Nex AGI Nex-N2.6: Pricing, Specs and Limits
Nex AGI Nex-N2.6: agentic model built on GLM-5.3-Flash, 262K context, 0.12 in / 0.40 out per 1M tokens. Specs, limits and test prompts.
By ShilpBot Team · Published · 3 min read
Nex-N2.6 is an agentic model from Nex AGI, built on GLM-5.3-Flash with about 321 billion parameters. It is suited for computer use, coding and long-horizon tasks that involve tools.
It is one of the cheapest models here for agentic work: $0.12 per million input tokens and $0.40 per million output tokens, with a 262K context window.
Prices and specifications checked against the public OpenRouter catalogue on 2026-11-16. See the live model page for current limits.
Nex AGI Nex-N2.6 quick facts
| Detail | Value |
|---|---|
| Developer | Nex AGI |
| Model ID | nex-agi/nex-n2.6 |
| Added to the catalogue | 2026-11-10 |
| Type | Agentic model built on GLM-5.3-Flash |
| Parameters | 321B |
| Context window | 262K tokens (262,144) |
| Maximum output | 235,929 tokens |
| Input types | text, image |
| Price | 0.12 in / 0.40 out per 1M tokens (cached input 0.024) |
Feature support from the catalogue: Tool calling: listed; JSON / structured output: listed; Adjustable reasoning effort: listed.
What Nex AGI Nex-N2.6 is good for
- Computer-use and tool-heavy agents, which is what the listing targets.
- Low-cost coding agents that run many steps.
- Experiments with models built on GLM-5.3-Flash.
Limits of Nex AGI Nex-N2.6
- The context window (262K) is smaller than the 1M-token models.
- A fine-tune of another model inherits that model's strengths and weaknesses.
- Test long tool-use chains for drift before trusting them.
How Nex AGI Nex-N2.6 compares
- Z.ai GLM-5.3-Prime: It has a smaller context window (262,144 against 1,000,000 tokens); its output cap is 235,929 tokens against 131,072; it also accepts image input; it costs 0.12 input and 0.40 output per million tokens against 2.80 and 8.80.
- StepFun Step 5 Preview: It has a smaller context window (262,144 against 1,000,000 tokens); its output cap is 235,929 tokens against 64,000; it does not accept video input; it costs 0.12 input and 0.40 output per million tokens against 1.00 and 2.70.
- Particle AI Particle-1: It has a smaller context window (262,144 against 1,048,576 tokens); its output cap is 235,929 tokens against 131,072; it is a paid model, while Particle AI Particle-1 has a free listing.
Calling Nex AGI Nex-N2.6 from code
Use the model ID nex-agi/nex-n2.6 with any OpenAI-compatible client pointed at OpenRouter:
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "nex-agi/nex-n2.6", "messages": [{"role": "user", "content": "Explain what you can do in two sentences."}]}'Prompts that show what Nex AGI Nex-N2.6 can do
- Give it three tools and a multi-step task and count how many steps it needs.
- Ask it to read a screenshot of a form and list the fields to fill in.
- Compare cost and result with a pricier agentic model on the same task.
What Nex AGI Nex-N2.6 costs
The catalogue lists 0.12 per million input tokens and 0.40 per million output tokens, with cached input at 0.024 per million. Sending 1 million input tokens and receiving 100,000 output tokens would cost about 0.16. A single coding-agent step with a 150,000-token prompt and a 10,000-token answer would cost about $0.022 before caching. If your client reuses the same prompt prefix, cached input at 0.024 per million tokens can cut the input side of that bill by about 80 percent. Prices are set by the provider, can change, and may differ between hosting providers, so check the live model page before you budget.
Keep reading
Compare every paid model by price in our AI model pricing roundup, or see the free models roundup. New to terms like mixture-of-experts? Start with how neural networks learn.
Frequently asked questions
What is Nex-N2.6 built on?
The listing says it is built on GLM-5.3-Flash, with about 321 billion parameters.
What are the cost and limits of Nex AGI Nex-N2.6?
As of 2026-11-16 the catalogue lists 0.12 per million input tokens and 0.40 per million output tokens. 262K tokens (262,144) context window, up to 235,929 output tokens, model ID nex-agi/nex-n2.6. Prices can change, so check the live model page.
