deepseek-v4-pro-t¶
Tier 5: 500 points ยท per message
Comparison method and assumptions.
Pricing¶
API Pricing (USD)¶
| Type | Cost |
|---|---|
| Request | $0.015/request |
Website Pricing¶
| Type | Cost |
|---|---|
| Total Cost | 500 points/message |
All parsed rates (both currencies):
| Service | Currency | Amount | Per |
|---|---|---|---|
| Total cost | USD | 0.015 | 1 message |
| Total cost | POINTS | 500 | 1 message |
Last Checked: 2026-10-22 13:41:10.442481
Bot Information¶
Creator: @togetherai
Description: DeepSeek V4 Pro is DeepSeek's 1.6T parameter (49B activated) MoE model supporting 1M token context. It introduces a hybrid attention architecture combining Compressed Sparse Attention and Heavily Compressed Attention, requiring only 27% of inference FLOPs and 10% of KV cache compared to V3.2 at million-token context. Pre-trained on 32T+ tokens with Muon optimizer and a two-stage post-training pipeline, V4 Pro delivers three configurable reasoning modes and strong performance across coding (93.5% LiveCodeBench), reasoning (90.1% GPQA Diamond), and agentic tasks (80.6% SWE-Bench Verified). MIT licensed.
Extra: Powered by a server managed by @togetherai. Learn more
Architecture¶
Input Modalities: text
Output Modalities: text
Modality: text->text
Technical Details¶
Model ID: deepseek-v4-pro-t
Object Type: model
Created: 1777056434492
Owned By: Together AI
Root: deepseek-v4-pro-t
API Last Updated: 2026-10-22 13:58:59.077064