Question 1

What is the cost of DeepSeek V3 by Helicone?

Accepted Answer

DeepSeek V3 by Helicone costs $0.56 per 1M input tokens and $1.68 per 1M output tokens. Cached reads cost $0.07 per 1M tokens.

Question 2

What is the context window of DeepSeek V3 by Helicone?

Accepted Answer

DeepSeek V3 by Helicone has a context window of 128K tokens. It supports up to 128K input tokens and can generate up to 8K output tokens.

Question 3

What are the capabilities of DeepSeek V3 by Helicone?

Accepted Answer

DeepSeek V3 by Helicone supports tool calling/function calling, adjustable temperature. It has closed weights.

Question 4

What input and output types does DeepSeek V3 support?

Accepted Answer

DeepSeek V3 by Helicone accepts text as input and can generate text as output.

Question 5

Is DeepSeek V3 by Helicone open source?

Accepted Answer

No, DeepSeek V3 by Helicone has closed weights. The model is only available through the Helicone API.

Question 6

Does DeepSeek V3 support function calling?

Accepted Answer

Yes, DeepSeek V3 by Helicone supports tool calling (also known as function calling), allowing it to interact with external tools and APIs during conversations.

Question 7

What is the knowledge cutoff date for DeepSeek V3?

Accepted Answer

DeepSeek V3 by Helicone has a knowledge cutoff date of 2024-12. This means the model was trained on data available up until that date.

DeepSeek V3 API

Input Modalities

Output Modalities

Standard (per 1M tokens)

Caching (per 1M tokens)

DeepSeek V3 API

Input Modalities

Output Modalities

Standard (per 1M tokens)

Caching (per 1M tokens)