Nex-N2-Pro
NexReleased Jun 8, 2026
Nex-N2-Pro is an agentic mixture-of-experts model from Nex AGI, with 17B active parameters out of 397B total. Built on the Qwen3.5 architecture, it accepts text and image input and produces...
- Context window
- 262K tokens
- Max output
- 262K tokens
- Input
- text, image
- Output
- text
- Tokenizer
- Qwen3
- Released
- Jun 8, 2026
- Reasoning
- optional
Pricing
Per 1M tokens. The provider price and our flat 3% fee are separate columns — what you pay is their sum.
| Per 1M tokens | Provider | + 3% fee | You pay |
|---|---|---|---|
| Input | $0.250 | $0.0075 | $0.258 |
| Output | $1.00 | $0.030 | $1.03 |
| Cache read | $0.025 | $0.0008 | $0.026 |
Benchmarks
Design Arena
| Category | Elo | Win rate | Rank |
|---|---|---|---|
| 3Dmodels | 1321 | 57% | #11 |
| Codemodels | 1274 | 50% | #24 |
| Data vizmodels | 1253 | 49.5% | #27 |
| Game devmodels | 1270 | 48.8% | #24 |
| SVGmodels | 1279 | 56.8% | #8 |
| UI componentsmodels | 1252 | 46.6% | #29 |
| Websitesmodels | 1255 | 47.7% | #29 |
Head-to-head preference voting. How we filter and rank
Supported parameters
- frequency_penalty
- include_reasoning
- logprobs
- max_tokens
- reasoning
- temperature
- top_k
- top_logprobs
- top_p
Call it
OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use model nex-agi/nex-n2-pro.
curl https://api.openkey.ai/v1/chat/completions \
-H "Authorization: Bearer $OPENKEY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "nex-agi/nex-n2-pro",
"messages": [{"role": "user", "content": "Hello"}]
}'import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.openkey.ai/v1",
api_key=os.environ["OPENKEY_API_KEY"],
)
completion = client.chat.completions.create(
model="nex-agi/nex-n2-pro",
messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.openkey.ai/v1",
apiKey: process.env.OPENKEY_API_KEY,
});
const completion = await client.chat.completions.create({
model: "nex-agi/nex-n2-pro",
messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);Questions
- How much does Nex-N2-Pro cost via API?
- Through OpenKey, Nex-N2-Pro costs $0.258 per 1M input tokens and $1.03 per 1M output tokens. That is the provider price ($0.250 / $1.00) plus a flat 3% fee — nothing else.
- What is Nex-N2-Pro's context window?
- Nex-N2-Pro accepts up to 262K tokens of context and returns up to 262K tokens per request.
- Is Nex-N2-Pro OpenAI-compatible?
- Yes. Send requests to OpenKey's /v1/chat/completions endpoint with model "nex-agi/nex-n2-pro" using any OpenAI SDK — only the base URL and API key change.
- What inputs does Nex-N2-Pro support?
- Nex-N2-Pro accepts text, image input and produces text output.