LLMnex-agi

Nex AGI: Nex-N2-Mini

Nex-N2-Mini is an open-source agentic mixture-of-experts model from Nex AGI, the smaller sibling in the Nex-N2 series. It accepts text and image input and is built for coding, tool use,...

Anyone in the Project can @-mention Nex AGI: Nex-N2-Mini with the team's shared context - pooled credits, one chat, one memory.

All models

Starter is free forever - 1 Project, 100 credits/month, 1 MCP. No card.

Verdict

Nex-N2-Mini offers a massive 262K token context window at rock-bottom pricing — $0.03 input makes it one of the cheapest ways to process long documents or multi-turn conversations. The vision capability adds flexibility for mixed-media workflows. Without public benchmarks, you're trading proven performance data for cost savings and context length. Reach for this when budget and context matter more than leaderboard rankings.

Best for

  • Budget-constrained long-context tasks
  • Multi-turn conversations with deep history
  • Document analysis with embedded images
  • Prototyping before scaling to premium models
  • High-volume workflows needing cost control

Strengths

The 262K context window handles entire codebases, long transcripts, or multi-document analysis in a single call. At $0.03 per million input tokens, it undercuts most competitors by 3-10x, making it viable for high-volume use cases. Vision support means you can mix screenshots, diagrams, and text without switching models. The output pricing at $0.10/Mtok keeps generation costs predictable even for lengthy responses.

Trade-offs

No public benchmark data means you're flying blind on reasoning depth, instruction-following accuracy, and coding performance relative to established models like GPT-4o or Claude. The 'Mini' designation suggests this is a smaller parameter model, likely trading raw capability for speed and cost. Early-stage provider means less community knowledge, fewer integration examples, and higher risk of API changes or service interruptions compared to major vendors.

Specifications

Provider
nex-agi
Category
llm
Context length
262,144 tokens
Max output
262,144 tokens
Modalities
text, image
License
proprietary
Released
2026-06-24

Pricing

Input
$0.03/Mtok
Output
$0.10/Mtok
Model ID
nex-agi/nex-n2-mini

Per-token prices show what the model costs upstream. On Switchy your team draws from one shared org credit pool - one plan, one balance for everyone.

Team cost calculator

Estimated monthly spend
$0.84
17.6M tokens / month
5 seats · 80 msgs/day

Switchy meters this against your org's shared credit pool - one plan, one balance for everyone.

Providers

Provider-level routing data is not available yet for this model.

Performance

Performance snapshots are collected daily. Check back after the next ingestion run.

Benchmarks

Public benchmark scores are not available yet for this model. Check back after the next ingestion run.

Works well with

Top MCPs

Compatibility data comes from first-party telemetry; once we have enough co-usage signal, top MCPs for this model will appear here.

How Switchy teams use it

Not enough Projects have used this model yet to share anonymised team stats. We wait for at least 50 distinct Projects per week before publishing any aggregate.

Starter prompts

Long Document Summary

Summarize the key findings, methodology, and conclusions from the attached document. Focus on actionable insights and highlight any limitations the authors mention.
Open in a Project →

Multi-Turn Conversation

I'm going to ask a series of related questions about this topic. Remember the details from each answer as we go deeper — I'll reference earlier points without repeating them.
Open in a Project →

Screenshot Analysis

Analyze this screenshot and list every interactive element you see. For each button or input field, describe its likely function based on visual context and any visible labels.
Open in a Project →

Codebase Context

Review these files for inconsistent naming conventions and suggest a unified pattern. Point out where the same logic is duplicated across multiple modules.
Open in a Project →

Cost-Sensitive Drafting

Write five variations of this marketing email, each emphasizing a different benefit. Keep tone professional but approachable, around 150 words each.
Open in a Project →
Data last verified 6 hours ago.Sources aggregated hourly to weekly. See docs/architecture/model-directory.md.