Ampersand v0.1
Toolshumansand/ampersand-v0.1Text · 1M context · Oct 2026 · 1 upstreamsupstream上游
Ampersand v0.1 is humans&'s collaborator model, trained from GLM 5.3 for people to achieve goals together: it tracks what each person wants, flags conflicts, shares context, and asks questions in group chats. Through Vercel AI Gateway it takes text in and text out with reasoning effort and client-side function tools over a 1M-token context window.
Needs your own keyTo use Ampersand v0.1, add a key from Vercel AI Gateway. AnyRouter adds no fee.
- contextngữ cảnh上下文
- 1M
- inputđầu vào输入 / 1M (list)
- $1.00
- outputđầu ra输出 / 1M (list)
- $5.20
- routestuyến路由
- 1
- speed, 24htốc độ, 24h速度,24h
- No data yetChưa có dữ liệu暂无数据
Upstreams
1- 1Vercel AI GatewayYour keynot addedBilled to your key
Quick start
curl
curl https://anyrouter.dev/api/v1/chat/completions \
-H "Authorization: Bearer $ANYROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "humansand/ampersand-v0.1",
"messages": [
{
"role": "user",
"content": "Say hi in 3 words."
}
]
}'Details
- Owner
- Humansand
- Kind
- Chat
- Released
- Oct 2026
- Context
- 1M
- Data policy
- Provider retention
- Endpoint
/api/v1/chat/completions
GalleryThư viện ảnh图库
Images from the vendorẢnh từ nhà phát hành图片来自厂商
Introducing Ampersand, a collaborator model© humans&
- Group-chat facilitation for workplace and social teams: surfacing context, flagging conflicts, and asking questions while tracking each person's goals.
- Multi-agent coding teams, with Ampersand as the lead agent coordinating subagents over long multi-step tasks.
- Long-running collaboration sessions that keep conversation state per group over months of simulated time.
Architecture and licenseKiến trúc và giấy phép架构与许可
StrengthsĐiểm mạnh优势[2],[1]
- Leads the vendor's long-horizon Collaboration Over Time result (12.94), ahead of its GLM 5.3 base (9.89).
- Strongest teamwork result shown: 59.1% on Collaborative Intelligence at high effort.
- Top multi-agent coding results the vendor reports: 92.2% on SWE-bench Pro v2 HARD-51 and 77.9% on DeepSWE v1.1 in collaborative mode.
Known limitsGiới hạn đã biết已知局限[1],[2]
- May misunderstand goals, give incorrect information, interrupt, or disclose inappropriate context; simulation results may not generalize to real groups.
- Higher interaction cost than leading models in the vendor's simulation: sometimes offers unwanted coaching when people just want an answer.
- Prompt-injection susceptibility stays close to its GLM 5.3 base in the vendor's tests.
API notesGhi chú APIAPI 说明[4],[2]
- Owner's Agents API at https://ampersand.humansand.ai/v1: sessions via POST /agents/sessions, follow-up events streamed over SSE; one session per conversation keeps history.
- Reasoning effort low, medium, high, or max (default high today); up to 32,768 output tokens including reasoning.
- Function tools take JSON Schemas and are run by the caller's app; image input is rejected.
Links and versionsLiên kết và phiên bản链接与版本
- AnnouncementBài công bố发布公告
- ampersand.humansand.ai
- Model cardThẻ mô hình模型卡
- ampersand.humansand.ai
- DocsTài liệu文档
- ampersand.humansand.ai
- Pricing pageTrang giá价格页
- ampersand.humansand.ai
- Previous versionPhiên bản trước上一版本
- z-ai/glm-5.3
SourcesNguồn来源
- [1]Ampersand v0.1 Model Cardaccessedtruy cập访问于 2026-11-08
- [2]Ampersand — Our first model trained for people to achieve more togetheraccessedtruy cập访问于 2026-11-08
- [3]Ampersand Pricing and Limitsaccessedtruy cập访问于 2026-11-08
- [4]Build with Ampersandaccessedtruy cập访问于 2026-11-08
Upstreams and pricingUpstream và giá上游与价格
Share cards2 images


params: max_tokens · temperature · stop · tools · tool_choice · reasoning · include_reasoning
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…