A 13B parameter model created by merging multiple base models using spherical linear interpolation (SLERP), designed to balance instruction-following with general capability.
- Strengths
- Combines strengths from multiple source models through its merge approach, offering broad capability across both structured tasks and open-ended generation.
- Best for
- Workloads requiring a small model footprint with general-purpose instruction-following and conversation across diverse prompts.
- Limitations
- The 6144-token context window limits handling of long documents or multi-turn conversations with substantial history.
Input / 1M
$0.35
Output / 1M
$0.65
Cached input / 1M
—
Context window
6K
Price history
Input (solid)Output (dashed)
Price change
- 30d
- in — out —
- 90d
- in decreased 22.2% out decreased 0.0%
- 1y
- in decreased 22.2% out decreased 0.0%
- Since launch
- in decreased 22.2% out decreased 0.0%
Snapshots
| Effective | Input | Output | Cached in | Note | Source |
|---|---|---|---|---|---|
| 4 Sep 2026 | $0.35 | $0.65 | — | Imported from OpenRouter | openrouter.ai |
| 11 Jun 2026 | $0.45 | $0.65 | — | Imported from OpenRouter | openrouter.ai |