Nex-N2.5-Mini
Nex-N2.5-Mini is a large language model made by Nex AGI, added to the catalog on 8 Sep 2026. It has a context window of 262,144 tokens and costs $0.025 per 1M input tokens and $0.10 per 1M output tokens. It accepts text and images and produces text. Typical uses: exploring codebases, implementing changes across multiple files and reasoning over text-and-image prompts.
Price checked · source: OpenRouter
What Nex-N2.5-Mini is
Nex AGI’s Nex-N2.5-Mini is an agentic model with a stated focus on coding in a visual feedback loop. It accepts text and images and produces text. The provider describes Nex-N2.5 as designed to turn goals into working, verified outcomes, and names codebase exploration and multi-file implementation as parts of its coding focus. The supplied description is incomplete, so this page does not infer additional functions from it. Image input means an image can be included with a request; the listed output remains text.
The model has a context length of 262,144 tokens and a maximum output of 235,929 tokens. That gives it room to receive extensive context and return long text, which may suit coding requests that include material from multiple files or require a detailed written response. The catalog also lists reasoning and structured outputs as supported features. These make the model a potential fit for tasks that involve examining a supplied problem, working through a coding request, and returning results in a defined structure. Its stated coding focus makes codebase exploration and multi-file implementation relevant ways to evaluate it. It can also be considered for text-and-image prompts where a text response is needed. The listed capabilities establish the model's input and output formats and supported features, but do not specify particular programming languages, tools, or other integrations.
Key features
- Accepts text and image inputs and produces text
- Has a 262,144-token context length
- Supports outputs of up to 235,929 tokens
- Supports reasoning and structured outputs
- Described as focused on coding with a visual feedback loop
Typical uses
- Exploring codebases
- Implementing changes across multiple files
- Reasoning over text-and-image prompts
- Returning structured text results
Nex-N2.5-Mini pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $0.025 |
| Output, per 1M tokens | $0.10 |
| Cached input read, per 1M tokens | $0.0025 |
No price change since it was added on 8 Sep 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0000 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0007 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0010 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.0039 |
Nex-N2.5-Mini specifications
| Model id | nex-agi/nex-n2.5-mini |
|---|---|
| Version | nex-n2.5-mini-20260908 |
| Context window | 262,144 tokensAbout 196,608 English words |
| Max output | 235,929 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 8 Sep 2026 |
| Input types | text, image |
|---|---|
| Output types | text |
| Tool calling | No |
| Structured outputs | Yes |
| Reasoning effort control | Yes |
| Content moderation | Not applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
No output has been recorded for Nex-N2.5-Mini yet.
Compare Nex-N2.5-Mini
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.