deepseek-ai/DeepSeek-V3

Created 1/27/2025

deepseek-ai

$0.72 / M Tokens

Live

We present DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token. To achieve efficient inference and cost-effective training, DeepSeek-V3 adopts Multi-head Latent Attention (MLA) and DeepSeekMoE architectures, which were thoroughly validated in DeepSeek-V2. Furthermore, DeepSeek-V3 pioneers an auxiliary-loss-free strategy for load balancing and sets a multi-token prediction training objective for stronger performance. We pre-train DeepSeek-V3 on 14.8 trillion diverse and high-quality tokens, followed by Supervised Fine-Tuning and Reinforcement Learning stages to fully harness its capabilities. Comprehensive evaluations reveal that DeepSeek-V3 outperforms other open-source models and achieves performance comparable to leading closed-source models. Despite its excellent performance, DeepSeek-V3 requires only 2.788M H800 GPU hours for its full training. In addition, its training process is remarkably stable. Throughout the entire training process, we did not experience any irrecoverable loss spikes or perform any rollbacks.

Text Generation

Model Usage

Code Examples

Get started with code samples in your preferred language

Chat Example

Basic example of chat with the selected model

curl

1curl https://api.targon.com/v1/chat/completions \
2  -H "Content-Type: application/json" \
3  -H "Authorization: Bearer YOUR_API_KEY" \
4  -N \
5  -d '{
6    "model": "deepseek-ai/DeepSeek-V3",
7    "stream": true,
8    "messages": [
9      {"role": "system", "content": "You are a helpful programming assistant."},
10      {"role": "user", "content": "Write a bubble sort implementation in Python with comments explaining how it works"}
11    ],
12    "temperature": 0.7,
13    "max_tokens": 256,
14    "top_p": 0.1,
15    "frequency_penalty": 0,
16    "presence_penalty": 0
17  }'

Completions Example

Basic example of completions with the selected model

curl

1curl https://api.targon.com/v1/completions \
2    -H "Content-Type: application/json" \
3    -H "Authorization: Bearer YOUR_API_KEY" \
4    -N \
5    -d '{
6      "model": "deepseek-ai/DeepSeek-V3",
7      "stream": true,
8      "prompt": "The x y problem is",
9      "temperature": 0.7,
10      "max_tokens": 256,
11      "top_p": 0.1,
12      "frequency_penalty": 0,
13      "presence_penalty": 0
14    }'