Clover 2 is Kitani's 27.8B dense model: a BF16 base with seven LoRA experts and trained per-token routing between them. This variant thinks before answering; tool calling is not available. Its 32,768-token context window is shared by input and output, with up to 8,192 output tokens. Free during its first week, until November 24, 2026 03:33 UTC.Clover 2 Thinking by kitani is currently listed from a single provider. It also has 1 free ($0) channel; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.
The context window is 200,000 tokens, with an output limit of 8,192 tokens. It supports reasoning and tool use.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| NanoGPT kitani/clover-2:thinking | Gateway | Free | — | — | 200,000 | 8,192 |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
1 / 1 providers expose no reasoning control (reasoning_options: []).
This model is $0 across all listed channels (NanoGPT).
Price history accumulates from each data sync; currently only 1 sample(s) (2026-11-17). Each future sync adds a point, and once accumulated a line is drawn here.