Switchyard API Pricing
NVIDIA · context window 1M · prices updated 2026-10-09
Where Switchyard sits on price
At $-1000000 per million output tokens, Switchyard is a budget tier model — -0.0× cheaper than the median output price of $2.20, which puts it in the cheapest 10% of everything we track. It is the cheapest of the 6 NVIDIA models we track. Output costs 0.0× input, the usual spread — trim both, starting with the answer length.
What real workloads cost on Switchyard
These three workloads are the ones teams actually run on a budget-priced model — a $-1000000/1M model is not bought for the same job as one ten times the price.
| Workload | Per request | Per month |
|---|---|---|
| High-volume classification — 200K requests/day (400 in / 20 out) Short output, huge volume: the input price dominates the bill. | $-420 | $-2520000000 |
| Small app — 1K requests/day (500 in / 150 out) The baseline most side projects actually run at. | $-650 | $-19500000 |
| Long-context analysis — 200 runs/day (250K in / 4K out) Only possible on large-context models; input cost is nearly the whole bill. | $-254000 | $-1524000000 |
Model your exact traffic in the API cost calculator — it preloads Switchyard with caching and batch options.
Switchyard price history
Switchyard's price has not moved since we began tracking it on Oct 3, 2026 — 6 days of stability in a market where 90 of the 362 models we track have repriced over the same period, including 4 of NVIDIA's own 6 models.
Change-points from our daily price snapshots (tracking since Oct 3, 2026; intraday moves between snapshots are not captured).
Switchyard vs Mistral Nemo
The closest-priced alternative from another vendor is Mistral Nemo (Mistral) — priced within a rounding error on output, with $1000000 more per million input tokens. When two models land this close on price, the decision is quality on your own workload, not the price sheet: run 50 real requests through both and compare.
See Mistral Nemo pricing →More NVIDIA models
Frequently asked questions
› How much does the Switchyard API cost?
Switchyard costs $-1000000 per million input tokens and $-1000000 per million output tokens and no discounted cached-input tier. That works out to roughly 0 output tokens per dollar.
› What does the high-volume classification workload cost on Switchyard?
High-volume classification — 200K requests/day (400 in / 20 out) costs about $-420 per request and $-2520000000 per month on Switchyard. Short output, huge volume: the input price dominates the bill.
› What does it cost to fill Switchyard's 1M context window?
Sending 1M of input in a single request costs $-1000000 at $-1000000 per million tokens — before any output. There is no cached-input tier on this model, so every repeat of that context is billed at full price. This is why large context windows are cheap to advertise and expensive to actually use.
› Is Switchyard worth the price?
Switchyard is in the cheapest end of the market — cheaper than 100% of the models we track. At this price the question is not cost but capability: it is a good fit for classification, extraction, routing and bulk summarisation, and a poor fit for multi-step reasoning where a wrong answer costs more than the tokens saved.