SubQ Preview
subquadratic/subq-previewsubquadratic · — context · text + file → text · 1 upstreamsupstream上游
You need your own SubQ key to use this model.Bạn cần key SubQ riêng để dùng model này.使用此模型需要你自己的 SubQ 密钥。
The provider bills you. AnyRouter fee is $0.Nhà cung cấp tính phí. Phí AnyRouter là $0.由提供商计费，AnyRouter 费用为 $0。
Only route: Tuyến duy nhất: 唯一路由：your keykey của bạn你的密钥
Call this id from your code; another provider takes over when one fails.Gọi id này từ code của bạn; khi một provider lỗi, provider khác sẽ thay thế.在代码里调用这个 id；一个供应商失败时，另一个自动接手。 How it works →Cách hoạt động →了解做法 →
Upstreams and pricingUpstream và giá上游与价格
CodeMã代码
import osfrom openai import OpenAI client = OpenAI( api_key=os.environ["ANYROUTER_API_KEY"], base_url="https://anyrouter.dev/api/v1",) resp = client.chat.completions.create( model="subquadratic/subq-preview", messages=[{"role": "user", "content": "Say hi in 3 words."}],)print(resp.choices[0].message.content)
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 file (document) input, function calling, JSON-schema structured outputs and a reasoning_effort control (none to max). SubQ serves it on Chat Completions and the Responses API. Reasoning text is never returned; reasoning tokens bill as output.
Uptime + latency
No health checks recorded for this model yet.
params: max_tokens · temperature · top_p · stop · reasoning_effort · response_format · tools · tool_choice
Run SubQ Preview on your own key — your requests are billed by the provider. Pool callers pay AnyRouter credits.
No BYOK keys configured for this model yet.
Share a key with the pool to earn credits for every request it serves, covering your plan cost.
