DeepSeek: DeepSeek V3

Text input Text output
Author's Description

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](https://github.com/deepseek-ai/DeepSeek-V3) for more information, or see the [launch announcement](https://api-docs.deepseek.com/news/news1226).

Key Specifications
Cost
$$$
Context
163K
Released
Dec 26, 2024
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Response Format Stop Max Tokens Top P Frequency Penalty Min P Seed Temperature Presence Penalty
Features

This model supports the following features:

Response Format
Performance Summary

DeepSeek V3, released on December 26, 2024, demonstrates a strong overall performance profile, particularly excelling in reliability. The model consistently delivers usable responses, achieving a perfect 100% success rate across all 8 benchmarks, indicating exceptional stability and minimal technical failures. In terms of speed, DeepSeek V3 performs competitively, ranking in the 54th percentile, while its pricing is also competitive, sitting at the 59th percentile. Analyzing benchmark results, DeepSeek V3 exhibits perfect accuracy in both Hallucinations (100%) and Ethics (100%), showcasing its ability to appropriately acknowledge uncertainty and adhere to ethical principles. It also performs very well in General Knowledge (99.5%) and Instruction Following (71.0%, 84th percentile), indicating strong comprehension and adherence to complex directives. Its mathematical capabilities are solid at 92.0% accuracy, and it demonstrates good reasoning (80.0%) and coding (89.0%) skills. A notable strength is its perfect accuracy in hallucination testing, making it the most accurate model at its price point and speed for this specific task. While no significant weaknesses are apparent, its speed and cost, while competitive, do not consistently place it at the very top of the rankings across all individual benchmarks.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.3
Completion $0.85

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
DeepInfra
DeepInfra | deepseek/deepseek-chat-v3 163K $0.3 / 1M tokens $0.85 / 1M tokens
Novita
Novita | deepseek/deepseek-chat-v3 64K $0.3 / 1M tokens $0.85 / 1M tokens
Nebius
Nebius | deepseek/deepseek-chat-v3 163K $0.5 / 1M tokens $1.5 / 1M tokens
Fireworks
Fireworks | deepseek/deepseek-chat-v3 131K $0.3 / 1M tokens $0.85 / 1M tokens
DeepInfra
DeepInfra | deepseek/deepseek-chat-v3 163K $0.38 / 1M tokens $0.89 / 1M tokens
Targon
Targon | deepseek/deepseek-chat-v3 163K $0.3 / 1M tokens $0.85 / 1M tokens
Chutes
Chutes | deepseek/deepseek-chat-v3 163K $0.3 / 1M tokens $0.85 / 1M tokens
SiliconFlow
SiliconFlow | deepseek/deepseek-chat-v3 163K $0.3 / 1M tokens $0.85 / 1M tokens
Chutes
Chutes | deepseek/deepseek-chat-v3 163K $0.3 / 1M tokens $1.2 / 1M tokens
Novita
Novita | deepseek/deepseek-chat-v3 64K $0.4 / 1M tokens $1.3 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by deepseek