Seminal AI
§1

DeepSeek-V4-Flash-Vision-Exp

The only DeepSeek model that takes images — use it for screenshot-driven and chart/document-reading agents at identical Flash pricing; it is explicitly experimental and drops FIM completion, so keep text-only traffic on deepseek-v4-flash.

Data checked 2026-09-06

DeepSeek preview open weights deepseek-v4-flash-vision-exp

Context window
1M tokens in
Max output
384K tokens out
Input
$0.44 per 1M tokens
Output
$1.32 per 1M tokens
Cached input
$0.01 per 1M tokens
Blended
$0.66 3:1 in:out
Released
2026-08-21
Parameters
305B total MoE (V4-Flash architecture plus vision modules, continued-trained)
Licence
MIT

A What it is for

Images bill as input tokens (up to 384 tokens each), accepted as base64, public URL (max 32 MiB), or Files API file_id (max 64 MiB, upload is free).

At a three-to-one input-to-output ratio, DeepSeek-V4-Flash-Vision-Exp costs $0.66 per million tokens blended. A workload of one million input and 330,000 output tokens per day would run about $26.27 per month at list price, before caching or batch discounts.

B Capabilities

tools vision reasoning prompt-caching streaming structured-output
Input modalitiestext, image
Output modalitiestext

C Others from DeepSeek

Model Context Max out In $/M Out $/M Blended Status
DeepSeek-V4-Flash deepseek-v4-flash 1M 384K $0.44 $1.32 $0.66 ga open
DeepSeek-V4-Pro deepseek-v4-pro 1M 384K $1.32 $3.96 $1.98 ga open

D Verify before you commit

Model pricing changes without notice and this page is a snapshot. Confirm against the vendor's own page before you build a budget on it.

Source: api-docs.deepseek.com · checked 2026-09-06 · DeepSeek pricing · API docs