R
Vendor
Reka 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
$0.11
3:1 input to output per 1M tokens
Strongest
-
no published benchmarks
Every Reka 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 |
|---|---|---|---|---|---|---|
| Reka Edgerekaai/reka-edge | Mar 20, 2026 | 16K | $0.10 | $0.10 | - | reasoning tools open weights |
| Reka Flash 3rekaai/reka-flash-3 | Mar 12, 2025 | 66K | $0.10 | $0.20 | - | reasoning open weights |
Frequently asked
- What is the cheapest Reka model?
- Reka Edge at $0.10 per 1M input tokens and $0.10 per 1M output tokens (vendor list price).
- Which Reka model has the largest context window?
- Reka Flash 3 accepts 66K tokens of context.
- How do I route to Reka models with OpenSmartRoute?
- Declare a target in targets.yaml with metadata.model set to the catalogue id (for example rekaai/reka-edge); the router scores it against every other target on cost, quality, latency and your policies for each request.
Route Reka with everything else
OpenSmartRoute picks the cheapest model that meets your quality bar per request, so a Reka flagship handles hard prompts while small models take the rest. Price a workload or try a routing decision live.