AGENTKERNEL
- Home
- All models
- DeepSeek V3 0324
DeepSeek V3 0324: price, performance and context
Open DeepSeek V3 0324 by DeepSeek costs $0.29 per 1M input and $1.14 per 1M output tokens, handles up to 163.8K tokens in one request (≈ 490 pages of text) and scores 9.7 points on the AgentKernel performance index, rank 156 of 212.
Privacy: zero data retention with one provider, not in the EU. Availability over the last 24 h: 99.9%.
Open in the interactive comparisonKey facts
- Licence
- Open weights: free to download and self-host
- Input / 1M tokens
- $0.29
- Output / 1M tokens
- $1.14
- Context window
- 163.8K tokens
- Max. output
- 115.2K tokens
- Performance index
- 9.7 points · rank 156 of 212
- Coding index
- 21.2 points · rank 96 of 119
- Agentic index
- 0.8 points · rank 86 of 91
- Cost at your usage
- $0.575 / month
- Knowledge cutoff
- Jul 2024
- In the catalog since
- Mar 24, 2025
- Capabilities
- Tool Calling
What do you get for $10.00?
Rules of thumb from the cost calculator, base rates without caching or taxes.
| Task | Cost per task | For $10.00 |
|---|---|---|
| Chat repliesA question with a short history, a detailed answer | $0.001 | 15,000 |
| Email draftsBullet points in, a finished email out | $0.001 | 19,000 |
| Document summariesRead 10 pages, write a one-page summary | $0.002 | 6,500 |
| Code reviewsReview and comment on 500 lines of code | $0.003 | 3,700 |
| Book analysesAnalyse a 300-page book in one go | $0.031 | 320 |
Cheaper with similar performance
| Model | Licence | Performance | Your cost / month |
|---|---|---|---|
| Ling 3.1 FlashinclusionAI | Proprietary | 41.1 | $0.00 |
| Ling 3.0 Flash VLinclusionAI | Open | 24.6 | $0.036 |
| Ling 3.0 FlashinclusionAI | Open | 20.1 | $0.037 |
Stronger models
| Model | Licence | Performance | Your cost / month |
|---|---|---|---|
| Qwen3 VL 235B A22B InstructQwen | Open | 9.9 | $0.685 |
| gpt-oss-20bOpenAI | Open | 10 | $0.041 |
| Llama 4 MaverickMeta | Open | 10 | $0.351 |