DeepSeek · live price
DeepSeek V3 0324 API pricing
DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the DeepSeek V3 model and performs really well...
- Input
- $0.29
- per 1M tokens
- Output
- $1.14
- per 1M tokens
- Cached input
- $0.11
- per 1M tokens
- Context
- 164K
- 147K max output
List price from OpenRouter, which passes DeepSeek's price through without markup. Refreshed hourly. Released March 24, 2025. Model id deepseek/deepseek-chat-v3-0324.
What DeepSeek V3 0324 costs in practice
1,000 chat messages
$0.86
1,000 input + 500 output tokens each
1,000 RAG questions
$2.89
8,000 input + 500 output tokens each
100 coding-agent steps
$1.10
30,000 input + 2,000 output tokens each, no caching
DeepSeek V3 0324 price history
DeepSeek V3 0324 price by host
- SiliconFlow$0.25 in · $1 out · 164K ctx · 99.4% uptime 24h
- GMICloud$0.29 in · $1.14 out · 164K ctx · 98.5% uptime 24h
Where to buy DeepSeek credits for less
Disclosure: this site is run by the team behind smaaart, one of the options compared. Tables are ranked by price only, from live quotes and published fees, including when smaaart isn't first. How we compare
DeepSeek V3 0324 cost calculator
Cheaper alternatives to DeepSeek V3 0324
| Model | Input / 1M | Output / 1M |
|---|---|---|
| OpenAI: GPT-6 Luna Pro | $0.1 | $0.5 |
| OpenAI: GPT-6 Luna | $0.1 | $0.5 |
| Qwen: Qwen3.8 Omni Flash | $0.15 | $0.47 |
| Qwen: Qwen3.8 Flash | $0.15 | $0.47 |
| Z.ai: GLM 5.3 Flash | $0.15 | $0.5 |
| Qwen: Qwen3.7 Flash | $0.03 | $0.13 |
Other DeepSeek models
| Model | Input / 1M | Output / 1M |
|---|---|---|
| R1 | $0.7 | $2.50 |
| R1 0528 | $0.5 | $2.15 |
| DeepSeek V3 | $0.257 | $1.03 |
| DeepSeek V3.1 | $0.25 | $0.95 |
| DeepSeek V3.1 Terminus | $0.3 | $1 |
| DeepSeek V3.2 Exp | $0.27 | $0.41 |