Vendor
IBM Granite 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
$0.08
3:1 input to output per 1M tokens
Every IBM Granite 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 |
|---|---|---|---|---|---|---|
| Granite 4.2 8Bibm-granite/granite-4.2-8b | Aug 31, 2026 | 131K | $0.10 | $0.15 | 14 | reasoning tools open weights |
| Granite 4.0 Microibm-granite/granite-4.0-h-micro | Oct 20, 2025 | 131K | $0.02 | $0.11 | - | open weights |
Frequently asked
- What is the cheapest IBM Granite model?
- Granite 4.0 Micro at $0.02 per 1M input tokens and $0.11 per 1M output tokens (vendor list price).
- Which IBM Granite model has the largest context window?
- Granite 4.2 8B accepts 131K tokens of context.
- How do I route to IBM Granite models with OpenSmartRoute?
- Declare a target in targets.yaml with metadata.model set to the catalogue id (for example ibm-granite/granite-4.2-8b); the router scores it against every other target on cost, quality, latency and your policies for each request.
Route IBM Granite with everything else
OpenSmartRoute picks the cheapest model that meets your quality bar per request, so a IBM Granite flagship handles hard prompts while small models take the rest. Price a workload or try a routing decision live.