GPT Image API and MCP: how to add image generation to your project

GPT Image is a family of image generation models. NeuralSpace offers the following models: GPT Image 1.5, GPT Image 2, GPT Image 2 Pro. They all run through a single public API, and there is a ready MCP server for AI agents. The key is issued on the API keys page. Below are the model capabilities, request examples and setup steps.

What GPT Image can do

GPT Image generates images from text. Version 1.5 is priced by medium/high quality, version 2 supports 1K, 2K and 4K resolutions, and 2 Pro offers low/medium/high quality. The models follow text descriptions well and suit precise tasks.

API endpoint

Send a request to POST /v1/images/generations. Example: {"model": "gpt-image-2", "prompt": "a still life with fruit", "resolution": "2K"}. Authorization uses an API key in the x-api-key header. Available model ids: gpt-image-15, gpt-image-2, gpt-image-2-pro.

MCP tools

The NeuralSpace MCP server is available at POST /mcp (Streamable HTTP). To work with GPT Image, an agent uses the tools: generate_image, list_models, get_balance. This lets Claude Code, Cursor and other MCP clients use the site models directly.

How to connect

Sign up on NeuralSpace, open the API keys page and create an nsk-… key. Then pass it in the request header or in your MCP client settings. Full documentation is on the the /v1/docs page.

FAQ

How does 2 Pro differ from 2?

2 Pro is priced by low/medium/high quality, 2 by resolution.

Which resolutions are available?

Version 2 supports 1K, 2K and 4K.

What format is the request?

POST /v1/images/generations with model and prompt fields.