DeepSeek V4.1 Flash

DeepSeek V4.1 Flash supports text and image input, reasoning, tool calling, and structured output with a 1M-token context window. This is a rate-limited beta with limited capacity, intended for testing rather than production use.

Reasoning
Vision
Tool Calling
Structured Output

Added Sep 8, 2026

Model weights

Pricing

Auto routing · per 1M tokens

Input: $0.090
Output: $0.30
Cache read: $0.0060

Compare provider prices

Specifications

Context window: 1M
Max output: 384K
Avg output (7d): 602 tokens; Longer than 53% of models

Benchmarks

Artificial Analysis

Design Arena

Sourced from Artificial Analysis.

Intelligence Index

24.7

Better than 77% of models compared

Agentic work

GDPval-AA (unversioned / legacy)

Legacy fallback · Economically valuable tasks

42.1%

Document reasoning

AA-LCR (unversioned / legacy)

Legacy fallback · Long context reasoning evaluation

55.3%

Better than 47% of models compared

Reasoning

HLE

Humanity's Last Exam

10.8%

Better than 52% of models compared

CritPt

Research-level physics reasoning

0.3%

Coding

SciCode

Python programming for scientific computing

35.5%

Better than 14% of models compared

Knowledge

AA-Omniscience Accuracy

Proportion of correctly answered questions

28.4%

AA-Omniscience Hallucination Rate

Rate of incorrect answers among non-correct responses

54.0%

Last updated Oct 13, 2026, 12:01 AM