DeepSeek V4 Flash Vision (Exp) API
About
Build advanced reasoning agents with DeepSeek V4 Flash Vision (Exp), a specialized AI model optimized for complex logic and chain-of-thought tasks. This model delivers cost-effective pricing at $0.24/1M input and $0.73/1M output tokens, native tool calling support, open weights architecture. Access DeepSeek V4 Flash Vision (Exp) via the above.dev API with up to 384K output tokens.
Capabilities
Input Modalities
textimage
Output Modalities
text
Reasoning
Yes
Limits
Context Window
1.0M
Tokens
Input Limit
1.0M
Tokens
Max Output
384K
Tokens
Pricing
Standard (per 1M tokens)
Input
$0.24
Output
$0.73
Reasoning (per 1M tokens)
Output
$0.73
Caching (per 1M tokens)
Read
$0.0077
Frequently Asked Questions
DeepSeek V4 Flash Vision (Exp) by above.dev costs $0.24 per 1M input tokens and $0.73 per 1M output tokens. Cached reads cost $0.0077 per 1M tokens.
Model Details
ID
deepseek-v4-flash-vision-exp
Provider
above.devFamily
deepseek-flash
Release Date
Aug 21, 2026
Knowledge Cutoff
N/A
API Integration
NPM Package
@ai-sdk/openai-compatible
Environment Variables
ABOVE_API_KEY
API Base URL
https://api.above.dev/v1