Model Library
DeepSeekReleased March 25, 2025DeepSeek V3 0324
DeepSeek · Released March 25, 2025
Intelligence score
15
At a glance
- Intelligence
- 15
- Speed
- —
- Latency
- —
- Input price
- $1.19per 1M tokens
- Output price
- $1.25per 1M tokens
- Context window
- 130Ktokens
- Parameters
- 671billions
Summary
Comparison summary
DeepSeek V3 0324 scores 15 on the Artificial Analysis Intelligence Index, placing it below average among other open weight non-reasoning models of similar size (median: 17). DeepSeek V3 0324 costs $1.19 per 1M input tokens (at the higher end, median: $0.60) and $1.25 per 1M output tokens (better than average, median: $2.40), based on the median across providers serving the model.
Specifications
Technical specifications
| Model name | DeepSeek V3 0324 |
|---|---|
| Provider | DeepSeek |
| Release date | March 25, 2025 |
| Intelligence score | 15 |
| Speed | — |
| Latency (TTFT) | — |
| Input price | $1.19 / 1M tokens |
| Output price | $1.25 / 1M tokens |
| Context window | 130,000 tokens |
| Parameters | 671B |
| Reasoning | No |
| Input modalities | text |
| Output modalities | — |
| Open weights | Yes |
| License | MIT |
| API availability | — |
| Source | Model Intelligence legacy profile: deepseek-v3-0324 |
Pricing
Token prices
Price per 1M tokens
DeepSeek V3 0324, as listed in the catalog record
- Input$1.19
- Output$1.25
| Token type | Price per 1M |
|---|---|
| Input | $1.19 |
| Output | $1.25 |
Model Intelligence legacy profile: deepseek-v3-0324
FAQ · 19
Frequently asked questions
DeepSeek V3 0324 was released on March 25, 2025.
DeepSeek V3 0324 was created by DeepSeek.
DeepSeek V3 0324 scores 15 on the Artificial Analysis Intelligence Index, placing it below average among other open weight non-reasoning models of similar size (median: 17).
DeepSeek V3 0324 costs $1.19 per 1M input tokens (at the higher end, median: $0.60) and $1.25 per 1M output tokens (better than average, median: $2.40), based on the median across providers serving the model.
DeepSeek V3 0324 costs $1.19 per 1M input tokens and $1.25 per 1M output tokens (based on the median across providers serving the model). For a blended rate (7:2:1 cache hit/input/output ratio), this is $1.20 per 1M tokens. Pricing may vary by provider.
When evaluated on the Intelligence Index, DeepSeek V3 0324 generated 4.6M output tokens, which is very competitive compared to other open weight non-reasoning models of similar size (median: 4.8M).
No, DeepSeek V3 0324 is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
DeepSeek V3 0324 supports text input.
DeepSeek V3 0324 supports text output.
No, DeepSeek V3 0324 does not support image input. It can only process text.
No, DeepSeek V3 0324 is not multimodal. It only supports text input.
DeepSeek V3 0324 has a context window of 130k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, DeepSeek V3 0324 is open weights. The model weights are publicly available and can be downloaded for self-hosting.
DeepSeek V3 0324 has 671 billion parameters (37 billion active).
DeepSeek V3 0324 is a Mixture of Experts (MoE) model with 671 billion total parameters, but only 37 billion active parameters are used during inference.
DeepSeek V3 0324 is released under the MIT license. This license allows commercial use.
DeepSeek V3 0324 achieves a score of 15 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, DeepSeek V3 0324 is available via API through 6 providers.
DeepSeek V3 0324 is available through 6 API providers.