Switchyard
NVIDIA · released Sep 21, 2026
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...
Specification
- Context window
- 1M
- Max output
- —
- Knowledge cutoff
- Not stated
- Parameters
- Undisclosed
- Licence
- Proprietary
- Serving providers
- 0
- Moderated
- No
Intelligence
—
Not benchmarked
Coding
—
Coding Index
Agentic
—
Agentic Index
Output speed
—
Median across providers
Latency
—
Time to first token
Cost per task
$-75000.000
Estimated
Benchmarks
Where the score comes from
The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.
Evaluation scores
This model has not been put through the benchmark suite. Its speed, latency and pricing figures below are still measured.
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- Qwen3.8 MaxQwen58.1
- Claude Opus 5.5Anthropic57.6
- Claude Sonnet 5.5Anthropic56.0
- Claude Fable 5.1Anthropic53.4
- GPT-6 AstraOpenAI52.7
- Gemini 4 ArgonGoogle52.6
- Muse WonderMeta52.4
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| Qwen3.8 Max | 58.1 |
| Claude Opus 5.5 | 57.6 |
| Claude Sonnet 5.5 | 56.0 |
| Claude Fable 5.1 | 53.4 |
| GPT-6 Astra | 52.7 |
| Gemini 4 Argon | 52.6 |
| Muse Wonder | 52.4 |
Pricing
What it costs to run
List prices per million tokens, plus what one representative task works out to.
List price
- Input / 1M tokens
- $-1000000
- Output / 1M tokens
- $-1000000
- Cached input / 1M
- Not offered
- Blended 3:1
- $-1000000
One task, estimated
$-75000.000
- Input tokens
- 50,000
- Output tokens
- 25,000
- Profile
- Standard
Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).
Serving providers
No serving providers listed.
Speed and latency figures are medians across these providers, so a widely-served model reports a blend rather than any single endpoint.