Capabilities and specifications
- Creator
- DeepSeek
- Model family
- Not documented
- Knowledge cutoff
- Not documented
- License
- Not documented
- Release date
- Not documented
- Model ID
deepseek/deepseek-v4-flash-0731
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.
deepseek/deepseek-v4-flash-0731Provider-specific identifiers, limits, and prices per million tokens.
The model record exists, but no source-linked provider offer is available yet.
Submit a sourceObserved serving measurements stay separate from model specifications and are never estimated from price or model size.
Generation speed; higher is faster.
Time until the first output token arrives.
Successful requests over a measured period.
Performance varies by inference provider, region, and load. Provider-level measurements appear only when a source reports them.
Raw results remain attached to their original source and version.
ModelBench does not infer quality from price, context size, or model name.
Read the methodologyDetected changes from successful source imports.
This record has not changed in the retained import history.
Fetch the complete source-linked model record without an API key.
GET https://www.modelbench.lol/api/v1/models/deepseek/deepseek-v4-flash-0731curl "https://www.modelbench.lol/api/v1/models/deepseek/deepseek-v4-flash-0731"