Author's Description
DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well on a variety of tasks.
Key Specifications
Supported Parameters
This model supports the following parameters:
Features
This model supports the following features:
Performance Summary
DeepSeek V3 0324, a 685B-parameter mixture-of-experts model, demonstrates a strong overall performance profile. While its speed performance is moderate, ranking in the 38th percentile across benchmarks, it generally offers cost-effective solutions, placing in the 61st percentile for price. The model excels in several key areas. It achieves an impressive 92.0% accuracy in Coding, indicating strong programming knowledge. Its performance in Ethics is particularly noteworthy, achieving perfect 100.0% accuracy, making it the most accurate model at its price point and among models of comparable speed. DeepSeek V3 0324 also shows robust General Knowledge with 99.5% accuracy. In Reasoning, it performs well with 80.0% accuracy. Its Email Classification accuracy is solid at 97.0%. A notable strength is its high accuracy across complex tasks like coding, reasoning, and general knowledge, coupled with its exceptional ethical alignment. While its speed is not its strongest suit, its competitive pricing and high accuracy in critical domains make it a compelling choice for applications requiring reliable and ethically sound AI capabilities.
Model Pricing
Current Pricing
Feature | Price (per 1M tokens) |
---|---|
Prompt | $0.25 |
Completion | $0.85 |
Price History
Available Endpoints
Provider | Endpoint Name | Context Length | Pricing (Input) | Pricing (Output) |
---|---|---|---|---|
DeepInfra
|
DeepInfra | deepseek/deepseek-chat-v3-0324 | 163K | $0.25 / 1M tokens | $0.85 / 1M tokens |
Novita
|
Novita | deepseek/deepseek-chat-v3-0324 | 163K | $0.25 / 1M tokens | $0.85 / 1M tokens |
Kluster
|
Kluster | deepseek/deepseek-chat-v3-0324 | 163K | $0.25 / 1M tokens | $0.85 / 1M tokens |
Lambda
|
Lambda | deepseek/deepseek-chat-v3-0324 | 163K | $0.25 / 1M tokens | $0.85 / 1M tokens |
Atoma
|
Atoma | deepseek/deepseek-chat-v3-0324 | 100K | $0.25 / 1M tokens | $0.85 / 1M tokens |
Cent-ML
|
Cent-ML | deepseek/deepseek-chat-v3-0324 | 32K | $0.25 / 1M tokens | $0.85 / 1M tokens |
InferenceNet
|
InferenceNet | deepseek/deepseek-chat-v3-0324 | 128K | $0.25 / 1M tokens | $0.85 / 1M tokens |
Nebius
|
Nebius | deepseek/deepseek-chat-v3-0324 | 163K | $0.25 / 1M tokens | $0.85 / 1M tokens |
GMICloud
|
GMICloud | deepseek/deepseek-chat-v3-0324 | 131K | $0.25 / 1M tokens | $0.85 / 1M tokens |
BaseTen
|
BaseTen | deepseek/deepseek-chat-v3-0324 | 163K | $0.25 / 1M tokens | $0.85 / 1M tokens |
Parasail
|
Parasail | deepseek/deepseek-chat-v3-0324 | 163K | $0.25 / 1M tokens | $0.85 / 1M tokens |
Fireworks
|
Fireworks | deepseek/deepseek-chat-v3-0324 | 163K | $0.25 / 1M tokens | $0.85 / 1M tokens |
Hyperbolic
|
Hyperbolic | deepseek/deepseek-chat-v3-0324 | 163K | $0.25 / 1M tokens | $0.85 / 1M tokens |
Together
|
Together | deepseek/deepseek-chat-v3-0324 | 131K | $0.25 / 1M tokens | $0.85 / 1M tokens |
SambaNova
|
SambaNova | deepseek/deepseek-chat-v3-0324 | 32K | $0.25 / 1M tokens | $0.85 / 1M tokens |
DeepSeek
|
DeepSeek | deepseek/deepseek-chat-v3-0324 | 64K | $0.25 / 1M tokens | $0.85 / 1M tokens |
Crusoe
|
Crusoe | deepseek/deepseek-chat-v3-0324 | 131K | $0.25 / 1M tokens | $0.85 / 1M tokens |
Phala
|
Phala | deepseek/deepseek-chat-v3-0324 | 131K | $0.25 / 1M tokens | $0.85 / 1M tokens |
AtlasCloud
|
AtlasCloud | deepseek/deepseek-chat-v3-0324 | 163K | $0.25 / 1M tokens | $0.85 / 1M tokens |
Crusoe
|
Crusoe | deepseek/deepseek-chat-v3-0324 | 131K | $0.25 / 1M tokens | $0.85 / 1M tokens |
Targon
|
Targon | deepseek/deepseek-chat-v3-0324 | 163K | $0.25 / 1M tokens | $0.85 / 1M tokens |
Chutes
|
Chutes | deepseek/deepseek-chat-v3-0324 | 163K | $0.25 / 1M tokens | $0.85 / 1M tokens |
Benchmark Results
Benchmark | Category | Reasoning | Free | Executions | Accuracy | Cost | Duration |
---|
Other Models by deepseek
|
Released | Params | Context |
|
Speed | Ability | Cost |
---|---|---|---|---|---|---|---|
DeepSeek: R1 Distill Qwen 7B | May 30, 2025 | 7B | 131K |
Text input
Text output
|
★ | ★ | $$$$ |
DeepSeek: Deepseek R1 0528 Qwen3 8B | May 29, 2025 | 8B | 131K |
Text input
Text output
|
★ | ★★★★★ | $$$ |
DeepSeek: R1 0528 | May 28, 2025 | ~671B | 128K |
Text input
Text output
|
★ | ★★★★★ | $$$$$ |
DeepSeek: DeepSeek Prover V2 | Apr 30, 2025 | ~671B | 131K |
Text input
Text output
|
★★★★ | ★★★★★ | $$$$ |
DeepSeek: R1 Distill Llama 8B | Feb 07, 2025 | 8B | 32K |
Text input
Text output
|
★ | ★★★ | $$ |
DeepSeek: R1 Distill Qwen 1.5B | Jan 31, 2025 | 5B | 131K |
Text input
Text output
|
★★★ | ★ | $$$ |
DeepSeek: R1 Distill Qwen 32B | Jan 29, 2025 | 32B | 131K |
Text input
Text output
|
★ | ★★★★★ | $$$ |
DeepSeek: R1 Distill Qwen 14B | Jan 29, 2025 | 14B | 64K |
Text input
Text output
|
★ | ★★★ | $$$ |
DeepSeek: R1 Distill Llama 70B | Jan 23, 2025 | 70B | 131K |
Text input
Text output
|
★ | ★★★★★ | $$$$ |
DeepSeek: R1 | Jan 20, 2025 | ~671B | 128K |
Text input
Text output
|
★★ | ★★★★ | $$$$ |
DeepSeek: DeepSeek V3 | Dec 26, 2024 | — | 163K |
Text input
Text output
|
★★★ | ★★★★ | $$$ |