Nex AGI: DeepSeek V3.1 Nex N1

Nex AGI: DeepSeek V3.1 Nex N1

nex-agi · Released Dec 8, 2025 Specialist
Intelligence #126 / 583
53.0 Our Score
AA Index #129 / 380
21.0 Artificial Analysis
Input #241 / 583
$0.135 per 1M tokens
Output #256 / 583
$0.500 per 1M tokens
Context #240 / 583
131,072 tokens

Analysis Summary

DeepSeek V3.1 Nex N1 from Nex AGI has an intelligence index of 21 and a coding index of 28.4. Agentic performance at 29.5 is modest, but MMLU Pro at 0.833 and GPQA at 0.735 show solid general knowledge. Tool use and function calling are supported. The 131K context window is adequate for most business document tasks. Instruction following at 0.378 is moderate.

For businesses, this model suits cost-sensitive coding assistance, structured content generation, and lightweight tool-use workflows. The coding index is competitive for its price tier, and the knowledge breadth makes it useful for research or drafting tasks. It is not suited to complex agentic pipelines or high-stakes reasoning.

At $0.135 input and $0.50 output, it is among the most affordable tool-capable models in this batch. Nex AGI is a newer provider, and enterprise support infrastructure is less established than major providers. Teams comfortable with the provider can extract strong value for routine coding and content tasks.

Assessed June 17, 2026

Editorial notes

Nex AGI's DeepSeek V3.1 Nex N1 offers competitive coding and instruction-following at very low cost with tool use support, though reasoning and agentic scores are mid-tier and the provider is less established for enterprise use.

Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?

Performance Profile

Intelligence3.8Technical4.5Value7.8Content5.5
Intelligence 3.8/10
Technical 4.5/10
Content 5.5/10
Value 7.8/10

How Nex AGI: DeepSeek V3.1 Nex N1 compares

Nex AGI: DeepSeek V3.1 Nex N1 ranks #129 of 380 AI models we track for overall intelligence, #147 of 292 for agentic tasks. Its 131K-token context window is larger than 59% of the models we list. At $0.14 per million input tokens it is cheaper than 59% of comparable models.

About Nex AGI: DeepSeek V3.1 Nex N1

DeepSeek V3.1 Nex-N1 is the flagship release of the Nex-N1 series — a post-trained model designed to highlight agent autonomy, tool use, and real-world productivity. Nex-N1 demonstrates competitive performance across..

Capabilities

Tool Use Function Calling

Performance Indices

Source: Artificial Analysis

21 Intelligence Index
29.5 Agentic Index
49.7 Math Index

Benchmark Scores

Intelligence

GPQA Diamond 73.5% Graduate-level scientific reasoning
HLE 6.3% Humanity's Last Exam
MMLU Pro 83.3% Multi-task language understanding
AIME 2025 49.7% Competition mathematics (2025)
SciCode 36.7% Scientific computing

Technical

LiveCodeBench 57.7% Live coding evaluation
TerminalBench Hard 24.2% Agentic terminal tasks
τ²-Bench 34.8% Conversational agent benchmark

Content

IFBench 37.8% Instruction following
LCR 45% Long-context reasoning

Benchmark data from Artificial Analysis and Hugging Face

How does Nex AGI: DeepSeek V3.1 Nex N1 stack up?

Compare side-by-side with other specialist models.

Compare Models

Model Information

OpenRouter ID nex-agi/deepseek-v3.1-nex-n1
Providernex-agi
Release Date December 8, 2025
Context Length131,072 tokens
Max Completion163,840 tokens
Status Active

Pricing

Token Type Cost per 1M tokens Cost per 1K tokens
Input $0.14 $0.000135
Output $0.50 $0.000500

Leaderboard Categories

Frequently asked questions about Nex AGI: DeepSeek V3.1 Nex N1

How much does Nex AGI: DeepSeek V3.1 Nex N1 cost?

Nex AGI: DeepSeek V3.1 Nex N1 costs $0.14 per million input tokens and $0.50 per million output tokens.

What is the context window of Nex AGI: DeepSeek V3.1 Nex N1?

Nex AGI: DeepSeek V3.1 Nex N1 has a context window of 131,072 tokens (131K).

What can Nex AGI: DeepSeek V3.1 Nex N1 do?

Nex AGI: DeepSeek V3.1 Nex N1 supports tool use and function calling.

Who created Nex AGI: DeepSeek V3.1 Nex N1?

Nex AGI: DeepSeek V3.1 Nex N1 is developed by Nex AGI and was released on December 8, 2025.