d3-lite
Freevllm-sr/d3-lite131K context · Oct 2026 · 2 upstreamsupstream上游
d3-lite is a 0.8B multimodal decision model from vLLM Semantic Router (Decision 3.0). Send a state, optionally with images and videos, plus typed questions (choice, noul and score) and get a calibrated probability for each answer in one forward pass, with no generated text. Official Jev Decision Index scores are 26.16 on the text board and 42.11 on the vision board. Context is 131,072 tokens per request. Call POST /api/v1/decisions (POST /api/v1/systemone is the same handler). The service logs requests and may train on them, so it is skipped when Always enforce ZDR is on (Dashboard, Privacy).
- contextngữ cảnh上下文
- 131K
- inputđầu vào输入 / 1M
- $0
- outputđầu ra输出 / 1M
- $0
- question typesloại câu hỏi问题类型
- noul · choice · score
Upstreams
2- 1vLLM Semantic RouterPlatform · freeFreeTPS —TTFT ——
- 2vLLM Semantic RouterYour key · not addedyour planTPS —TTFT ——
- Up
- No traffic
- Down
Details
- Owner
- Vllm Sr
- Kind
- Decisions
- Released
- Oct 2026
- Context
- 131K
- Data policy
- Provider retention
- Endpoint
/api/v1/decisions
Quick start
curl https://anyrouter.dev/api/v1/decisions \ -H "Authorization: Bearer $ANYROUTER_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "state": "Help! My payouts have been failing for 3 days.", "model": "vllm-sr/d3-lite", "questions": { "is_urgent": { "type": "noul", "instructions": "Does this convey urgency?" } } }'
- Routing, classification and moderation of text, images and video
- Scoring and grading with calibrated probabilities
Architecture and licenseKiến trúc và giấy phép架构与许可
- Total parametersTổng tham số总参数
- 0.85B[1]
- Native contextNgữ cảnh gốc原生上下文
- 131,072[2]
- LicenseGiấy phép许可
- Apache-2.0 · Open weightsTrọng số mở开放权重[1]
StrengthsĐiểm mạnh优势[1],[2]
- Official Jev Decision Index scores of 26.16 (text board) and 42.11 (vision board)
- Answers every typed question about one input in a single forward pass, with a probability per answer
- Reads text, images and videos
Known limitsGiới hạn đã biết已知局限[2]
- Generates no text, so there is no written rationale
- A request may take at most 30 seconds, with per-key rate limits and daily quotas
- Requests and responses may be logged and used to train models
API notesGhi chú APIAPI 说明[2]
- System One request shape: a state plus named questions of type choice, noul and score
- Answers come back keyed by question name, with input token usage and zero output tokens
Links and versionsLiên kết và phiên bản链接与版本
- Model cardThẻ mô hình模型卡
- huggingface.co
- DocsTài liệu文档
- decision.vllm-sr.ai
SourcesNguồn来源
- [1]d3-lite model cardaccessedtruy cập访问于 2026-10-28
- [2]Decision API referenceaccessedtruy cập访问于 2026-10-28
Upstreams and pricingUpstream và giá上游与价格
Share cards3 images



params: state · model · questions
Uptime + latency
—recent checks · all routes
No health checks recorded for this model yet.
24h
No traffic in the last 24h.