Nex AGI: Nex-N2-Pro (free)
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 Space can @-mention Nex AGI: Nex-N2-Pro (free) with the team's shared context - pooled credits, one chat, one memory.
Starter is free forever - 1 Space, 100 credits/month, 1 MCP. No card.
Verdict
Best for
- Budget-constrained document analysis projects
- Prototyping multimodal applications
- Long-context experimentation without usage fees
- Screenshot and image understanding tasks
- High-volume testing environments
Strengths
The 262K token context window handles substantial documents, codebases, or conversation histories in a single pass. Vision support enables screenshot analysis, diagram interpretation, and image-text workflows without switching models. Zero pricing removes cost as a barrier for experimentation, high-volume testing, or educational use cases. The combination of long context and multimodal input at no charge creates a unique position for teams exploring capabilities before committing to paid infrastructure.
Trade-offs
No public benchmark data means quality is unverified against peers like GPT-4o, Claude, or Gemini—you're testing blind. Proprietary licensing limits transparency into training data, safety measures, or model architecture. Free tier models often impose rate limits, availability constraints, or deprioritized inference that can disrupt production workflows. Without established performance metrics, you'll need to run your own validation suite before trusting outputs for anything beyond experimentation.
Specifications
- Provider
- nex-agi
- Category
- llm
- Context length
- 262,144 tokens
- Max output
- 262,144 tokens
- Modalities
- text, image
- License
- proprietary
- Released
- 2026-06-08
Pricing
- Input
- $0.00/Mtok
- Output
- $0.00/Mtok
- Model ID
nex-agi/nex-n2-pro:free
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
5 seats · 80 msgs/day
Switchy meters this against your org's shared credit pool - one plan, one balance for everyone.
Providers
| Provider | Context | Input | Output | P50 latency | Throughput | 30d uptime |
|---|---|---|---|---|---|---|
| nex-agi | 262k | $0.00/Mtok | $0.00/Mtok | — | — | — |
Performance
Benchmarks
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
Starter prompts
Long Document Summary
Read this entire document and provide a structured summary with: (1) main thesis, (2) three key findings, (3) methodology used, and (4) limitations mentioned by the authors.Open in a Space →
Screenshot Debugging
Analyze this screenshot of an application error. Identify what went wrong, suggest the likely cause, and recommend specific debugging steps.Open in a Space →
Codebase Context Analysis
Here are five files from a Python project. Explain how the modules interact, identify any circular dependencies, and suggest refactoring opportunities.Open in a Space →
Diagram Interpretation
Examine this system architecture diagram and describe: (1) main components, (2) data flow between services, (3) potential bottlenecks, and (4) missing redundancy.Open in a Space →
Multi-Turn Conversation
I'm going to describe a complex business scenario in stages. After each stage, summarize what you understand so far and ask clarifying questions before I continue.Open in a Space →