Skip to main content

Nex AGILanguage modelOpen weights

Nex-N2.6

Summary

Nex-N2.6 is a language model with image input, built on GLM-5.3-Flash. Nex AGI developed it for coding, computer use, and longer tasks that involve tools.

Nex AGI provides FP8 weights under Apache 2.0. OpenRouter offers an API route with a 262,144-token context window.

All specifications

Input and output

Input
Text and images.
Source: Input
Output
Text.
Source: Output

Watermarking and provenance

AI watermarking refers to invisible signals embedded in the output. Visible marks and provenance metadata are listed separately. Unknown means there is insufficient evidence for that particular field.

AI watermarking
Unknown
no source
Watermarking technique
Not known
no source

Licence and access

License
Apache 2.0 according to the model card.
Source: License
Shutdown
None announced
no source

Further details

Checkpoint
nex-agi/Nex-N2.6. Released FP8 weights based on GLM-5.3-Flash.
Source: Checkpoint
Reasoning
The bundled chat template supports low, high, and max. The default is max.
Source: Reasoning
Checkpoint configuration
The published configuration sets the maximum number of positions to 1,048,576.
Source: Checkpoint configuration
OpenRouter access
Model ID nex-agi/nex-n2.6. OpenRouter lists a 262,144-token context window for this API route.
Source: OpenRouter access

Prices

OpenRouter pricing
Listed on November 12: $0.12 input, $0.40 output, and $0.024 cache read per million tokens.Source

Frequently asked questions about Nex-N2.6

Can I run Nex-N2.6 locally?

Yes, the weights are open. With 321B parameters it needs a lot of memory, more a server than a laptop.

Stated by Nex AGI

Open weights
yes
License
Apache 2.0 according to the model card.
Parameters
321B
active per token
n/a