The Unified Interface For Uncensored Language Models

Better prices, better uptime, no subscriptions. Access raw abliterated models through one API endpoint.

Featured Models

Abliterated flagship and reasoning architectures available right now.

Qwepus 35B A3B

35B

Flagship hybrid MoE+SSM model. 35B total parameters with only 3.6B active per token. Native 262K context with reasoning and thinking capabilities.

Price / 1M tokens$3.00 / $9.00

Details →

Qwen 3.6 35B Pro

35B

Aggressively tuned 35B MoE with zero refusals. Same architecture as Qwepus with custom imatrix quantization for maximum quality.

Price / 1M tokens$3.00 / $9.00

Details →

Total Recall 42B

42B

42B MoE thinking coder with only 3B active parameters. Built on Qwen3-30B-A3B-2507 with Brainstorm 20x enhancements for superior coding.

Price / 1M tokens$3.00 / $9.00

Details →

Integrate in seconds

Conform directly to standard OpenAI payload structures. Switch your endpoint base URL and API keys to start querying.

Get your key from the Console Dashboard

Set endpoint to api.unces.xyz/v1

Execute your request payload

# Quick curl execution
curl https://api.unces.xyz/v1/chat/completions \
  -H "Authorization: Bearer $UNCES_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwepus-35b-a3b",
    "messages": [
      {"role": "user", "content": "Hello"}
    ]
  }'