NVIDIA: Switchyard
NVIDIA: Switchyard offers a 1,000,000-token context window at — per 1M input tokens and — per 1M output tokens. Supported inputs: text. Data via OpenRouter /models, as of Oct 29, 2026.
Source: OpenRouter /models · as of
OpenRouter model catalogue feed
These are provider-catalog specifications, not a task-quality benchmark. Prices describe the source listing and may vary by provider or routing. Unknown values are shown as — when the feed did not supply that value.
Specifications
| Context window | 1,000,000 tokens |
|---|---|
| Input price | — / 1M tokens |
| Output price | — / 1M tokens |
| Input modalities | text |
| Output modalities | text |
| Model id | nvidia/switchyard |
Frequently asked questions
What is the context window of NVIDIA: Switchyard?
NVIDIA: Switchyard supports up to 1,000,000 tokens of context.
How much does NVIDIA: Switchyard cost?
Pricing for NVIDIA: Switchyard is not published in OpenRouter /models.
What input types does NVIDIA: Switchyard support?
NVIDIA: Switchyard accepts text.
Related models
- Anthropic: Claude Fable Latest
- Anthropic: Claude Haiku Latest
- Anthropic: Claude Opus Latest
- Anthropic: Claude Sonnet Latest
- DeepSeek: DeepSeek Flash Latest
- DeepSeek: DeepSeek Pro Latest
Open the prompt composer, then choose a model →
Open the composer and choose a supported target model. The reference catalogue may include models unavailable in the composer.