Unisound Token Hub
Researched 81d agoAI LabUnisound
Unisound Token Hub offers 1 tracked model (0 with output token pricing). This catalog covers coding, agents, and json / tool use; open any model detail page for benchmarks, batch tiers, and migration prompts.
Covers 3 workload areas across 1 tracked model; last verified 2026-06-29.
Use it for
- Operators routing coding, agents, and json / tool use workloads through this API
Do not use it for
- Final benchmark picks without opening the relevant model detail page
- Strict price-per-token comparisons until output pricing is sourced
Tracked models
1
Models available through this provider
Priced output routes
0
Output pricing not yet tracked
Cheapest output
Unknown
Output pricing not yet tracked
Batch-ready models
0
No batch pricing tracked
Latest model release
2026-06-08
102d since newest release
Freshness
2026-06-29
Researched 81d ago
Information
Unisound Token Hub is Unisound's MaaS platform for text, speech, and vision models. Its text-generation API exposes Unisound U2 through OpenAI-compatible and Anthropic-compatible endpoints.
Links
WebsiteWhere this host wins
- Coding: 1 tracked model with SWE-bench / HumanEval-style scores.
- Agentic: 1 tracked model with BFCL, tau-bench, and SWE-bench tool-use coverage.
- JSON/tool-use: 1 tracked model with BFCL / Nexus strict-JSON routing coverage.
Getting started
Platform Overview
Unisound Token Hub provides API access to Unisound's U2 text-generation model plus related speech and vision models. The OpenAI-compatible chat endpoint uses model code u2, supports streaming, function calling, and reasoning output, and lists pay-as-you-go pricing in CNY per 1M tokens.