API — Beta
Build with DRUX
One API call. Multiple AI models. A confidence-weighted answer with an agreement score — ready for your app.
Quick start
curl -X POST https://drux.space/api/v1/search \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"query": "What is the best way to learn TypeScript?",
"models": [
"meta-llama/llama-3.2-3b-instruct:free",
"google/gemma-4-26b-a4b-it:free"
]
}'Response format
Every response includes per-model answers and a synthesized best answer with a 0–10 agreement score.
{
"query": "What is the best way to learn TypeScript?",
"models": [
{
"id": "meta-llama/llama-3.2-3b-instruct:free",
"name": "Llama 3.2 3B",
"provider": "Meta",
"status": "done",
"response": "Start with the official TypeScript handbook...",
"durationMs": 1823,
"error": null
}
],
"synthesis": {
"content": "The best way to learn TypeScript is...",
"score": 9,
"label": "Strong consensus",
"agreement": ["Start with official docs", "Practice with real projects"],
"disagreement": []
}
}Endpoint
POST
/api/v1/searchRequest body
querystringrequiredThe question to ask all modelsmodelsstring[]Array of model IDs (max 5). Defaults to 3 free models.Authentication
Authorization: Bearer YOUR_API_KEYModel reference
Pass any of these IDs in the models array.
Free
meta-llama/llama-3.2-3b-instruct:freeLlama 3.2 3B · Metagoogle/gemma-4-26b-a4b-it:freeGemma 4 26B · Googlegoogle/gemma-4-31b-it:freeGemma 4 31B · Googlenvidia/nemotron-nano-9b-v2:freeNemotron 9B · NVIDIAnvidia/nemotron-3-super-120b-a12b:freeNemotron 120B · NVIDIAopenai/gpt-oss-120b:freeGPT OSS 120B · OpenAIopenai/gpt-oss-20b:freeGPT OSS 20B · OpenAIarcee-ai/trinity-large-thinking:freeTrinity Thinking · Arcee AIliquid/lfm-2.5-1.2b-thinking:freeLFM Thinking 1.2B · Liquid AIqwen/qwen3-coder:freeQwen3 Coder · AlibabaPaid (requires credits)
openai/gpt-5.5GPT-5.5 · OpenAIopenai/gpt-5.4GPT-5.4 · OpenAIopenai/gpt-oss-120bGPT OSS 120B · OpenAIopenai/gpt-oss-20bGPT OSS 20B · OpenAIopenai/gpt-4o-miniGPT-4o Mini · OpenAIanthropic/claude-opus-4.7Claude Opus 4.7 · Anthropicanthropic/claude-sonnet-4.6Claude Sonnet 4.6 · Anthropicanthropic/claude-sonnet-4.5Claude Sonnet 4.5 · Anthropicanthropic/claude-haiku-4.5Claude Haiku 4.5 · Anthropicgoogle/gemini-3.5-flashGemini 3.5 Flash · Googlegoogle/gemini-2.5-proGemini 2.5 Pro · Googlegoogle/gemini-2.5-flashGemini 2.5 Flash · Googledeepseek/deepseek-v3.2DeepSeek V3.2 · DeepSeekdeepseek/deepseek-chatDeepSeek V3 · DeepSeekmistralai/mistral-large-2512Mistral Large 3 · Mistralmistralai/mistral-small-3.2-24b-instructMistral Small 3.2 · Mistralmistralai/codestral-2508Codestral 2508 · Mistralmeta-llama/llama-4-maverickLlama 4 Maverick · Metameta-llama/llama-4-scoutLlama 4 Scout · Metaqwen/qwen3-maxQwen3 Max · Alibabaqwen/qwen3-coderQwen3 Coder · Alibabaqwen/qwen3-32bQwen3 32B · Alibabacohere/command-aCommand A · Coherecohere/command-r-plus-08-2024Command R+ · Cohereamazon/nova-premier-v1Nova Premier · Amazonamazon/nova-pro-v1Nova Pro · Amazonmicrosoft/phi-4Phi-4 · Microsoftnvidia/nemotron-3-super-120b-a12bNemotron Super 120B · NVIDIA