Model prices / DeepSeek / DeepSeek V3 0324
DeepSeek V3 0324Open weights
DeepSeek · released 2025-03-24
No price from the maker itself is on record for DeepSeek V3 0324. The lowest of 10 providers is NanoGPT: $0.2 per 1M input tokens and $0.77 per 1M output tokens (as of 2026-11-12). Context window: 164K tokens, up to 164K output tokens per request.
Price by providerUSD per 1M tokens
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
NNanoGPTLowestdeepseek-v3-0324 | $0.2 | $0.77 | $0.135 | Lowest | Official docs |
| $0.2 | $0.8 | — | Official docs | ||
EEden AIdeepinfra/ | $0.24 | $0.9 | $0.135 | Official docs | |
| $0.25 | $1 | — | Official docs | ||
MMeganovadeepseek-ai/ | $0.275 | $1.1 | — | Official docs | |
| $0.27 | $1.12 | — | Official docs | ||
JJiekou.AIdeepseek/ | $0.28 | $1.14 | $0.14 | Official docs | |
| $0.298895 | $1.19558 | $0.029889 | Official docs | ||
| $0.298895 | $1.19558 | $0.029889 | Official docs | ||
| $0.24 | $0.9 | $0.135 | Deprecated | Official docs | |
| $0.5 | $1.5 | $0.25 | Deprecated | Official docs |
Providers are those listed by models.dev. This site has not vetted them one by one; each provider's own page has the binding price.
About
DeepSeek chat model for instruction following, coding, and analysis
Description from models.dev.
Specs
- Type
- Text
- Context
- 164K
- Max output
- 164K
- Input
- Text
- Output
- Text
- Reasoning
- No
- Tool calling
- Yes
- Structured output
- Yes
- Knowledge cutoff
- —
- Open weights
- Yes
- Released
- 2025-03-24
Source
Prices and specs come from models.dev (MIT licence), updated 2026-11-12. Each provider's name links to its official docs. A provider priced at 0 usually includes the model in a subscription; it is not necessarily a free API.