DeepSeek: DeepSeek V4 Flash 0731
deepseek/deepseek-v4-flash-0731
DeepSeek V4 Flash 0731 (DeepSeek) is a low-cost open-weight model priced near the bottom of the board, at $0.06/$0.12 per million input/output tokens, served by 33 independent hosts. For the money it delivers #98 of 238 on the TryAii Score — among the best score-per-dollar in its class. Its best showing is #20 on LiveCodeBench. It's reasonably quick at roughly 33-62 tokens/sec.
Prompt $/1M
$0.060
Completion $/1M
$0.120
Context
1,310,720 tok
Best provider
96 tok/s · Baidu
Specs
- Model id
- deepseek/deepseek-v4-flash-0731
- Display name
- DeepSeek: DeepSeek V4 Flash 0731
- Modality
- text->text
- Tokenizer
- DeepSeek
- Instruct type
- —
- Context length
- 1,310,720
- Max completion
- 943,718
- Prompt $/1M
- $0.060
- Completion $/1M
- $0.120
- Free tier
- no
Capabilities
- Function callingno
- JSON modeno
- System promptno
- Visionyes
- Moderatedno
Benchmark scores
Each axis is one benchmark, normalized to the best model in the field.
No benchmark data for this model.
Speed by provider
| Provider | tok/s |
|---|---|
| Baidufastest | 96 |
| CoreWeave | 93 |
| Relace | 89 |
| Novita | 86 |
| StreamLake | 82 |
| DeepSeek | 82 |
| Io Net | 70 |
| Makora | 68 |
| Reka | 63 |
| Alibaba | 61 |
| SiliconFlow | 61 |
| AtlasCloud | 56 |
| Cloudflare | 56 |
| Sail Research | 54 |
| Fireworks | 53 |
| Wafer | 50 |
| BaseTen | 45 |
| GMICloud | 45 |
| Nebius | 44 |
| Ambient | 40 |
| Together | 40 |
| Phala | 40 |
| NextBit | 38 |
| Parasail | 37 |
| Inceptron | 36 |
| Venice | 32 |
| Decart | 31 |
| Ionstream | 31 |
| Morph | 30 |
| DigitalOcean | 28 |
| Mancer 2 | 26 |
| DeepInfra | 18 |
| AkashML | 17 |
| OpenInference | 16 |
| deepseekfastest | — |