DeepSeek V4 Flash 0731

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.

Compare

Context window: 1M
Input: Text
Output: Text
Released: 2026-07-31

Max output: 66K
Knowledge cutoff: 2025-05
Model parameters: 304B
Active parameters: 13B
Weights: Open
License: mit
Capabilities: Open weight, Reasoning, Structured, Temperature, Tool call

Pricing

No official pricing available.

Estimate usage cost

Compare verified public prices for this exact model and region. Enter uncached input and cache usage separately. Estimates exclude unspecified fees, credits and currency conversion. Set requests to zero to estimate token charges only.

Input tokens

Output tokens

Cache read tokens

Cache write tokens

Requests

Context tokens (optional)

Currency

Batch processing

Performance

Overall capability

52.5/100

Coding: 48.1
Reasoning: 52.1
Professional work: 58.8
Knowledge & language: 49.8


SimpleQA Verified	Knowledge & language	Epoch AI	2026-11-05
Code Migration	Coding	Vals AI	2026-11-05
AA-LCRDeepSeek V4 Flash 0731 (Max)	Knowledge & language	Artificial Analysis	2026-11-05
AA-Briefcase	Professional work	Artificial Analysis	2026-11-05
Humanity’s Last ExamDeepSeek V4 Flash 0731 (Max)	Reasoning	Artificial Analysis	2026-11-05
CritPtDeepSeek V4 Flash 0731 (Max)	Reasoning	Artificial Analysis	2026-11-05
BullshitBench v2	Knowledge & language	BullshitBench	2026-11-05
Terminal-Bench 4.0 (Vals rerun)	Coding	Vals AI	2026-11-05

Providers

							Cache write
OpenRouter	deepseek/deepseek-v4-flash-0731	Openai chat	global				-

ModelRegistry · Catalog updated 2026-11-05