Question 1

What is the cost of gpt-oss-120b by Nebius Token Factory?

Accepted Answer

gpt-oss-120b by Nebius Token Factory costs $0.15 per 1M input tokens and $0.60 per 1M output tokens. Cached reads cost $0.01 per 1M tokens. Cache writes cost $0.18 per 1M tokens.

Question 2

What is the context window of gpt-oss-120b by Nebius Token Factory?

Accepted Answer

gpt-oss-120b by Nebius Token Factory has a context window of 131K tokens. It supports up to 124K input tokens and can generate up to 8K output tokens.

Question 3

What are the capabilities of gpt-oss-120b by Nebius Token Factory?

Accepted Answer

gpt-oss-120b by Nebius Token Factory supports advanced reasoning, tool calling/function calling, structured output, adjustable temperature. It has open weights.

Question 4

What input and output types does gpt-oss-120b support?

Accepted Answer

gpt-oss-120b by Nebius Token Factory accepts text as input and can generate text as output.

Question 5

Does gpt-oss-120b by Nebius Token Factory support reasoning?

Accepted Answer

Yes, gpt-oss-120b by Nebius Token Factory supports advanced reasoning capabilities. Reasoning output costs $0.60 per 1M tokens.

Question 6

Is gpt-oss-120b by Nebius Token Factory open source?

Accepted Answer

Yes, gpt-oss-120b by Nebius Token Factory has open weights, meaning the model weights are publicly available for download and self-hosting.

Question 7

Does gpt-oss-120b support function calling?

Accepted Answer

Yes, gpt-oss-120b by Nebius Token Factory supports tool calling (also known as function calling), allowing it to interact with external tools and APIs during conversations.

Question 8

What is the knowledge cutoff date for gpt-oss-120b?

Accepted Answer

gpt-oss-120b by Nebius Token Factory has a knowledge cutoff date of 2025-09. This means the model was trained on data available up until that date.

gpt-oss-120b API

Input Modalities

Output Modalities

Standard (per 1M tokens)

Reasoning (per 1M tokens)

Caching (per 1M tokens)