Vendor
Inception models
2 models in the reference catalogue, vendor list prices per million tokens. 0 are routable on this deployment today.
Models
2
0 routable here
Median list price
$0.22
3:1 input to output per 1M tokens
Strongest
-
no published benchmarks
Every Inception model
Newest first. Prices are the vendor's published rates per million tokens; click a model for the full specification.
| Model | Released | Context | Input / 1M | Output / 1M | Intelligence | Capabilities |
|---|---|---|---|---|---|---|
| Mercury 2.5 Previewinception/mercury-2.5-preview | Aug 31, 2026 | 260K | $0.04 | $0.15 | - | reasoning tools |
| Mercury 2inception/mercury-2 | Mar 4, 2026 | 128K | $0.25 | $0.75 | - | reasoning tools |
Frequently asked
- What is the cheapest Inception model?
- Mercury 2.5 Preview at $0.04 per 1M input tokens and $0.15 per 1M output tokens (vendor list price).
- Which Inception model has the largest context window?
- Mercury 2.5 Preview accepts 260K tokens of context.
- How do I route to Inception models with OpenSmartRoute?
- Declare a target in targets.yaml with metadata.model set to the catalogue id (for example inception/mercury-2.5-preview); the router scores it against every other target on cost, quality, latency and your policies for each request.
Route Inception with everything else
OpenSmartRoute picks the cheapest model that meets your quality bar per request, so a Inception flagship handles hard prompts while small models take the rest. Price a workload or try a routing decision live.