In Early Access

SubQ 1.1 Small

The first long-context model for data-intensive workloads.

SubQ is the first model built for multi-million token reasoning, allowing enterprises to work across full repositories, financial filings, and contract archives for a fraction of the cost.

Request Access → Read the Research

Built by researchers and engineers from

The problem

Enterprises are spending billions to work around the limitations of today's models.

Use cases

The data-heavy workloads that become possible.

Whole Artifact Reasoning

Analyze entire datasets at once: an entire GitHub repo, all legal documentation, every vendor contract, or years of SEC filings, without chunking, compression, or context loss.

Long Horizon Agents

Agents that hold the full task in context and remember long sequences of events, collapsing brittle multi-agent orchestration into one coherent run.

Search & Retrieval

Surface material insights that you can trust from across an entire company's IP, code, or documents without risk of hallucination.

All your context.
Always available.

Reason across millions of tokens in one prompt: entire repos, whole artifacts, and long-running agent state, with context to spare.

Tokens 0 12M

Five enterprise vendor contracts

Each a 500-page master agreement

~1.6M
Three years of SEC filings

A Fortune 500 10-Ks and 10-Qs

~2.9M
Python source code

The entire 3.13 standard library

~5.1M

~ Approximate token counts.

The breakthrough

The most compute-efficient model.

Learn More

Today's transformer-based LLMs waste compute by processing every possible relationship between tokens, but only a small fraction of these relationships matter.

SubQ is built differently. Using a proprietary algorithm called Subquadratic Sparse Attention (SSA), it isolates the tokens and relationships that matter, ensuring compute is used efficiently.

At 2M tokens, SubQ uses 128x less compute than frontier models.

Benchmarks

A leader in long-context retrieval and reasoning tasks.

Multi-Fact Retrieval

RULER · 128K multi-task retrieval 99.12%

Single Fact Retrieval: 1–2M

Needle-in-a-haystack · 1–2M tokens 100%

Single Fact Retrieval: 6–12M

Needle-in-a-haystack · 6–12M tokens 98%

Benchmark	SubQ 1.1 Small	GPT-5.5	Opus 4.8	Sonnet 4.6	GPT-5.4-mini	GPT-5.4-nano	Haiku 4.5
Graduate-level scienceGPQA Diamond · pass@1	85.4	93.2	92	87.5	87.5	81.7	67.2
Agentic financeAutomationBench	13%	18%	16%	8%	0%	n/r	3%
Competitive programmingLiveCodeBench v6 · pass@4	89.7	92	92.2	88.9	78.6	78.2	69.7

n/r = result not reported by the model provider

* SubQ 1.2 Medium coming soon

Technical report

Early access

Request API Access.

Research

From the lab.

ResearchJune 16, 2026

How SSA Makes Long Context Practical

Building a new class of LLMs from the architecture up.

Subquadratic is a frontier AI research company that believes the architecture layer is the highest-leverage surface in AI. While other major labs focus on incremental improvements to Transformer models, we're pushing foundational change at the architecture level to build models and products that scale efficiently.