DeepSeek-V4-Pro-OSL¶
Tier 3: 96.5 points · 1,000 tokens (500 input + 500 output)
Comparison method and assumptions.
Pricing¶
Website Pricing¶
| Type | Cost |
|---|---|
| Input Text | 48 points/1k tokens |
| Output (Text) | $4.40/1M tokens · 145 points/1k tokens |
All parsed rates (both currencies):
| Service | Currency | Amount | Per |
|---|---|---|---|
| Input | USD | 1.46 | 1000000 tokens |
| Input | POINTS | 48 | 1000 tokens |
| Output (text) | USD | 4.40 | 1000000 tokens |
| Output (text) | POINTS | 145 | 1000 tokens |
Last Checked: 2026-10-22 13:01:07.494722
Bot Information¶
Creator: @OpenSourceLab
Description: Based on the MIT-licensed and open-weights model DeepSeek-V4-Pro and extended with file processing capabilities. This multimodal bot accepts PDF, TXT, HTML, DOCX and PY files. Previous version: https://poe.com/DeepSeek-V3.2-OSL This bot can't process HEIC, RTF files, PNG, JPG, ODS, WEBM, MP4 and MP3 audios. Maximum file size is 50 MB. Context window: 1M tokens
Extra: Powered by a server managed by @OpenSourceLab. Learn more
Architecture¶
Input Modalities: Unknown
Output Modalities: Unknown
Modality: unknown
Technical Details¶
Model ID: DeepSeek-V4-Pro-OSL
Object Type: bot
Created: Unknown
Owned By: OpenSourceLab
Root: DeepSeek-V4-Pro-OSL
API Last Updated: Not listed in API