DeepSeek: V3 0324
DeepSeek chat model for instruction following, coding, and analysis
Price changes
Cheapest list input/output only. Rates move rarely, so this is an event log. Down means cheaper. Showing the 8 latest changes.
- ↑ higherOutput $1 → $1.14
- ↑ higherInput $0.25 → $0.29
- ↓ lowerOutput $1.14 → $1
- ↓ lowerInput $0.29 → $0.25
- ↑ higherOutput $1 → $1.14
- ↑ higherInput $0.25 → $0.29
- ↑ higherOutput $0.28 → $1
- ↑ higherInput $0.14 → $0.25
Sources
Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| models.devcheapestdeepseek/deepseek-chat-v3-0324 | Kilo Gateway | $0.29 | $1.14 | $0.11 | 128K |
| OpenRouterdeepseek/deepseek-chat-v3-0324 | OpenRouter | $0.29 | $1.14 | $0.11 | 164K |
| models.devdeepseek/deepseek-chat-v3-0324 | AI/ML API | $0.3068 | $1.21 | $0.1481 | 128K |
Capabilities
- Tool calling
- Structured output
- Open weights
- In: text
- Out: text
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Hover or tap the i next to any score for its source. Full boards on /benchmarks.
- AA intelligence9.7i
- AA coding21.2i
- AA agentic0.8i
Arena rows are community-vote Elo from Arena AI, Artificial Analysis indices arrive via OpenRouter, and launch-eval figures are collected from vendor announcements, analyst writeups, and community benchmarks. Full boards and credits on /benchmarks.
See what this model costs you
The app reads the sessions your tools already wrote and prices this model's tokens at the published API rate. Free on your computer.