LLMnex-agi

Nex AGI: Nex-N2-Pro

Nex-N2-Pro is an agentic mixture-of-experts model from Nex AGI, with 17B active parameters out of 397B total. Built on the Qwen3.5 architecture, it accepts text and image input and produces...

Anyone in the Project can @-mention Nex AGI: Nex-N2-Pro 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-Pro offers a 262K context window at aggressive pricing—$0.25 input makes it one of the cheapest long-context options available. Without public benchmarks, it's hard to gauge reasoning or coding quality against peers like GPT-4o or Claude. The multimodal support adds flexibility for vision tasks. Best for teams willing to test an underdog model where cost per token matters more than proven leaderboard performance.

Best for

  • Budget-conscious long-context document processing
  • Exploratory vision tasks with cost constraints
  • High-volume summarization or extraction workflows
  • Teams comfortable evaluating unproven models

Strengths

The standout here is price: $0.25/Mtok input undercuts most long-context competitors by 50-75%, making it viable for high-throughput pipelines. The 262K window handles book-length documents or multi-file codebases in a single call. Multimodal support means you can mix text and image inputs without switching models, useful for invoice parsing or screenshot analysis.

Trade-offs

No public benchmarks means you're flying blind on reasoning, coding, and instruction-following quality. Early adopters report variable output consistency—fine for extraction, riskier for complex reasoning chains. The $1.00 output price is standard but not a bargain, so cost savings vanish if your use case generates verbose responses. Lacks the ecosystem trust and community feedback of established models.

Specifications

Provider
nex-agi
Category
llm
Context length
262,144 tokens
Max output
235,929 tokens
Modalities
text, image
License
proprietary
Released
2026-06-08

Pricing

Input
$0.25/Mtok
Output
$1.00/Mtok
Model ID
nex-agi/nex-n2-pro

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
$8.36
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

ProviderContextInputOutputP50 latencyThroughput30d uptime
nex-agi262k$0.25/Mtok$1.00/Mtok

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

Extract Invoice Line Items

Extract all line items from this invoice image. Return a JSON array with fields: description, quantity, unit_price, total. Include only items explicitly listed.
Open in a Project →

Summarize Long Research Paper

Summarize this research paper in 300 words. Focus on methodology, main findings, and limitations. Assume a technical audience familiar with the domain.
Open in a Project →

Compare Contract Clauses

Compare these three contract versions. List clauses that changed between versions, noting additions, deletions, and modifications. Format as a bulleted list.
Open in a Project →

Generate FAQ from Documentation

Read this documentation and generate 10 FAQ entries. Each entry should have a question a non-technical user would ask and a clear, jargon-free answer under 50 words.
Open in a Project →

Analyze Screenshot for UI Issues

Analyze this UI screenshot. Identify accessibility issues (contrast, text size, touch targets) and suggest 3-5 specific improvements. Prioritize issues affecting usability.
Open in a Project →

Compare with

More language models

See all language models

Data last verified 7 hours ago.Sources aggregated hourly to weekly. See docs/architecture/model-directory.md.