← DeepSeek V4 Flash Vision Exp
DeepSeek V4 Flash Vision Exp: 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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100%◆ (best) | 99.99% | 99.88%◆ (best) | 99.40% | 3.49s | 23.3s | 85 tps | 1.0M | $0.440 / $1.32 | |
Novitanovita | Healthy | 100%◆ (best) | 99.97% | 99.00% | 99.41% | 1.50s | 4.14s | 78 tps | 1.0M | $0.440 / $1.32 |
| Healthy | 100%◆ (best) | 99.97% | 99.77% | 99.14% | 1.48s | 2.98s◆ (best) | 116 tps◆ (best) | 1.0M | $0.440 / $1.32 | |
| Healthy | 99.69% | 99.72% | 99.68% | 95.96% | 1.27s◆ (best) | 7.15s | 83 tps | 1.0M | $0.216 / $0.647◆ (best) | |
| No data | — | — | — | 93.37% | — | — | — | 1.0M | $0.440 / $1.32 | |
DeepSeekdeepseek | No data | — | — | — | 99.95%◆ (best) | — | — | — | 1.0M | $0.440 / $1.32 |
Fireworksfireworks | No data | — | — | 0.00% | 95.01% | — | — | — | 1.0M | $0.220 / $0.660 |
- GMICloud100%◆ (best)Healthy24h 99.99%
- 7d
- 99.88%◆ (best)
- 30d
- 99.40%
- p50
- 3.49s
- p99
- 23.3s
- Throughput
- 85 tps
- Context
- 1.0M
- $/Mtok
- $0.440 / $1.32
gmicloud/fp8fp8 - Novita100%◆ (best)Healthy24h 99.97%
- 7d
- 99.00%
- 30d
- 99.41%
- p50
- 1.50s
- p99
- 4.14s
- Throughput
- 78 tps
- Context
- 1.0M
- $/Mtok
- $0.440 / $1.32
novita - SiliconFlow100%◆ (best)Healthy24h 99.97%
- 7d
- 99.77%
- 30d
- 99.14%
- p50
- 1.48s
- p99
- 2.98s◆ (best)
- Throughput
- 116 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $0.440 / $1.32
siliconflow/fp8fp8 - DeepInfra99.69%Healthy24h 99.72%
- 7d
- 99.68%
- 30d
- 95.96%
- p50
- 1.27s◆ (best)
- p99
- 7.15s
- Throughput
- 83 tps
- Context
- 1.0M
- $/Mtok
- $0.216 / $0.647◆ (best)
deepinfra/fp8fp8 - No data24h —
- 7d
- —
- 30d
- 93.37%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.440 / $1.32
atlas-cloud/fp8fp8 - No data24h —
- 7d
- —
- 30d
- 99.95%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.440 / $1.32
deepseek - No data24h —
- 7d
- 0.00%
- 30d
- 95.01%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.220 / $0.660
fireworks
Measured 4m 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.