Question 1

What is the cost of Mercury by Inception?

Accepted Answer

Mercury by Inception costs $0.25 per 1M input tokens and $1.00 per 1M output tokens. Cached reads cost $0.25 per 1M tokens. Cache writes cost $1.00 per 1M tokens.

Question 2

What is the context window of Mercury by Inception?

Accepted Answer

Mercury by Inception has a context window of 128K tokens. It supports up to 128K input tokens and can generate up to 16K output tokens.

Question 3

What are the capabilities of Mercury by Inception?

Accepted Answer

Mercury by Inception supports tool calling/function calling, adjustable temperature. It has closed weights.

Question 4

What input and output types does Mercury support?

Accepted Answer

Mercury by Inception accepts text as input and can generate text as output.

Question 5

Is Mercury by Inception open source?

Accepted Answer

No, Mercury by Inception has closed weights. The model is only available through the Inception API.

Question 6

Does Mercury support function calling?

Accepted Answer

Yes, Mercury by Inception 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 Mercury?

Accepted Answer

Mercury by Inception has a knowledge cutoff date of 2023-10. This means the model was trained on data available up until that date.

Mercury API

Input Modalities

Output Modalities

Standard (per 1M tokens)

Caching (per 1M tokens)

Mercury API

Input Modalities

Output Modalities

Standard (per 1M tokens)

Caching (per 1M tokens)