DeepSeek
DeepSeek V3 0324
DeepSeek chat model for instruction following, coding, and analysis
Model facts
- Context window
- 164K tokens
- Maximum output
- 164K tokens
- Cheapest paid input
- $0.2 per 1M tokens
- Cheapest paid output
- $0.8 per 1M tokens
- Open weights
- yes
- Providers
- 11
Capabilities and modalities
tool calling, structured output, temperature control, open weights, text.
Local hardware estimate
At 4K context: Q4_K_M 419.9 GiB, Q8_0 738.7 GiB, F16 1336.4 GiB working memory.
- Parameters
- 684.5 billion
- Architecture
- deepseekv3
- Model license
- mit
Planning estimate adapted from the MIT-licensed whichllm estimator using metadata from Hugging Face; not a vendor minimum requirement.
Artificial Analysis benchmarks
Compare this model on the full LLM benchmark leaderboard.
| Configuration | AAI | Coding | Math | Output tokens/s |
|---|---|---|---|---|
| default | 15.2 | 21.2 | 41.0 | not measured |
Observed price history
- 2026-08-24: $0.2 input / $0.8 output per 1M tokens
API providers
- submodel — model id deepseek-ai/DeepSeek-V3-0324; $0.2 input / $0.8 output per 1M tokens; provider documentation
- Meganova — model id deepseek-ai/DeepSeek-V3-0324; $0.25 input / $0.88 output per 1M tokens; provider documentation
- Deep Infra — model id deepseek-ai/DeepSeek-V3-0324; $0.24 input / $0.9 output per 1M tokens; provider documentation
- Eden AI — model id deepinfra/deepseek-ai/DeepSeek-V3-0324; $0.24 input / $0.9 output per 1M tokens; provider documentation
- Kilo Gateway (DeepSeek) — model id deepseek/deepseek-chat-v3-0324; $0.25 input / $1 output per 1M tokens; provider documentation
- OpenRouter — model id deepseek/deepseek-chat-v3-0324; $0.25 input / $1 output per 1M tokens; provider documentation
- Hugging Face — model id deepseek-ai/DeepSeek-V3-0324; $0.27 input / $1.12 output per 1M tokens; provider documentation
- NovitaAI — model id deepseek/deepseek-v3-0324; $0.27 input / $1.12 output per 1M tokens; provider documentation
- Jiekou.AI — model id deepseek/deepseek-v3-0324; $0.28 input / $1.14 output per 1M tokens; provider documentation
- Crusoe — model id deepseek-ai/DeepSeek-V3-0324; $0.5 input / $1.5 output per 1M tokens; provider documentation
- Qiniu — model id deepseek-v3-0324; not published input / not published output per 1M tokens; provider documentation