Alibaba
100.00%Context1M
Max output384K
p50 latency2,267 ms
Throughput111.0 t/s
Input price$0.22
Output price$0.66
Zero retentionNo trainingCaching
Model directory
Baseer model profileLanguage model
deepseek/deepseek-v4-flash-0731
DeepSeek V4 Flash 0731
A technical profile of this model's capabilities, pricing, and available inference providers.
Input / 1M tokens$0.065
Output / 1M tokens$0.153
Maximum context1M
Inference providers17
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.
Baseten
99.85%Context1M
Max output384K
p50 latency1,150 ms
Throughput184.0 t/s
Input price$0.13
Output price$0.26
Zero retentionNo trainingCaching
Blackbox
82.95%Context1M
Max output384K
p50 latency1,801 ms
Throughput71.0 t/s
Input price$0.076
Output price$0.153
Caching
Deepinfra
99.99%Context1M
Max output1M
p50 latency761 ms
Throughput73.5 t/s
Input price$0.08
Output price$0.18
Zero retentionNo trainingCaching
Digitalocean
99.91%Context1M
Max output1M
p50 latency403 ms
Throughput46.5 t/s
Input price$0.08
Output price$0.252
Zero retentionNo trainingCaching
Fireworks
100.00%Context1M
Max output384K
p50 latency1,666 ms
Throughput129.0 t/s
Input price$0.22
Output price$0.66
Zero retentionNo trainingCaching
Gmicloud
98.74%Context1M
Max output384K
p50 latency1,459 ms
Throughput106.0 t/s
Input price$0.352
Output price$1.06
Caching
Inceptron
99.94%Context1M
Max output1M
p50 latency747 ms
Throughput72.0 t/s
Input price$0.13
Output price$0.28
No trainingCaching
Morph
100.00%Context1M
Max output1M
p50 latency1,513 ms
Throughput4.5 t/s
Input price$0.079
Output price$0.278
Zero retentionNo trainingCaching
Novita
100.00%Context1M
Max output393.2K
p50 latency3,729 ms
Throughput192.0 t/s
Input price$0.44
Output price$1.32
No trainingCaching
Parasail
100.00%Context1M
Max output1M
p50 latency658 ms
Throughput75.0 t/s
Input price$0.14
Output price$0.28
Zero retentionNo trainingCaching
Particle
100.00%Context1M
Max output384K
p50 latency365 ms
Throughput—
Input price$0.14
Output price$0.28
Zero retentionNo trainingCaching
Relace
100.00%Context1M
Max output1M
p50 latency2,446 ms
Throughput41.5 t/s
Input price$0.065
Output price$0.18
Caching
Runware
99.97%Context1M
Max output384K
p50 latency2,334 ms
Throughput399.5 t/s
Input price$0.076
Output price$0.153
Caching
Streamlake
100.00%Context1M
Max output384K
p50 latency1,565 ms
Throughput61.0 t/s
Input price$0.44
Output price$1.32
Caching
Togetherai
99.78%Context1M
Max output1M
p50 latency660 ms
Throughput71.0 t/s
Input price$0.14
Output price$0.28
Zero retentionNo trainingCaching
Wafer
99.98%Context1M
Max output1M
p50 latency1,751 ms
Throughput274.0 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 | 2,267 ms | 111.0 t/s | 99.997% | $0.22 | $0.66 | |
Baseten | 1M | 384K | 1,150 ms | 184.0 t/s | 99.846% | $0.13 | $0.26 | |
Blackbox | 1M | 384K | 1,801 ms | 71.0 t/s | 82.955% | $0.076 | $0.153 | |
Deepinfra | 1M | 1M | 761 ms | 73.5 t/s | 99.991% | $0.08 | $0.18 | |
Digitalocean | 1M | 1M | 403 ms | 46.5 t/s | 99.909% | $0.08 | $0.252 | |
Fireworks | 1M | 384K | 1,666 ms | 129.0 t/s | 99.999% | $0.22 | $0.66 | |
Gmicloud | 1M | 384K | 1,459 ms | 106.0 t/s | 98.740% | $0.352 | $1.06 | |
Inceptron | 1M | 1M | 747 ms | 72.0 t/s | 99.935% | $0.13 | $0.28 | |
Morph | 1M | 1M | 1,513 ms | 4.5 t/s | 100.000% | $0.079 | $0.278 | |
Novita | 1M | 393.2K | 3,729 ms | 192.0 t/s | 99.998% | $0.44 | $1.32 | |
Parasail | 1M | 1M | 658 ms | 75.0 t/s | 99.998% | $0.14 | $0.28 | |
Particle | 1M | 384K | 365 ms | — | 99.997% | $0.14 | $0.28 | |
Relace | 1M | 1M | 2,446 ms | 41.5 t/s | 99.996% | $0.065 | $0.18 | |
Runware | 1M | 384K | 2,334 ms | 399.5 t/s | 99.972% | $0.076 | $0.153 | |
Streamlake | 1M | 384K | 1,565 ms | 61.0 t/s | 100.000% | $0.44 | $1.32 | |
Togetherai | 1M | 1M | 660 ms | 71.0 t/s | 99.782% | $0.14 | $0.28 | |
Wafer | 1M | 1M | 1,751 ms | 274.0 t/s | 99.981% | $0.28 | $0.56 |
What can this model do?
Available modalities and capabilities across inference providers.
TextAdvanced reasoningTool useAutomatic cachingTools
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-flash-0731Model profile updated: Sep 12, 2026, 1:46 PM
Related models
More options from the same creator or model category.