Nex-N2.6
Summary
Nex-N2.6 is an open-weight language model from NEX AGI, released on 10 Nov 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 $0.12 per million input tokens and $0.40 per million output tokens (OpenRouter), across 1 provider we track.
Nex-N2.6 is an agentic model from Nex AGI, built on [GLM-5.3-Flash](https://huggingface.co/zai-org/GLM-5.3-Flash-BF16) with about 321B parameters. It is suited for computer use, coding, and long-horizon tasks that involve tools. Compared with...
Last verified 18 Nov 2026. Every figure on this page links to its source.
Specifications
| Developer | NEX AGI |
|---|---|
| Release date | 10 Nov 2026 [OpenRouter] |
| Status | Generally available |
| Weights | Open weights [Hugging Face] |
| License | apache-2.0 [Hugging Face] |
| Parameters | 321B [Hugging Face] |
| Context window | 262K (262,144 tokens) [OpenRouter] |
| Max output | 236K tokens [OpenRouter] |
| Input | Text and images [OpenRouter] |
| Output | Text [OpenRouter] |
| Reasoning mode | Yes [OpenRouter] |
| Tool calling | Yes [OpenRouter] |
| Structured output | Yes [OpenRouter] |
| Hugging Face | nex-agi/Nex-N2.6 [Hugging Face] |
Nex-N2.6 API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| OpenRouter nex-agi/nex-n2.6 | $0.12 | $0.40 | $0.02 | 262K | OpenRouter, 18 Nov 2026 |
Running Nex-N2.6 locally
Estimated memory, from the parameter count and the architecture in config.json on Hugging Face. Includes about 0.8 GB of runtime overhead.
| Quantization | Weights | Total, 8K context | Total, 32K context |
|---|---|---|---|
| Q4_K_M (4-bit) | 195 GB | 196 GB | 196 GB |
| Q8_0 (8-bit) | 341 GB | 342 GB | 343 GB |
| FP16 / BF16 (16-bit) | 643 GB | 644 GB | 644 GB |
At 4-bit with an 8K conversation, Nex-N2.6 needs about 196 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-N2.6?
Nex-N2.6 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-N2.6 API cost?
Nex-N2.6 is listed from $0.12 per million input tokens and $0.40 per million output tokens (OpenRouter). Prices last verified 18 Nov 2026.
Is Nex-N2.6 open source?
Nex-N2.6 is an open-weight model: its weights are published on Hugging Face as nex-agi/Nex-N2.6 under the apache-2.0 license. Check the license terms before commercial use.
When was Nex-N2.6 released?
NEX AGI released Nex-N2.6 on 10 Nov 2026, according to OpenRouter.
How much VRAM does Nex-N2.6 need?
About 196 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 342 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.
| Model | Lab | Released | Context | Input $/1M | Output $/1M | Weights |
|---|---|---|---|---|---|---|
| Ternary Bonsai 2 27B | Prism ML | 18 Sept 2026 | 262K | $0.07 | $0.50 | Open |
| LFM3-1.7B | Liquid | 6 Nov 2026 | 262K | $0.08 | $0.20 | Open |
| Mi:dm K 3.0 Pro | KT | 5 Nov 2026 | 262K | $0.20 | $0.80 | – |
| Hy3 | Tencent (Hunyuan) | 6 Jul 2026 | 262K | $0.13 | $0.53 | Open |
| Ternary Bonsai 2 9B | Prism ML | 16 Oct 2026 | 262K | $0.08 | $0.13 | Open |
| Ling 3.0 Flash Fin | Inclusionai | 27 Aug 2026 | 256K | $0.07 | $0.22 | Open |
Change history
- License changed from none to apache-2.0
- Parameter count changed from none to 321B
- Added to the directory
- Now listed on OpenRouter