DeepSeek V4.1 Flash 1017: 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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
BaseTenbaseten | Healthy | 100%◆ (best) | 100% | 100%◆ (best) | 100%◆ (best) | 285ms◆ (best) | 18.9s | 304 tps◆ (best) | 1.0M | $0.300 / $1.20 |
Cloudflarecloudflare | Healthy | 100%◆ (best) | 98.57% | 100%◆ (best) | 100%◆ (best) | 2.10s | 26.6s | 87 tps | 1.0M | $0.100 / $0.600 |
| Healthy | 100%◆ (best) | 98.58% | 100%◆ (best) | 100%◆ (best) | 698ms | 5.12s | 84 tps | 1.0M | $0.098 / $0.294 | |
| Healthy | 100%◆ (best) | 95.49% | 100%◆ (best) | 100%◆ (best) | 3.19s | 12.5s | 73 tps | 1.0M | $0.078 / $0.235 | |
| Healthy | 100%◆ (best) | 98.11% | 100%◆ (best) | 100%◆ (best) | 987ms | 7.34s | 106 tps | 1.0M | $0.147 / $0.441 | |
DeepSeekdeepseek | Healthy | 100%◆ (best) | 100% | 100%◆ (best) | 100%◆ (best) | 1.01s | 3.28s◆ (best) | 51 tps | 1.0M | $0.150 / $0.600 |
Fireworksfireworks | Healthy | 100%◆ (best) | 100% | 100%◆ (best) | 100%◆ (best) | 646ms | 11.3s | 145 tps | 1.0M | $0.300 / $1.20 |
| Healthy | 100%◆ (best) | 100% | 100%◆ (best) | 100%◆ (best) | 427ms | 4.80s | 151 tps | 262K | $0.080 / $0.500 | |
| Healthy | 100%◆ (best) | 100% | 100%◆ (best) | 100%◆ (best) | 983ms | 21.8s | 132 tps | 1.0M | $0.300 / $1.20 | |
PrimeIntellectprimeintellect | Healthy | 100%◆ (best) | 99.46% | 99.39% | 99.39% | 1.41s | 19.6s | 115 tps | 1.0M | $0.300 / $1.20 |
Relacerelace | Healthy | 100%◆ (best) | 100% | 100%◆ (best) | 100%◆ (best) | 1.04s | 6.05s | 129 tps | 1.0M | $0.050 / $0.600◆ (best) |
| No data | — | — | 100%◆ (best) | 100%◆ (best) | — | — | — | 1.0M | $0.081 / $0.550 |
- BaseTen100%◆ (best)Healthy24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 285ms◆ (best)
- p99
- 18.9s
- Throughput
- 304 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $0.300 / $1.20
baseten - Cloudflare100%◆ (best)Healthy24h 98.57%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 2.10s
- p99
- 26.6s
- Throughput
- 87 tps
- Context
- 1.0M
- $/Mtok
- $0.100 / $0.600
cloudflare - DeepInfra100%◆ (best)Healthy24h 98.58%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 698ms
- p99
- 5.12s
- Throughput
- 84 tps
- Context
- 1.0M
- $/Mtok
- $0.098 / $0.294
deepinfra/fp8fp8 - DeepInfra100%◆ (best)Healthy24h 95.49%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 3.19s
- p99
- 12.5s
- Throughput
- 73 tps
- Context
- 1.0M
- $/Mtok
- $0.078 / $0.235
deepinfra/fp8/flexfp8 - DeepInfra100%◆ (best)Healthy24h 98.11%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 987ms
- p99
- 7.34s
- Throughput
- 106 tps
- Context
- 1.0M
- $/Mtok
- $0.147 / $0.441
deepinfra/fp8/priorityfp8 - DeepSeek100%◆ (best)Healthy24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 1.01s
- p99
- 3.28s◆ (best)
- Throughput
- 51 tps
- Context
- 1.0M
- $/Mtok
- $0.150 / $0.600
deepseek - Fireworks100%◆ (best)Healthy24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 646ms
- p99
- 11.3s
- Throughput
- 145 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $1.20
fireworks - InferenceNet100%◆ (best)Healthy24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 427ms
- p99
- 4.80s
- Throughput
- 151 tps
- Context
- 262K
- $/Mtok
- $0.080 / $0.500
inference-net/fp8fp8 - Parasail100%◆ (best)Healthy24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 983ms
- p99
- 21.8s
- Throughput
- 132 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $1.20
parasail/fp8fp8 - PrimeIntellect100%◆ (best)Healthy24h 99.46%
- 7d
- 99.39%
- 30d
- 99.39%
- p50
- 1.41s
- p99
- 19.6s
- Throughput
- 115 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $1.20
primeintellect - Relace100%◆ (best)Healthy24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 1.04s
- p99
- 6.05s
- Throughput
- 129 tps
- Context
- 1.0M
- $/Mtok
- $0.050 / $0.600◆ (best)
relace - No data24h —
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.081 / $0.550
morph/fp8fp8
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.