Providers + pricing
| Capabilities | Provider details | ||||
|---|---|---|---|---|---|
| ● Credits · billed by AnyRouter | |||||
NVIDIA nvidia | $0 | $0 | |||
| ● Your own key · billed by your provider · AnyRouter fee $0 | |||||
AIHubMix aihubmix-byok | $0 | $0 | Unavailable | ||
NVIDIA nvidia-byok | $0 | $0 | Unavailable | ||
OpenRouter openrouter-byok | $0 | $0 | Unavailable | ||
Ollama Cloud ollama-byok | $0 | $0 | Unavailable | ||
Baseten baseten-byok | $0 | $0 | Unavailable | ||
CommandCode commandcode-byok | $0 | $0 | Unavailable | ||
Ramp Router router-byok | $0 | $0 | Unavailable | ||
Vercel AI Gateway vercel-byok | $0 | $0 | Unavailable | ||
| ● Free pool · donated keys · not available for this model — donate a key | |||||
Try it
import { createAnyRouter } from "@anyr/ai-sdk-provider"import { generateText } from "ai" const anyrouter = createAnyRouter() const { text } = await generateText({ model: anyrouter("nvidia/nemotron-3-ultra-550b-a55b"), prompt: "Say hi in 3 words.",})console.log(text)
ANYROUTER_API_KEY · edits on the demo update this codeUptime + latency
No health checks recorded for this model yet.
More performance detail
Nemotron 3 Ultra 550BFree
nvidia/nemotron-3-ultranemotron-3-ultranvidia/nemotron-3-ultra-550b-a55b:free- AIHubMix
- NVIDIA
- NVIDIA
- OpenRouter
- Ollama Cloud
- Baseten
- CommandCode
- Ramp Router
- Vercel AI Gateway
Your access
Run Nemotron 3 Ultra 550B on your own key — your requests are billed by the provider. Pool callers pay AnyRouter credits.
No BYOK keys configured for this model yet.
Share a key with the pool to earn credits for every request it serves, covering your plan cost.
About
NVIDIA Nemotron-3-Ultra-550B-A55B is a 550B parameter (55B active) frontier model built on a LatentMoE hybrid architecture combining Mamba-2, MoE, and Attention with Multi-Token Prediction. Features a 1M token context window, configurable reasoning mode (enable_thinking), and strong multilingual support across English, French, Spanish, Italian, German, Japanese, Korean, Hindi, Brazilian Portuguese, and Chinese. Best suited for complex agentic workflows, long-context analysis, tool use, and high-stakes RAG.
Released 2026-06-04
