Bison 1
Decisionsbaselabs/bison-1Decision · 131K context · Nov 2026 · 1 upstreamsupstream上游
Bison 1 is an open-weight Base Labs decision model post-trained from Gemma 4 31B. It returns calibrated probabilities for choice, yes/no and score questions over text and images, with a 128K-token context and the top score on the independent decision index v2.1.
Needs your own keyTo use Bison 1, add a key from Baseten Systemone. AnyRouter adds no fee.
- contextngữ cảnh上下文
- 131K
- inputđầu vào输入 / 1M (list)
- $0.10
- outputđầu ra输出, not token-billed, không tính theo token,不按 token 计费
- n/a
- question typesloại câu hỏi问题类型
- noul · choice · score
Upstreams
1- 1BasetenBYOKnot addedBilled to your key
Compare
Compared with models of similar price and context window.
| Model | In / out per 1M | Context | |
|---|---|---|---|
| Bison 1 | $0.10 / $0 | 131K (best) | |
| Groundhog 1 | $0.04 / $0 (best) | 131K (best) | |
| Nemotron 3.5 Content Safety | $0.05 / $0.15 | 131K (best) | |
| Schematron V2 Turbo | $0.03 / $0.15 | 128K (second best) | |
| GPT-OSS-120b | $0.03 / $0.14 (second best) | 131K (best) |
Quick start
POST /api/v1/decisions
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": "baselabs/bison-1",
"questions": {
"is_urgent": {
"type": "noul",
"instructions": "Does this convey urgency?"
}
}
}'Details
- Owner
- Baselabs
- Kind
- Decisions
- Released
- Nov 2026
- Context
- 131K
- Data policy
- Provider retention
- Endpoint
/api/v1/decisions
GalleryThư viện ảnh图库
Images from the vendorẢnh từ nhà phát hành图片来自厂商
- Routing requests and classifying cases over long documents or policy text.
- Yes/no checks and scoring against a rubric with calibrated confidence thresholds.
- Decisions over text and images using choice, noul and score questions.
Architecture and licenseKiến trúc và giấy phép架构与许可
- TypeLoại类型
- Dense[2]
- Total parametersTổng tham số总参数
- 31B[2]
- LicenseGiấy phép许可
- MIT · Open weightsTrọng số mở开放权重[3],[2]
StrengthsĐiểm mạnh优势[1]
- Ranked first of 19 decision models on the independent decision index v2.1 with a score of 76, ahead of d1.2-ultra at 75 and mammoth-1 at 71.
- Lowest Brier score on the index at 0.14, so its stated confidence tracks how often it is right.
- 128K context, eight times the previous generation, with text and image input.
Known limitsGiới hạn đã biết已知局限[2]
- Returns structured decisions and option probabilities, not free-form chat text.
- Designed for classification, routing and scoring; it does not generate long-form answers.
API notesGhi chú APIAPI 说明[4],[2]
- Native System One: POST https://inference.baseten.co/v1/systemone with {model, state, questions}; anyrouter exposes it at /v1/systemone.
- Auth is a Baseten API key sent as a Bearer token; add it under Dashboard → BYOK.
- Questions are choice, noul (yes/no) or score; Baseten bills input tokens per 1M and output is one token per question.
Links and versionsLiên kết và phiên bản链接与版本
- AnnouncementBài công bố发布公告
- baseten.co
- Model cardThẻ mô hình模型卡
- baseten.co
- DocsTài liệu文档
- docs.baseten.co
SourcesNguồn来源
- [1]Meet bison-1 and groundhog-1, frontier American decision modelsaccessedtruy cập访问于 2026-11-21
- [2]bison-1 model page - Basetenaccessedtruy cập访问于 2026-11-21
- [3]baselabs/bison-1 released weights and MIT licenseaccessedtruy cập访问于 2026-11-21
- [4]Baseten System One API referenceaccessedtruy cập访问于 2026-11-21
Upstreams and pricingUpstream và giá上游与价格
Share cards2 images


params: state · model · questions · service_tier · max_len
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…