27B- input
- $0.12
- cached
- $0.024
- output
- $0.40
- Context
- 262Ktokens
- Listed
- 2d ago
- Size
- —parameters
Cost/1M tokens
Nex-N2.6 is a multimodal agentic model from Nex AGI, built on the GLM-5.3-Flash base and following Nex-N2.5-Pro. Its maker reports a 90% relative reduction in reasoning repetition compared with Nex-N2.5-Pro, alongside improved adherence to the declared tool list. It is built for computer use, coding, and long-horizon tasks involving tools.
- Multimodal model
- Open weights
- Accepts images
- Reasoning
- Tools
- Structured output
How it compares
Frequently asked questions
API and pricing
Input costs $0.12 per 1M tokens and output costs $0.40 per 1M tokens. 1 paid provider is tracked.
Yes. Cached input costs $0.024 per 1M tokens versus $0.12 per 1M tokens uncached, a discount of 80%.
A typical request of 10,000 input tokens and 1,000 output tokens costs $0.0016 at the cheapest provider, Nex AGI.
Over the last day, 1 of 1 endpoints with uptime data reached 99% uptime or better. The best uptime was 100.0%, by Nex AGI.
Privacy and data
Yes, Nex-N2.6 has open weights, so it can be self-hosted for full control of your data.
Capabilities and specs
The context window is 262K tokens (262,144) and the maximum output is 236K tokens (235,929).
Nex-N2.6 accepts text and image input. Audio and video input are not listed as supported modalities.
Yes, tool calling (function calling) is supported.
Yes, structured output (JSON schema or JSON mode) is supported.
Yes, reasoning is supported and always on. Effort levels are high and medium, with high as the default. 1 of 1 tracked providers expose reasoning, and the reasoning_effort setting is offered by a provider.
Quality and benchmarks
Alternatives matched on model kind, blended price and release date include Ternary Bonsai 2 27B by PrismML at $0.1813 per 1M tokens, LFM2.5-24B-A2B by Liquid AI at $0.2125 per 1M tokens, and MiMo-V2.6-Flash by Xiaomi at $0.175 per 1M tokens.
Ternary Bonsai 2 27BNex-N2.6 vs Ternary Bonsai 2 27BLFM2.5-24B-A2BNex-N2.6 vs LFM2.5-24B-A2BMiMo-V2.6-FlashNex-N2.6 vs MiMo-V2.6-Flash
Licensing and access
Nex-N2.6 has open weights.
The weights can be downloaded from the Hugging Face repository nex-agi/Nex-N2.6.
Basics
Nex-N2.6 was made by Nex AGI and was first listed on OpenRouter on November 10, 2026.
No, the listed API price is $0.12 input and $0.40 output per 1M tokens. The model has open weights, so self-hosting is an option.
Generated from Vertical Tabs data, updated November 10, 2026.
Discussion
No comments yet
Be the first to share your thoughts.