DeepSeek V4.1 Flash Thinking

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): 2.5K tokens; Longer than 96% of models

Benchmarks

Sourced from Artificial Analysis.

Intelligence Index

39.5

Better than 92% of models compared

Agentic work

GDPval-AA (unversioned / legacy)

Legacy fallback · Economically valuable tasks

55.0%

Document reasoning

AA-LCR (unversioned / legacy)

Legacy fallback · Long context reasoning evaluation

84.0%

Better than 98% of models compared

Reasoning

HLE

Humanity's Last Exam

39.2%

Better than 86% of models compared

CritPt

Research-level physics reasoning

14.3%

Coding

SciCode

Python programming for scientific computing

51.9%

Better than 62% of models compared

Knowledge

AA-Omniscience Accuracy

Proportion of correctly answered questions

46.4%

AA-Omniscience Hallucination Rate

Rate of incorrect answers among non-correct responses

96.5%

Last updated Oct 5, 2026, 4:15 PM

Artificial Analysis

Providers

Choose explicit providers for this model. Auto routing remains available as the default option.

Loading provider options…