gpt-6-luna

GPT-6 Luna is an efficient reasoning model in OpenAI’s GPT-6 family, designed for high-concurrency and cost-sensitive workloads. It is well suited for large-scale use cases such as batch text processing, classification and extraction, customer service automation, content generation, and lightweight agents. The model has an approximately 1.05 million-token context window and can generate up to 128,000 tokens in a single response. It supports text and image input with text output. Through the Responses API, it can use function calling, web search, file search, code interpreter, computer use, and MCP tools. Reasoning effort can be configured from none to max, with medium as the default. It is ideal for enterprise applications that prioritize high throughput and low cost.

Context

1050000 tokens

Max output

128000 tokens

Input

llm image

Output

llm