NVIDIA's Cosmos 3 vision-language reasoning model for physical AI, built for understanding real-world environments and multi-step reasoning over visual input.
LLM Gateway routes requests to the best providers that are able to handle your prompt size and parameters.
NVIDIA's Cosmos 3 vision-language reasoning model for physical AI, built for understanding real-world environments and multi-step reasoning over visual input. You can access it through LLM Gateway's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.
Pricing for Cosmos 3 Super Reasoner on LLM Gateway starts at $0.10 per million input tokens and $0.30 per million output tokens, depending on the provider. The pricing table above always reflects the current per-provider rates.
Cosmos 3 Super Reasoner supports a context window of up to 262,144 tokens on its largest provider deployment.
Cosmos 3 Super Reasoner is served by Nebius AI through LLM Gateway. Requests are automatically routed to the best available provider, with fallback when a provider has issues.
Yes. Cosmos 3 Super Reasoner supports both tool (function) calling and structured JSON outputs through LLM Gateway.
Cosmos 3 Super Reasoner was released on June 1, 2026.