od NVIDIAPremium
Nemotron 3 Ultra
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).
nemotron-3-ultra-freeGenerate chat completions with this model.
/api/v1/chat/completionsGET /api/v1/models?type=chat{
"model": "nemotron-3-ultra-free",
"messages": [
{
"role": "user",
"content": "Hello!"
}
],
"stream": false,
"thinking": true
}curl -X POST https://kunya.ai/api/v1/chat/completions \
-H "Authorization: Bearer kunya_YOUR_API_KEY" \
-H "Content-Type: application/json"
-d '{"model":"nemotron-3-ultra-free","messages":[{"role":"user","content":"Hello!"}],"stream":false,"thinking":true}'Poolside
Poolside flagship coding agent — tool calling, reasoning, 256K context, up to 32K output. Free on Kunya until July 28.
Dokumentacja APIZ-AI
Large-scale reasoning model — long-horizon agent workflows, project-level software engineering, 256K context, tools + structured outputs. Free on OpenRouter (rate-limited preview).
Dokumentacja APIMiniMax
Recursive self-improvement — SOTA in software engineering, tool calling, and office productivity
Dokumentacja API