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 #173 of 348 models in the default AI Benchmark Hub order (quality first, then cost). At $0.72 blended per million tokens, it is cheaper than 60% of models with published API pricing. Its 163,840-token context window is 1.6× smaller than the catalog median (262,144 tokens).
Context
Max output: 147456
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 Pro 0423$1.43 / 1M · Q 86.5
- DeepSeek V4 Pro 0813$2.10 / 1M · Q 86.5
- DeepSeek V4 Flash 0731$0.12 / 1M · Q 86.3
- DeepSeek V4 Flash 0423$0.13 / 1M · Q 86.3
- DeepSeek V3.2$0.33 / 1M
Closest API price
- GPT-5.4 Nano$0.72 / 1M
- Muse Glimmer 30B$0.70 / 1M
- GPT-5.6 Luna Pro$0.70 / 1M
- GPT-5.6 Luna$0.70 / 1M
- Llama 3.3 Euryale 70B$0.70 / 1M