Last refreshed 2026-06-29. Next refresh: weekly.
Why use Unisound U2 on Unisound Token Hub?
Unisound Token Hub offers Unisound U2. Unisound Token Hub is Unisound's MaaS platform for text, speech, and vision models.
Setup recipe
Docs fallbackUse the provider REST API or SDKCreate a provider API keymodel: u2u2Request example
u2.Gotchas
- Use provider model ID "u2", not the LLMReference slug "unisound-u2".
Capabilities
About Unisound U2
Unisound U2 is a native agentic large language model announced June 8, 2026, by Chinese AI company Unisound (云知声). Designed for multi-step autonomous task execution, it uses native reasoning-path distillation for task decomposition, execution, verification, and optimization. The official Token Hub page lists a sparse MoE architecture with 266B total parameters and 10B active parameters, plus API access through Unisound Token Hub. Emphasis is on coding, tool orchestration, and long-horizon agent workflows. Unisound self-reports GPQA Diamond 87.9, SWE-bench Verified 75.0, and Claw-Eval 76.9; treat those benchmarks as vendor-reported until independently verified. Context window is not disclosed.