nex-agi
Nex AGI: Nex-N2.5-Mini
nex-agi/nex-n2.5-mini
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
Nex-AGI's Nex-N2.5-mini is the smallest variant in the Nex-N2.5 agentic model family, which its developer positions for long-horizon tasks such as computer use, web browsing, and agentic coding driven by visual feedback. The OpenRouter catalog lists text and image inputs, text output, a 262,144-token context window, and selectable reasoning effort. Vendor-published benchmark tables cover coding, agentic, and multimodal suites, but several figures come from the developer's own evaluations, so they should be read as reported rather than independently verified. Weights are released under Apache-2.0.[1][2]
Strengths
- According to the developer, the model can operate computers and browsers and autonomously execute and test programs, using visual feedback to verify outcomes and self-correct during long tasks.[2]
- Reasoning effort is configurable (none, medium, high), and function calling plus structured outputs are supported, giving integrators control over latency-versus-depth trade-offs.[1][2]
- It accepts both text and image input over a long context window, and weights are published under Apache-2.0 for self-hosted deployment.[1][2]
Limitations
- All benchmark figures are vendor-published; several were produced with the developer's own harnesses, and the OpenRouter catalog lists no third-party results, so measured performance lacks independent confirmation.[1][2]
- The sources disagree on the default reasoning effort: the OpenRouter catalog says high, while the vendor documentation describes medium as the default.[1][2]
- Evidence is catalog- and vendor-card-only; fields such as knowledge cutoff are absent, and real-world behavior should be validated on the target workload.[1]
Where to use it
- Agentic coding assistants that explore repositories and apply multi-file changes, where the vendor's claimed visual self-verification could help; suitability should be confirmed in pilot tests.[1][2]
- Computer-use and browser automation agents that act on screenshots, a focus area the developer emphasizes.[2]
- Document- and UI-understanding tasks that combine image input with text output, such as parsing screens or structured documents.[1][2]
Sources
- [1] OpenRouter catalog · Nex AGI: Nex-N2.5-MiniSources checked: Nov 13, 2026
- [2] Model documentation · Nex AGI: Nex-N2.5-MiniSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file...
Specifications
- Model ID
- nex-agi/nex-n2.5-mini
- Canonical ID
- nex-agi/nex-n2.5-mini-20260908
- Creator
- nex-agi
- Added to OpenRouter
- 08.09.2026
- Context length
- 262,144
- Modality
- text+image->text
- Input modalities
- text, image
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0.025 / out $0.100
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | reasoning: optional · default high · efforts: high, medium, none · parameters: include_reasoning, reasoning, reasoning_effort |
| Coding | No measurement | — |
| Agents | No measurement | parameters: structured_outputs |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: optional · default high · efforts: high, medium, none · parameters: include_reasoning, reasoning, reasoning_effort |
| Document analysis | No measurement | — |
| Vision | No measurement | input: image |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
No evaluations are supplied for this model.
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| Nex AGIbf16 | 262,144 | $0.025 | $0.100 | — | — | 86.21% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.