import requests r = requests.post( "https://api.aimlapi.com/v1/chat/completions", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "nex-agi/nex-n2.5-pro", "messages": [ { "role": "user", "content": "Hello!" } ] }, ) print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/chat/completions", { method: "POST", headers: { Authorization: `Bearer ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ "model": "nex-agi/nex-n2.5-pro", "messages": [ { "role": "user", "content": "Hello!" } ] }), }); console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/chat/completions \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"nex-agi/nex-n2.5-pro","messages":[{"role":"user","content":"Hello!"}]}'
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
| Cached input |
Cached input is billed at a fifth of the fresh-input rate, which matters for agent loops that re-send the same long prefix every turn.
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Nex-N2.5-Pro This page | Agentic workflows and structured output | |||
| Multimodal reasoning |
Nex-N2.5-Pro is an agentic multimodal model from Nex AGI. It is the mid-size member of the Nex-N2.5 family and is built for computer-use and visual feedback workflows.
Nex-N2.5-Pro accepts text and images as input. It produces text output.
Yes, Nex-N2.5-Pro supports tool calling. It can interact with external tools, APIs, and data sources as part of its response flow.
Yes, Nex-N2.5-Pro supports structured outputs. It can return JSON-schema-style structured responses.
It is built for agentic coding inside a visual feedback loop, including exploring codebases, making multi-file changes, running commands, driving browser and desktop interfaces, and testing results before revising. It is also targeted at autonomous software engineering, GUI-based QA, computer-use automation, deep research, and scientific workflows.
Nex-N2.5-Pro has a 262K-token context window. The provider page states that it supports 262K tokens.
Developers typically search for whether Nex-N2.5-Pro supports text and image input, tool calling, structured outputs, and reasoning control. They also look for whether it is suited to computer-use agents, browser automation, coding workflows, and visual self-correction.
Yes, Nex-N2.5-Pro is multimodal. Its documented inputs are text and image, and its design centers on visual feedback for computer-use tasks.
The developer is Nex AGI. The model is listed as Nex-N2.5-Pro by Nex AGI.
