Hunyuan A13B Instruct is a 13-billion-parameter instruction-tuned language model from Tencent with a 131k-token context window.
- Strengths
- The model balances parameter efficiency with broad language understanding across general reasoning and instruction-following tasks.
- Best for
- Applications where a smaller dense model meets latency and throughput requirements without sacrificing instruction adherence.
- Limitations
- It does not specialize in reasoning, mixture-of-experts architecture, or translation like later Tencent releases, and is superseded by more recent models in the Tencent lineup.
Input / 1M
$0.14
Output / 1M
$0.57
Cached input / 1M
—
Context window
131K
Price history
Snapshots
| Effective | Input | Output | Cached in | Note | Source |
|---|---|---|---|---|---|
| 11 Jun 2026 | $0.14 | $0.57 | — | Imported from OpenRouter | openrouter.ai |