DeepSeek-V4-OSL¶
Tier 1: 6.5 points · 1,000 tokens (500 input + 500 output)
Comparison method and assumptions.
Pricing¶
Website Pricing¶
| Type | Cost |
|---|---|
| Input Text | 4 points/1k tokens |
| Output (Text) | $0.27/1M tokens · 9 points/1k tokens |
All parsed rates (both currencies):
| Service | Currency | Amount | Per |
|---|---|---|---|
| Input (text) | USD | 0.12 | 1000000 tokens |
| Input (text) | POINTS | 4 | 1000 tokens |
| Output (text) | USD | 0.27 | 1000000 tokens |
| Output (text) | POINTS | 9 | 1000 tokens |
Last Checked: 2026-10-22 13:00:51.562636
Bot Information¶
Creator: @OpenSourceLab
Description: Based on DeepSeek-V4-Flash an MIT-licensed open-weights model. This multimodal bot can process PDF, PNG, JPG, HEIC, TXT, HTML, DOCX, XLSX, CSS and PY files. This bot can't process RTF, WEBM, MP4 and MP3. Maximum file size is 50 MB. Users can adjust the temperature and verbosity of the responses in the settings. Context window: 1M tokens
Previous version: https://poe.com/DeepSeek-v3.2-OSL
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-OSL
Object Type: bot
Created: Unknown
Owned By: OpenSourceLab
Root: DeepSeek-V4-OSL
API Last Updated: Not listed in API