
- 30d
- 95.94%
- p50
- 776ms
- p99
- 2.93s
- Throughput
- 100 tps
- Context
- 1.0M
- $/Mtok
- $0.090 / $0.180
decart/fp4fp4 - DeepInfra100%◆ (best)Healthy24h 100%
- 7d
- 100%◆ (best)
- 30d
- 99.99%
- p50
- 683ms
- p99
- 4.04s
- Throughput
- 100 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.420
deepinfra/fp8fp8 - DeepInfra100%◆ (best)Healthy24h 100%
- 7d
- 99.00%
- 30d
- 96.11%
- p50
- 2.55s
- p99
- 8.39s
- Throughput
- 79 tps
- Context
- 1.0M
- $/Mtok
- $0.112 / $0.336
deepinfra/fp8/flexfp8 - DeepInfra100%◆ (best)Healthy24h 100%
- 7d
- 71.43%
- 30d
- 73.10%
- p50
- 1.18s
- p99
- 4.74s
- Throughput
- 69 tps
- Context
- 1.0M
- $/Mtok
- $0.210 / $0.630
deepinfra/fp8/priorityfp8 - DigitalOcean100%◆ (best)Healthy24h 100%
- 7d
- 100%◆ (best)
- 30d
- 99.88%
- p50
- 643ms
- p99
- 4.99s
- Throughput
- 158 tps
- Context
- 1.0M
- $/Mtok
- $0.225 / $0.900
digitalocean - Fireworks100%◆ (best)Healthy24h 96.26%
- 7d
- 97.69%
- 30d
- 94.60%
- p50
- 785ms
- p99
- 5.52s
- Throughput
- 126 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $1.20
fireworks - Fireworks100%◆ (best)Healthy24h 99.51%
- 7d
- 99.82%
- 30d
- 99.88%
- p50
- 432ms
- p99
- 3.47s
- Throughput
- 173 tps
- Context
- 1.0M
- $/Mtok
- $0.210 / $0.840
fireworks/spot - Fireworks100%◆ (best)Healthy24h 100%
- 7d
- 100%◆ (best)
- 30d
- 99.37%
- p50
- 328ms
- p99
- 1.27s◆ (best)
- Throughput
- 249 tps
- Context
- 1.0M
- $/Mtok
- $0.450 / $1.80
fireworks/us - GMICloud100%◆ (best)Healthy24h 98.90%
- 7d
- 96.36%
- 30d
- 98.84%
- p50
- 2.63s
- p99
- 11.0s
- Throughput
- 68 tps
- Context
- 1.0M
- $/Mtok
- $0.180 / $0.720
gmicloud/fp8fp8 - Google100%◆ (best)Healthy24h 97.26%
- 7d
- 98.52%
- 30d
- 97.53%
- p50
- 782ms
- p99
- 8.61s
- Throughput
- 102 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $1.20
google-vertex/global - InferenceNet100%◆ (best)Healthy24h 100%
- 7d
- 100%◆ (best)
- 30d
- 99.97%
- p50
- 239ms
- p99
- 2.12s
- Throughput
- 120 tps
- Context
- 1.0M
- $/Mtok
- $0.103 / $0.600
inference-net/fp8fp8 - InferenceNet100%◆ (best)Healthy24h 100%
- 7d
- 100%◆ (best)
- 30d
- 99.97%
- p50
- 252ms
- p99
- 2.07s
- Throughput
- 104 tps
- Context
- 1.0M
- $/Mtok
- $0.103 / $0.600
inference-net/usfp8 - Makora100%◆ (best)Healthy24h 99.15%
- 7d
- 99.60%
- 30d
- 99.44%
- p50
- 638ms
- p99
- 7.37s
- Throughput
- 112 tps
- Context
- 1.0M
- $/Mtok
- $0.260 / $1.17
makora/fp8fp8 - Mancer 2100%◆ (best)Healthy24h 99.84%
- 7d
- 98.91%
- 30d
- 95.37%
- p50
- 621ms
- p99
- 4.04s
- Throughput
- 58 tps
- Context
- 1.0M
- $/Mtok
- $0.150 / $0.750
mancer/fp8fp8 - Modal100%◆ (best)Healthy24h 100%
- 7d
- 99.80%
- 30d
- 99.94%
- p50
- 335ms
- p99
- 1.55s
- Throughput
- 120 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $1.20
modal - Morph100%◆ (best)Healthy24h 99.86%
- 7d
- 99.92%
- 30d
- 99.15%
- p50
- 420ms
- p99
- 5.77s
- Throughput
- 74 tps
- Context
- 1.0M
- $/Mtok
- $0.050 / $0.192
morph/fp8fp8 - Nebius100%◆ (best)Healthy24h 100%
- 7d
- 99.02%
- 30d
- 99.02%
- p50
- 697ms
- p99
- 2.91s
- Throughput
- 142 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $1.20
nebius/fp8fp8 - Novita100%◆ (best)Healthy24h 100%
- 7d
- 100%◆ (best)
- 30d
- 99.26%
- p50
- 881ms
- p99
- 4.40s
- Throughput
- 100 tps
- Context
- 1.0M
- $/Mtok
- $0.195 / $0.780
novita/fp8fp8 - OpenInference100%◆ (best)Healthy24h 99.86%
- 7d
- 99.91%
- 30d
- 98.54%
- p50
- 560ms
- p99
- 18.8s
- Throughput
- 110 tps
- Context
- 1.0M
- $/Mtok
- $0.035 / $0.500◆ (best)
open-inference/fp4fp4 - Parasail100%◆ (best)Healthy24h 100%
- 7d
- 100%◆ (best)
- 30d
- 98.85%
- p50
- 296ms
- p99
- 12.0s
- Throughput
- 167 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $1.20
parasail/fp8fp8 - Phala100%◆ (best)Healthy24h 99.62%
- 7d
- 96.79%
- 30d
- 98.51%
- p50
- 915ms
- p99
- 3.52s
- Throughput
- 57 tps
- Context
- 1.0M
- $/Mtok
- $0.210 / $0.840
phala - PrimeIntellect100%◆ (best)Healthy24h 100%
- 7d
- 99.99%
- 30d
- 97.65%
- p50
- 1.09s
- p99
- 5.77s
- Throughput
- 135 tps
- Context
- 1.0M
- $/Mtok
- $0.156 / $1.20
primeintellect - Reka100%◆ (best)Healthy24h 99.03%
- 7d
- 99.15%
- 30d
- 97.52%
- p50
- 334ms
- p99
- 4.14s
- Throughput
- 74 tps
- Context
- 1.0M
- $/Mtok
- $0.105 / $0.840
reka - Relace100%◆ (best)Healthy24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 224ms
- p99
- 3.10s
- Throughput
- 204 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $0.900
relace/fastfp4 - Relace100%◆ (best)Healthy24h 99.86%
- 7d
- 99.95%
- 30d
- 99.95%
- p50
- 1.53s
- p99
- 45.1s
- Throughput
- 87 tps
- Context
- 1.0M
- $/Mtok
- $0.035 / $0.500◆ (best)
relace/fp4fp4 - SiliconFlow100%◆ (best)Healthy24h 100%
- 7d
- 99.95%
- 30d
- 99.83%
- p50
- 1.44s
- p99
- 3.51s
- Throughput
- 89 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $1.20
siliconflow/fp8fp8 - StreamLake100%◆ (best)Healthy24h 100%
- 7d
- 99.98%
- 30d
- 99.87%
- p50
- 1.53s
- p99
- 6.71s
- Throughput
- 67 tps
- Context
- 1.0M
- $/Mtok
- $0.147 / $0.588
streamlake/fp8fp8 - Together100%◆ (best)Healthy24h 100%
- 7d
- 100%◆ (best)
- 30d
- 99.59%
- p50
- 262ms
- p99
- 4.95s
- Throughput
- 203 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $1.20
together - Venice100%◆ (best)Healthy24h 99.86%
- 7d
- 99.83%
- 30d
- 99.71%
- p50
- 266ms
- p99
- 4.05s
- Throughput
- 139 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $1.20
venice/fp8fp8 - Wafer100%◆ (best)Healthy24h 100%
- 7d
- 100%◆ (best)
- 30d
- 99.98%
- p50
- 247ms
- p99
- 3.04s
- Throughput
- 176 tps
- Context
- 1.0M
- $/Mtok
- $0.190 / $0.650
wafer/mxfp4mxfp4 - Wafer100%◆ (best)Healthy24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 316ms
- p99
- 3.71s
- Throughput
- 169 tps
- Context
- 1.0M
- $/Mtok
- $0.045 / $0.500
wafer/usmxfp4 - No data24h —
- 7d
- 31.84%
- 30d
- 83.80%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.600 / $2.40
baseten/fast - No data24h —
- 7d
- —
- 30d
- 99.84%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.300 / $1.20
baseten/fp32fp32 - No data24h —
- 7d
- —
- 30d
- 99.94%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.300 / $1.20
baseten/fp8fp8 - No data24h —
- 7d
- —
- 30d
- 100%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.300 / $1.20
baseten/fp8/usfp8 - No data24h —
- 7d
- —
- 30d
- 99.63%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.100 / $0.900
cloudflare - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.300 / $1.20
deepinfra/fp4fp4 - No data24h —
- 7d
- —
- 30d
- 99.24%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.150 / $0.600
deepseek - No data24h —
- 7d
- —
- 30d
- 98.04%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.120 / $1.20
dekallm - No data24h —
- 7d
- —
- 30d
- 100%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.210 / $0.840
fireworks/flex - No data24h —
- 7d
- —
- 30d
- 99.61%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.070 / $0.300
inference-net - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.110 / $0.410
io-net/fp8fp8 - No data24h —
- 7d
- —
- 30d
- 99.16%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.220 / $0.600
ionstream - Krea—No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.225 / $0.900
krea/fp8fp8 - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.300 / $1.20
makora - No data24h —
- 7d
- 100%◆ (best)
- 30d
- 96.25%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.170 / $0.670
modelrun/fp4fp4 - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.079 / $0.317
morph - No data24h —
- 7d
- —
- 30d
- 99.96%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.210 / $0.840
nextbit/fp8fp8 - Reka—No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.290 / $1.16
reka/fp4fp4 - No data24h —
- 7d
- 99.98%
- 30d
- 99.82%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.070 / $0.500
relace - No data24h —
- 7d
- 65.00%
- 30d
- 65.00%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.070 / $0.500
relace/mxfp4mxfp4 - No data24h 100%
- 7d
- 100%◆ (best)
- 30d
- 99.10%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.090 / $0.250
sail-research/fp4fp4 - No data24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.090 / $0.250
sail-research/fp4/usfp4 - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.300 / $1.20
streamlake - No data24h —
- 7d
- —
- 30d
- 99.82%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.100 / $0.650
wafer
Measured 3m 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.
Throughput
Median tokens per second.