DeepSeek V3 0324
DeepSeek · deepseek/deepseek-chat-v3-0324
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](/deepseek/deepseek-chat-v3) model and performs really well...
DeepSeek V3 0324 ranks #150 of 377 models in the default AI Benchmark Hub order (quality first, then cost). At $0.72 blended per million tokens, it is cheaper than 59% of models with published API pricing. Its 128,000-token context window is 2.0× smaller than the catalog median (262,144 tokens).
Context
Max output: 115200
Pricing
Output / 1M: 1.14
Blend / 1M: 0.72
Quality
Provider
Moderated: no
Monthly cost at this blended rate
Estimated API spend if every token is billed at $0.72per million (the blend of this model's input and output prices). Real bills depend on the input/output mix.
| Tokens / month | Est. cost (USD) |
|---|---|
| 1,000,000 | $0.72 |
| 10,000,000 | $7.15 |
| 100,000,000 | $71.50 |
Related models
Same lab, similar price, or similar quality — useful next comparisons.
More from DeepSeek
- DeepSeek V4 Flash 0423$0.14 / 1M
- DeepSeek V4 Flash 0731$0.18 / 1M
- DeepSeek V4.1 Flash$0.27 / 1M
- DeepSeek V3.2$0.32 / 1M
- DeepSeek V3.2 Exp$0.34 / 1M
Closest API price
- Llama 3.1 70B Instruct$0.72 / 1M
- GPT-5.4 Nano$0.72 / 1M
- GPT-5.6 Luna Pro$0.70 / 1M
- GPT-5.6 Luna$0.70 / 1M
- GLM Latest$0.73 / 1M