Vendor
Upstage 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
$0.16
3:1 input to output per 1M tokens
Strongest
-
no published benchmarks
Every Upstage 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 |
|---|---|---|---|---|---|---|
| Solar Pro 4upstage/solar-pro4 | Aug 10, 2026 | 524K | $0.03 | $0.12 | - | reasoning tools |
| Solar Pro 3upstage/solar-pro-3 | Jan 27, 2026 | 131K | $0.15 | $0.60 | - | reasoning tools |
Frequently asked
- What is the cheapest Upstage model?
- Solar Pro 4 at $0.03 per 1M input tokens and $0.12 per 1M output tokens (vendor list price).
- Which Upstage model has the largest context window?
- Solar Pro 4 accepts 524K tokens of context.
- How do I route to Upstage models with OpenSmartRoute?
- Declare a target in targets.yaml with metadata.model set to the catalogue id (for example upstage/solar-pro4); the router scores it against every other target on cost, quality, latency and your policies for each request.
Route Upstage with everything else
OpenSmartRoute picks the cheapest model that meets your quality bar per request, so a Upstage flagship handles hard prompts while small models take the rest. Price a workload or try a routing decision live.