DeepSeek V4 Flash Latest

Compatibility alias for the current dated DeepSeek V4 Flash release. It currently routes to DeepSeek V4 Flash 0731 and inherits that release's limits and capabilities.

Reasoning
Tool Calling
Structured Output

Added Aug 2, 2026

Pricing

Auto routing · per 1M tokens

Input: $0.044
Output: $0.13
Cache read: $0.0014

Compare provider prices

Specifications

Context window: 1M
Max output: 131.1K
Parameters: 284B / 13B; Total / active

Benchmarks

Artificial Analysis

LMArena

Sourced from Artificial Analysis.

Intelligence Index

34.3

Better than 87% of models compared

Coding Index

69.1

Better than 81% of models compared

Agentic Index

41.0

Better than 81% of models compared

Agentic work

AutomationBench-AA

Workflow automation with guardrail penalties

54.0%

Better than 74% of models compared

AA-Briefcase

Agentic knowledge work (Elo)

1257 Elo

Better than 67% of models compared

GDPval-AA v2

Economically valuable tasks (Elo)

1427 Elo

Better than 78% of models compared

Document reasoning

GDP.pdf

Professional PDF reasoning: all-pass rate

11.0%

Better than 43% of models compared

AA-LCR v1.1

Long context reasoning with updated grading

79.7%

Better than 85% of models compared

MLCR-AA

Medical long-context reasoning

13.3%

Better than 43% of models compared

Reasoning

HLE

Humanity's Last Exam

38.6%

Better than 86% of models compared

CritPt

Research-level physics reasoning

16.6%

Coding

Terminal-Bench v4.0

Practical coding and terminal tasks

12.1%

Better than 64% of models compared

SciCode

Python programming for scientific computing

50.3%

Better than 55% of models compared

Knowledge

AA-Omniscience Accuracy

Proportion of correctly answered questions

40.4%

AA-Omniscience Hallucination Rate

Rate of incorrect answers among non-correct responses

91.7%

Legacy benchmarks

GPQA Diamond (legacy)

Graduate-level scientific reasoning

90.8%

Better than 91% of models compared

AA-LCR (unversioned / legacy)

Long context reasoning evaluation

79.7%

Better than 85% of models compared

GDPval-AA (unversioned / legacy)

Economically valuable tasks

46.3%

Last updated Oct 2, 2026