Context
1.0M tokens (~524 books)
Input $/1M
$0.14
Output $/1M
$0.28
Type
text
License
Proprietary
Benchmarks
0 tested
Data as of
About
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....
No benchmark data available yet.
Recently Happened
DeepSeek V4 Flash 0731 (batch) added
Aug 29, 2026
Links
Research
Documentation
Community
BenchGecko API
deepseek-v4-flash-0731-batch
Specifications
- Typetext
- Context1.0M tokens (~524 books)
- ReleasedJul 2026
- LicenseProprietary
- StatusActive
- Cost / Message~$0.001
Available On
Learn More
Share & Export
Frequently Asked Questions
DeepSeek V4 Flash 0731 (batch) is a proprietary text AI model by DeepSeek, released in July 2026. Context window: 1M tokens.
Related Models
Qwen3 Coder Next FP8 · AlibabaQwen2.5 Coder 32B Instruct AWQ · AlibabaSpeaker Diarization Community 1 · PyannoteGemma 3 12B (free) · Google DeepMindQwen3 Next 80B A3B Instruct (free) · Alibaba QwenBenchmarks
Key facts · as of 2026-09-21
- DeepSeek V4 Flash 0731 (batch) by DeepSeek. Not enough public benchmark scores to rank yet.
- List price $0.14 input · $0.28 output per 1M tokens (as of 2026-09-21).
How to cite · data as of 2026-09-21
DeepSeek V4 Flash 0731 (batch) · benchmarks, pricing and providers. BenchGecko, data as of 2026-09-21. https://benchgecko.ai/model/deepseek-v4-flash-0731-batch
Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP