NEX AGI

Nex-N2.5-Pro

Generally availableOpen weights262K contextReasoning

Summary

Nex-N2.5-Pro is an open-weight language model from NEX AGI, released on 8 Sept 2026. It accepts text and images and generates text, with a 262K-token context window and up to 236K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $0.07 per million input tokens and $0.25 per million output tokens (OpenRouter), across 1 provider we track.

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...

Last verified 18 Nov 2026. Every figure on this page links to its source.

Specifications

DeveloperNEX AGI
Release date8 Sept 2026 [OpenRouter]
StatusGenerally available
WeightsOpen weights [Hugging Face]
Licenseapache-2.0 [Hugging Face]
Parameters397B [Hugging Face]
Context window262K (262,144 tokens) [OpenRouter]
Max output236K tokens [OpenRouter]
InputText and images [OpenRouter]
OutputText [OpenRouter]
Reasoning modeYes [OpenRouter]
Tool callingYes [OpenRouter]
Structured outputYes [OpenRouter]
Hugging Facenex-agi/Nex-N2.5-Pro [Hugging Face]

Nex-N2.5-Pro API pricing by provider

USD per million tokens. Sorted by input price.

ProviderInputOutputCached inputContextSource
OpenRouter
nex-agi/nex-n2.5-pro
$0.07$0.25$0.01262KOpenRouter, 18 Nov 2026

Running Nex-N2.5-Pro locally

Estimated memory, from the parameter count and the architecture in config.json on Hugging Face. Includes about 0.8 GB of runtime overhead.

QuantizationWeightsTotal, 8K contextTotal, 32K context
Q4_K_M (4-bit)241 GB242 GB242 GB
Q8_0 (8-bit)422 GB423 GB423 GB
FP16 / BF16 (16-bit)794 GB795 GB795 GB

At 4-bit with an 8K conversation, Nex-N2.5-Pro needs about 242 GB, more than any single consumer graphics card; it needs a unified-memory machine, a multi-GPU setup or a split between graphics card and system RAM. Check your own hardware, or see Best computer for local AI on our sister site AIPCs.

Frequently asked questions

What is the context window of Nex-N2.5-Pro?

Nex-N2.5-Pro has a context window of 262,144 tokens (262K) and can generate up to 235,929 tokens in a single response, according to OpenRouter.

How much does the Nex-N2.5-Pro API cost?

Nex-N2.5-Pro is listed from $0.07 per million input tokens and $0.25 per million output tokens (OpenRouter). Prices last verified 18 Nov 2026.

Is Nex-N2.5-Pro open source?

Nex-N2.5-Pro is an open-weight model: its weights are published on Hugging Face as nex-agi/Nex-N2.5-Pro under the apache-2.0 license. Check the license terms before commercial use.

When was Nex-N2.5-Pro released?

NEX AGI released Nex-N2.5-Pro on 8 Sept 2026, according to OpenRouter.

How much VRAM does Nex-N2.5-Pro need?

About 242 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 423 GB at 8-bit. That is more than any single consumer graphics card holds. These are estimates from the model's published parameter count and architecture.

Similar models from other labs

Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.

ModelLabReleasedContextInput $/1MOutput $/1MWeights
Ling 3.0 Flash FinInclusionai27 Aug 2026256K$0.07$0.22Open
Ling 3.0 Flash VLInclusionai10 Sept 2026256K$0.06$0.18Open
LFM3-1.7BLiquid6 Nov 2026262K$0.08$0.20Open
Nemotron 3.5 Lightning 30BNVIDIA11 Aug 2026262K$0.06$0.16Open
Ternary Bonsai 2 27BPrism ML18 Sept 2026262K$0.07$0.50Open
Ternary Bonsai 2 9BPrism ML16 Oct 2026262K$0.08$0.13Open

Change history

No changes detected since we started tracking this model. We re-check every source daily.

Sources