Switchyard pricing & price history
Switchyard by NVIDIA costs — per 1M input tokens and — per 1M output tokens, with a 1M token context window.
Price history
No price changes since tracking began on 2026-10-02. We check every 10 minutes.
No real-traffic data for NVIDIA's own API on this model (it may not be served directly); the table below covers third-party hosts and says nothing about the official API.
Cost calculator
Alternatives to Switchyard
| Model | Input | Output | Context | Intel. | |
|---|---|---|---|---|---|
GLM 5.3 Flash Z.ai (Zhipu) | $0.0163 | $0.14 | 1M | 27.8 | compare |
DeepSeek V4 Flash 0731 DeepSeek | $0.12 | $0.24 | 1M | — | compare |
Llama 4 Scout Meta Llama | $0.10 | $0.30 | 1.3M | — | compare |
DeepSeek V4.1 Flash DeepSeek | $0.045 | $0.50 | 1M | — | compare |
MiMo-V2.6-Flash Xiaomi | $0.14 | $0.28 | 1.1M | 26.7 | compare |
Llama Guard 4 12B Meta Llama | $0.18 | $0.18 | 164K | — | compare |
Claude Haiku 5.5 Anthropic | $0.10 | $0.50 | 1M | 36.2 | compare |
GPT-6 Luna Pro OpenAI | $0.10 | $0.50 | 1.1M | — | compare |
About Switchyard
Switchyard is an open-source model router that switches between multiple models to optimize the cost of requests. By default it will use OpenRouter market data to select the most popular...
FAQ
How much does Switchyard cost?
Switchyard by NVIDIA costs — per 1M input tokens and — per 1M output tokens, with a 1M token context window. A typical request with 2,000 input and 500 output tokens costs about $0.
What is the context window of Switchyard?
Switchyard supports up to 1,000,000 tokens of context.
Has Switchyard’s price changed?
No price changes recorded since ModelBank started tracking it on 2026-10-02.
Is Switchyard being deprecated?
No retirement date has been announced for Switchyard as of 2026-10-31.