Alibaba
99.99%Context1M
Max output384K
p50 latency3,502 ms
Throughput110.0 t/s
Input price$0.22
Output price$0.66
Zero retentionNo trainingCaching
Model directory
Baseer model profileLanguage model
deepseek/deepseek-v4-flash
DeepSeek V4 Flash
A technical profile of this model's capabilities, pricing, and available inference providers.
Input / 1M tokens$0.08
Output / 1M tokens$0.18
Maximum context1M
Inference providers9
Price comparison
USD per one million tokens, using current provider data.
Provider latency
Last-hour p50 in milliseconds; lower is better.
Provider uptime
Reported availability over the last 24 hours; not a contractual SLA.
Inference providers
Compare current pricing, performance, and privacy across every available provider.
Azure
99.99%Context1M
Max output128K
p50 latency7,681 ms
Throughput148.0 t/s
Input price$0.19
Output price$0.51
Zero retentionNo trainingCaching
Baseten
99.86%Context1M
Max output384K
p50 latency1,124 ms
Throughput212.5 t/s
Input price$0.13
Output price$0.26
Zero retentionNo trainingCaching
Deepinfra
99.99%Context1M
Max output1M
p50 latency1,021 ms
Throughput69.0 t/s
Input price$0.08
Output price$0.18
Zero retentionNo trainingCaching
Digitalocean
99.99%Context262.1K
Max output52.5K
p50 latency483 ms
Throughput104.5 t/s
Input price$0.112
Output price$0.224
Zero retentionNo trainingCaching
Fireworks
100.00%Context1M
Max output384K
p50 latency667 ms
Throughput125.0 t/s
Input price$0.22
Output price$0.66
Zero retentionNo trainingCaching
Gmicloud
95.57%Context1M
Max output384K
p50 latency1,369 ms
Throughput—
Input price$0.352
Output price$1.06
Caching
Novita
100.00%Context1M
Max output393.2K
p50 latency2,423 ms
Throughput227.0 t/s
Input price$0.44
Output price$1.32
No trainingCaching
Wafer
100.00%Context1M
Max output1M
p50 latency480 ms
Throughput315.0 t/s
Input price$0.28
Output price$0.56
Zero retentionNo trainingCaching
| Provider | Maximum context | Max output | p50 latency | p50 throughput | 24h uptime | Input / 1M tokens | Output / 1M tokens | Privacy |
|---|---|---|---|---|---|---|---|---|
Alibaba | 1M | 384K | 3,502 ms | 110.0 t/s | 99.995% | $0.22 | $0.66 | |
Azure | 1M | 128K | 7,681 ms | 148.0 t/s | 99.992% | $0.19 | $0.51 | |
Baseten | 1M | 384K | 1,124 ms | 212.5 t/s | 99.857% | $0.13 | $0.26 | |
Deepinfra | 1M | 1M | 1,021 ms | 69.0 t/s | 99.987% | $0.08 | $0.18 | |
Digitalocean | 262.1K | 52.5K | 483 ms | 104.5 t/s | 99.994% | $0.112 | $0.224 | |
Fireworks | 1M | 384K | 667 ms | 125.0 t/s | 99.997% | $0.22 | $0.66 | |
Gmicloud | 1M | 384K | 1,369 ms | — | 95.566% | $0.352 | $1.06 | |
Novita | 1M | 393.2K | 2,423 ms | 227.0 t/s | 100.000% | $0.44 | $1.32 | |
Wafer | 1M | 1M | 480 ms | 315.0 t/s | 100.000% | $0.28 | $0.56 |
What can this model do?
Available modalities and capabilities across inference providers.
TextAdvanced reasoningTool useAutomatic cachingTools
Reasoning options
HighXhigh
Technical profile
- Model type
- Language model
- Release date
- Apr 23, 2026
- Knowledge cutoff
- 2025-05
- Regions
- US
- API specifications
- V2, V3, V4
- Temperature control
- Supported
Model identifier
deepseek/deepseek-v4-flashModel profile updated: Sep 12, 2026, 1:46 PM
Related models
More options from the same creator or model category.