A decision model trained by StartLux Labs for agents and workflows. Send a state and typed questions; receive choices, scores and probabilities. Auto-Think reasons when its first answer is uncertain.
Free testing in the default group. A valid Bamboo API key is required. No top-up is required.
export BAMBOO_API_KEY="YOUR_API_KEY"
curl --request POST 'https://api.bamboonode.cn/v1/decisions' \
--header "Authorization: Bearer $BAMBOO_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
"model": "startlux-decision-27b-autothink",
"state": "A customer was charged twice for the same order and requests a refund.",
"questions": {
"team": {
"type": "choice",
"instructions": "Which team should handle this ticket?",
"criteria": {
"billing": "Payments and refunds",
"tech": "Technical errors"
}
},
"urgent": {
"type": "noul",
"instructions": "Does the customer report an immediate safety emergency?"
}
},
"think_mode": "auto"
}'73.4
27B Auto-Think · public part
86.9%
27B Auto-Think · contrast pairs across 7,800 core items
#1
On the public part of Decision Index 0.3, the family leads at each published size from 0.8B to 27B.
Ask choice, score and yes/no probability questions. Use structured results directly in your workflow.
Answer in one pass first. Auto-Think adds reasoning when the initial answer is uncertain.
Route support tickets, review tool calls and check agent steps. Set a probability threshold for human review.
BAMBOO DESKTOP
Bring Bamboo, Claude and Codex into one desktop workspace. Work with files, write code and create content with the assistant that fits your task.
macOS 13+ · Apple Silicon
1.0.4 · Public beta · 0.89 GB
Choose Bamboo, Claude or Codex for your next task.
Organize documents, collaborate on code and keep work in context.
Explore image and video tools, plus local-model chat.
This download is for Apple Silicon Macs (M1 or later). Intel Mac and Windows installers are not available here yet.
b1a1a8a7d80ace3cd4aea4586e86d70d6e352c7f9b434fd41a7804c60e17866dAccess models from OpenAI, Anthropic, Google and more with one API key. Use OpenAI-compatible endpoints for chat and native APIs for specialized models.
from openai import OpenAI
client = OpenAI(
base_url="https://api.bamboonode.cn/v1",
api_key="bk-••••••••••••••••",
)
resp = client.chat.completions.create(
model="claude-sonnet-4-5",
messages=[{"role": "user", "content": "Hello"}],
)Connected providers
Configured backup channels can retry requests when an upstream fails.
Inspect and export the model, tokens, latency, and cost for every request.
Usage billing plus key-level limits keep budgets under control even if a key leaks.
Build with every model
Create an account and make your first API request.
Get started