SubQ Savant 1.4
subquadratic/subq-savant-1.4Vision · 4.2M context · Nov 2026 · 2 upstreamsupstream上游
SubQ Savant 1.4 is Subquadratic's long-context reasoning model. It reads up to 4M tokens per request and reasons before it answers, with text, image and file input on OpenAI-compatible Chat Completions and Responses endpoints. It is in early access and enabled per organization.
- contextngữ cảnh上下文
- 4.2M
- inputđầu vào输入 / 1M
- $0.10
- outputđầu ra输出 / 1M
- $0.50
- modalitiesphương thức模态
- text · image · file
- speed, 24htốc độ, 24h速度,24h
- No data yetChưa có dữ liệu暂无数据
Upstreams
2- 1SubQPlatform$0.10 / $0.50
- 2SubQBYOKnot addedBilled to your key
Compare
Compared with its other versions and models of similar price and context window.
| Model | In / out per 1M | Context | |
|---|---|---|---|
| SubQ Savant 1.4 | $0.10 / $0.50 (second best) | 4.2M (best) | |
| SubQ Preview | $0 / $0 (best) | – | |
| GPT-6 Luna Pro | $0.10 / $0.50 (second best) | 1.1M (second best) | |
| Muse Ember | $0.10 / $0.50 (second best) | 1M | |
| Particle-1 | $0.13 / $0.50 | 1M |
Quick start
curl https://anyrouter.dev/api/v1/chat/completions \
-H "Authorization: Bearer $ANYROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "subquadratic/subq-savant-1.4",
"messages": [
{
"role": "user",
"content": "Say hi in 3 words."
}
]
}'Details
- Owner
- Subquadratic
- Kind
- Vision
- Released
- Nov 2026
- Context
- 4.2M
- Data policy
- Provider retention
- Endpoint
/api/v1/chat/completions
- Whole-repository and long-document reasoning
- Contract, filing and data-room analysis over very large inputs
- Long-horizon agents that keep the full task in context
Architecture and licenseKiến trúc và giấy phép架构与许可
- Native contextNgữ cảnh gốc原生上下文
- 4,194,304[1]
StrengthsĐiểm mạnh优势[1],[2]
- Reads up to 4M tokens in a single request
- Reasons before answering with low, high and max effort levels
- Function calling, structured outputs and file input on OpenAI-compatible endpoints
Known limitsGiới hạn đã biết已知局限[1],[2]
- Early access; requests return 403 until SubQ enables the model for the organization
- Always reasons and samples at temperature 1; turning reasoning off or changing temperature returns 400
- Image input only, with no image output
API notesGhi chú APIAPI 说明[2],[1]
- Chat Completions and Responses endpoints; use an OpenAI SDK against https://api.subq.ai/v1
- reasoning_effort accepts low, high or max; none returns 400
- Reasoning tokens bill as output and count toward max_tokens
- Cached input bills at $0.01 per 1M tokens
Links and versionsLiên kết và phiên bản链接与版本
- DocsTài liệu文档
- docs.subq.ai
- Pricing pageTrang giá价格页
- docs.subq.ai
- Previous versionPhiên bản trước上一版本
- subquadratic/subq-preview
SourcesNguồn来源
- [1]SubQ modelsaccessedtruy cập访问于 2026-11-18
- [2]SubQ Chat Completions APIaccessedtruy cập访问于 2026-11-18
- [3]SubQ release notesaccessedtruy cập访问于 2026-11-18
Upstreams and pricingUpstream và giá上游与价格
Share cards3 images



AliasesBí danh别名 (1)
subquadratic/subq-savant-latest
params: max_tokens · temperature · top_p · stop · reasoning_effort · response_format · tools · tool_choice
Uptime + latency
—recent checks · all routes
No health checks recorded for this model yet.
24h
No traffic in the last 24h.
Across all upstreams
Loading usage…