NVIDIA's most capable model with 550B parameters for complex reasoning, coding, and multimodal tasks.
OffRail routes requests to the best providers that are able to handle your prompt size and parameters.
NVIDIA's most capable model with 550B parameters for complex reasoning, coding, and multimodal tasks. You can access it through OffRail's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.
Pricing for Nemotron 3 Ultra 550B on OffRail starts at $0.50 per million input tokens and $2.20 per million output tokens, depending on the provider. The pricing table above always reflects the current per-provider rates.
Nemotron 3 Ultra 550B supports a context window of up to 1,048,576 tokens on its largest provider deployment.
Nemotron 3 Ultra 550B is served by DeepInfra, Nebius AI through OffRail. Requests are automatically routed to the best available provider, with fallback when a provider has issues.
Nemotron 3 Ultra 550B supports tool (function) calling and soft JSON output, but NOT strict JSON output schema (its upstream provider does not enforce it).
Nemotron 3 Ultra 550B was released on June 1, 2026.