Model Library
Nex AGIReleased June 2, 2026Nex-N2-Pro
Nex AGI · Released June 2, 2026
Intelligence score
41
At a glance
- Intelligence
- 41
- Speed
- 92.3tokens/sec
- Latency
- 1.81stime to first token
- Input price
- $0.50per 1M tokens
- Output price
- $2.50per 1M tokens
- Context window
- 260Ktokens
- Parameters
- 397billions
Summary
Comparison summary
Nex-N2-Pro scores 41 on the Artificial Analysis Intelligence Index, placing it well above average among other open weight models of similar size (median: 25). Nex-N2-Pro generates output at 92.3 tokens per second (based on the median across providers serving the model), which is above average compared to other open weight models of similar size (median: 61.7 t/s). Nex-N2-Pro costs $0.50 per 1M input tokens (better than average, median: $0.59) and $2.50 per 1M output tokens (somewhat higher than average, median: $2.20), based on the median across providers serving the model.
Specifications
Technical specifications
| Model name | Nex-N2-Pro |
|---|---|
| Provider | Nex AGI |
| Release date | June 2, 2026 |
| Intelligence score | 41 |
| Speed | 92.3 tokens/sec |
| Latency (TTFT) | 1.81s |
| Input price | $0.50 / 1M tokens |
| Output price | $2.50 / 1M tokens |
| Context window | 260,000 tokens |
| Parameters | 397B |
| Reasoning | Yes |
| Input modalities | text, image |
| Output modalities | — |
| Open weights | Yes |
| License | Apache 2 |
| API availability | — |
| Source | Model Intelligence legacy profile: nex-n2-pro |
Pricing
Token prices
Price per 1M tokens
Nex-N2-Pro, as listed in the catalog record
- Input$0.50
- Output$2.50
| Token type | Price per 1M |
|---|---|
| Input | $0.50 |
| Output | $2.50 |
Model Intelligence legacy profile: nex-n2-pro
FAQ · 21
Frequently asked questions
Nex-N2-Pro was released on June 2, 2026.
Nex-N2-Pro was created by Nex AGI.
Nex-N2-Pro scores 41 on the Artificial Analysis Intelligence Index, placing it well above average among other open weight models of similar size (median: 25).
Nex-N2-Pro generates output at 92.3 tokens per second (based on the median across providers serving the model), which is above average compared to other open weight models of similar size (median: 61.7 t/s).
Nex-N2-Pro has a time to first token (TTFT) of 1.81s (based on the median across providers serving the model), which is better than average compared to other open weight models of similar size (median: 2.01s).
Nex-N2-Pro costs $0.50 per 1M input tokens (better than average, median: $0.59) and $2.50 per 1M output tokens (somewhat higher than average, median: $2.20), based on the median across providers serving the model.
Nex-N2-Pro costs $0.50 per 1M input tokens and $2.50 per 1M output tokens (based on the median across providers serving the model). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.53 per 1M tokens. Pricing may vary by provider.
When evaluated on the Intelligence Index, Nex-N2-Pro generated 97M output tokens, which is somewhat higher than average compared to other open weight models of similar size (median: 92M).
Yes, Nex-N2-Pro is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
Nex-N2-Pro supports text and image input.
Nex-N2-Pro supports text output.
Yes, Nex-N2-Pro supports image input and can analyze, describe, and answer questions about images.
Yes, Nex-N2-Pro is multimodal. It can process text and image input and generate text output.
Nex-N2-Pro has a context window of 260k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, Nex-N2-Pro is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Nex-N2-Pro has 397 billion parameters (17 billion active).
Nex-N2-Pro is a Mixture of Experts (MoE) model with 397 billion total parameters, but only 17 billion active parameters are used during inference.
Nex-N2-Pro is released under the Apache 2.0 license. This license allows commercial use.
Nex-N2-Pro achieves a score of 41 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, Nex-N2-Pro is available via API through 1 provider.
Nex-N2-Pro is available through 1 API provider.