deepseek

DeepSeek: DeepSeek V4 Flash Vision Exp

Name: DeepSeek: DeepSeek V4 Flash Vision Exp
Creator: deepseek
Published: 2026-08-21T11:26:03.000Z

DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of DeepSeek V4 Flash 0731 from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,...

OpenRouter에서 출처 보기

개요

모델 사양

Context: 1,048,576 tokens
최대 출력: 384,000 tokens
아키텍처: text+image->text
토크나이저: DeepSeek
지식 기준일: Not provided
검토됨: 아니요

기능 및 모달리티

Input → Output

Input

textimage

Output

text

추론

예 · max · high · low

API

지원 API 매개변수

frequency_penaltyinclude_reasoninglogprobsmax_tokenspresence_penaltyreasoningreasoning_effortresponse_formatstoptemperaturetool_choicetoolstop_logprobstop_p

사용 가능한 제공업체

1 제공업체

DeepSeek

unknown

Context: 1.0M
최대 출력: 384K
Input: $0.440
Output: $1.32
캐시 읽기: $0.014
캐시 쓰기: Not provided

deepseek

models

모든 모델

deepseek

출시일 2026. 8. 12.

DeepSeek: DeepSeek V4 Pro 0813

DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.

Context: 1.0M
Input: text
Output: text

Input: $1.32Output: $3.96per 1M tokens

모델 상세 보기 →

deepseek

출시일 2026. 8. 12.

DeepSeek: DeepSeek V4 Pro 0813 (batch)

DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.

Context: 1.0M
Input: text
Output: text

Input: $1.32Output: $3.96per 1M tokens

모델 상세 보기 →

deepseek

출시일 2026. 7. 31.

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....

Context: 1.3M
Input: text
Output: text

Input: $0.065Output: $0.180per 1M tokens

모델 상세 보기 →

deepseek

출시일 2026. 7. 31.

DeepSeek: DeepSeek V4 Flash 0731 (batch)

Context: 1.0M
Input: text
Output: text

Input: $0.140Output: $0.280per 1M tokens

모델 상세 보기 →