Model Comparison

Author
deepseek
Context Length164K

DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations reveal that the model outperforms other open-source models and rivals leading closed-source models.

For model details, please visit the DeepSeek-V3 repo for more information, or see the launch announcement.

Provider

Pricing

Input$0.38 / M tokens
Output$0.89 / M tokens
Images– –

Endpoint Features

Quantizationfp8
Max Tokens (input + output)164K
Max Output Tokens164K
Stream cancellation
Supports Tools
No Prompt Training
Reasoning– –