Question 1

What is the cost of GLM-4.7 (FP8) by Nebius Token Factory?

Accepted Answer

GLM-4.7 (FP8) by Nebius Token Factory costs $0.40 per 1M input tokens and $2.00 per 1M output tokens. Cached reads cost $0.04 per 1M tokens. Cache writes cost $0.50 per 1M tokens.

Question 2

What is the context window of GLM-4.7 (FP8) by Nebius Token Factory?

Accepted Answer

GLM-4.7 (FP8) by Nebius Token Factory has a context window of 128K tokens. It supports up to 124K input tokens and can generate up to 4K output tokens.

Question 3

What are the capabilities of GLM-4.7 (FP8) by Nebius Token Factory?

Accepted Answer

GLM-4.7 (FP8) by Nebius Token Factory supports tool calling/function calling, structured output, adjustable temperature. It has closed weights.

Question 4

What input and output types does GLM-4.7 (FP8) support?

Accepted Answer

GLM-4.7 (FP8) by Nebius Token Factory accepts text as input and can generate text as output.

Question 5

Is GLM-4.7 (FP8) by Nebius Token Factory open source?

Accepted Answer

No, GLM-4.7 (FP8) by Nebius Token Factory has closed weights. The model is only available through the Nebius Token Factory API.

Question 6

Does GLM-4.7 (FP8) support function calling?

Accepted Answer

Yes, GLM-4.7 (FP8) by Nebius Token Factory 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 GLM-4.7 (FP8)?

Accepted Answer

GLM-4.7 (FP8) by Nebius Token Factory has a knowledge cutoff date of 2025-12. This means the model was trained on data available up until that date.

GLM-4.7 (FP8) API

Input Modalities

Output Modalities

Standard (per 1M tokens)

Caching (per 1M tokens)

GLM-4.7 (FP8) API

Input Modalities

Output Modalities

Standard (per 1M tokens)

Caching (per 1M tokens)