Kunya Uncensored
by Kunya GPUPremium
Kunya Uncensored
Self-hosted dialogue model on dedicated GPU. Available when the inference server is running; offline when the VM is stopped.
kunya-uncensoredAPI Documentation
Generate chat completions with this model.
/api/v1/chat/completionsGET /api/v1/models?type=chat{
"model": "kunya-uncensored",
"messages": [
{
"role": "user",
"content": "Hello!"
}
],
"stream": false,
"max_tokens": 4096
}curl -X POST https://kunya.ai/api/v1/chat/completions \
-H "Authorization: Bearer kunya_YOUR_API_KEY" \
-H "Content-Type: application/json"
-d '{"model":"kunya-uncensored","messages":[{"role":"user","content":"Hello!"}],"stream":false,"max_tokens":4096}'Notes
- •OpenAI-compatible endpoint — works with any Kunya API key.
- •Set `"stream": true` for server-sent events.
Pricing
Capabilities
Similar Models
Nemotron 3 Ultra
NVIDIA
550B MoE frontier reasoning model (55B active) — long-horizon agentic workflows, coding agents, and deep research with 1M context. Free on OpenRouter. Web search via Kunya smart search (native tool calling not supported).
API DocumentationQwen 3.8 Max Prime
Qwen
Higher-throughput Qwen 3.8 Max SKU — same 2.4T MoE capability with faster serving, vision, tools, 1M context
API DocumentationMiniMax M3 (Nebius)
Nebius
MiniMax M3 served on Nebius Token Factory (B200, FP4, EAGLE3 speculative decoding) — cheaper than the direct MiniMax API ($0.30/$1.20 vs $0.60/$2.40 per 1M) but a shared, non-production endpoint. Admin-only for A/B testing against direct minimax-m3.
API Documentation