deepseek-vision-exp¶
Tier 3: 29.5 points · 1,000 tokens (500 input + 500 output)
Comparison method and assumptions.
Pricing¶
API Pricing (USD)¶
| Type | Cost |
|---|---|
| Prompt | $4.444E-7/token |
| Completion | $0.0000013333/token |
Website Pricing¶
| Type | Cost |
|---|---|
| Input Text | 15 points/1k tokens |
| Output (Text) | $1.33/1M tokens · 44 points/1k tokens |
All parsed rates (both currencies):
| Service | Currency | Amount | Per |
|---|---|---|---|
| Input (text) | USD | 0.44 | 1000000 tokens |
| Input (text) | POINTS | 15 | 1000 tokens |
| Output (text) | USD | 1.33 | 1000000 tokens |
| Output (text) | POINTS | 44 | 1000 tokens |
Last Checked: 2026-10-22 13:47:07.599581
Bot Information¶
Creator: @novitaai
Description: Try https://poe.com/DeepSeek-V4.1-Flash-1017 for the first-party DeepSeek bot.
DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of DeepSeek V4 Flash 0731(opens in new tab) from DeepSeek, adding image understanding while matching the base model on text capabilities including agents, reasoning, and world knowledge. It is a sparse mixture-of-experts model with 13B active parameters out of 284B total.
It is suited for document and chart understanding, visual question answering, and multimodal agent workflows that interleave text and images.
File Support: Text, Markdown, Image and PDF files Context window: 1M tokens
Extra: Powered by a server managed by @novitaai. Learn more
Architecture¶
Input Modalities: text, image
Output Modalities: text
Modality: text,image->text
Technical Details¶
Model ID: deepseek-vision-exp
Object Type: model
Created: 1788179087945
Owned By: Novita AI
Root: deepseek-vision-exp
API Last Updated: 2026-10-22 13:58:59.077961