# SubQ Preview

> SubQ Preview is Subquadratic's long-context chat model, built on its Subquadratic Sparse Attention (SSA) architecture for reasoning over very large inputs such as whole repositories, contract archives and filings. It is in early access: model availability and features may change. Text in, text out, with function calling, JSON-schema structured outputs and a reasoning_effort control (none to max). Reasoning text is never returned; reasoning tokens bill as output.

**ID**: `subquadratic/subq-preview`  
**Creator**: subquadratic  
**Category**: text  
**Context**: Not published  
**Pricing**: BYOK — billed by your provider  
**Released**: 2026-05-05  
**Web page**: https://anyrouter.dev/model/subquadratic/subq-preview

**Input modalities**: text  
**Output modalities**: text  

**Capabilities**: chat, reasoning, function-calling, structured-output, streaming

**Supported parameters**: max_tokens, temperature, top_p, stop, reasoning_effort, response_format, tools, tool_choice

## Usage

**Endpoint**: `POST https://anyrouter.dev/api/v1/chat/completions`

```bash
curl https://anyrouter.dev/api/v1/chat/completions \
  -H "Authorization: Bearer $ANYROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "subquadratic/subq-preview",
  "messages": [
    {
      "role": "user",
      "content": "Say hi in 3 words."
    }
  ]
}'
```

## Providers

| Provider | Input | Output |
| --- | --- | --- |
| subq-byok | BYOK — billed by your provider | — |

BYOK routes are billed by your own provider key — AnyRouter charges $0. Rates marked (list) are the provider's published list price.

## Source

- Upstream docs: https://docs.subq.ai/using-the-api/models/