nex-agi
Nex AGI: Nex-N2.6
nex-agi/nex-n2.6
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
nex-agi/nex-n2.6 is a text-and-image-to-text agentic model from Nex AGI, built on GLM-5.3-Flash and released with FP8-quantized weights of approximately 321B parameters. Nex AGI positions it for computer use, coding, and long-horizon work involving tools, with attention to less repetitive reasoning and better use of declared tools. OpenRouter lists a 262,144-token context, text and image inputs, text outputs, tool calling, structured outputs, and reasoning controls.[1][2]
Strengths
- Accepts text and image inputs, produces text, and is listed with a 262,144-token context.[1]
- Exposes tool calling, tool choice, structured outputs, response formatting, logprobs, and reasoning parameters through OpenRouter.[1]
- Nex AGI reports reduced reasoning repetition, improved tool-list adherence, and stronger computer-use results than its predecessor and base model; these figures are vendor-reported.[2]
Limitations
- The supplied evidence is only the OpenRouter catalog entry and Nex AGI's model card, and no knowledge cutoff is stated; validate the model on your own workloads.[1][2]
- Benchmark and reliability figures are Nex AGI-reported; the card says they are model-level results, not a separate evaluation of this FP8 export.[2]
- Reasoning settings differ between sources: OpenRouter describes mandatory reasoning with high or medium effort, while the bundled chat template lists low, high, and max with max as the default; confirm the endpoint configuration.[1][2]
Where to use it
- Evaluate for computer-use or coding agents that must follow a declared tool list across long tasks.[1][2]
- Consider for multimodal assistants that read text plus images and return text within a large context.[1]
- Pilot through OpenRouter, or self-host with a GLM-5.3-Flash-capable runtime after confirming FP8 compatibility.[1][2]
Sources
- [1] OpenRouter catalog · Nex AGI: Nex-N2.6Sources checked: Nov 13, 2026
- [2] Model documentation · Nex AGI: Nex-N2.6Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
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...
Specifications
- Model ID
- nex-agi/nex-n2.6
- Canonical ID
- nex-agi/nex-n2.6-20261110
- Creator
- nex-agi
- Added to OpenRouter
- 10.11.2026
- Context length
- 262,144
- Modality
- text+image->text
- Input modalities
- text, image
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0.120 / out $0.400
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | reasoning: mandatory · default high · efforts: high, medium · parameters: include_reasoning, reasoning, reasoning_effort |
| Coding | No measurement | — |
| Agents | No measurement | parameters: structured_outputs, tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: mandatory · default high · efforts: high, medium · parameters: include_reasoning, reasoning, reasoning_effort |
| Document analysis | No measurement | — |
| Vision | No measurement | input: image |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
No evaluations are supplied for this model.
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| Nex AGIfp8 | 262,144 | $0.120 | $0.400 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.