An 8-billion-parameter language model from IBM's Granite family with a 131K-token context window.
- Strengths
- Handles long-context tasks efficiently while maintaining reasonable inference speed for its size.
- Best for
- Applications requiring extended context windows and moderate reasoning capability without the computational overhead of larger models.
- Limitations
- Superseded by Granite 4.2 8B, which is optimized for multi-step reasoning workloads; for simpler tasks at lower latency, Granite 4.0 Micro offers a smaller alternative.
Input / 1M
$0.05
Output / 1M
$0.1
Cached input / 1M
$0.05
Context window
131K
Price history
Snapshots
| Effective | Input | Output | Cached in | Note | Source |
|---|---|---|---|---|---|
| 11 Jun 2026 | $0.05 | $0.1 | $0.05 | Imported from OpenRouter | openrouter.ai |