Capabilities
7-day heat trend
−7.5%Pricing breakdown
Typical 3:1 output-to-input mix, per 1M tokens
Estimated monthly cost by workload
Market position
- Cheaper than 43% of tracked models
- Faster than 95% of tracked models
- Efficiency rank: #807 of 1105
Best suited for
General-purpose text generation, chat, summarization and content workloads where broad capability and low cost matter most.
About sts-legacy
Resemble Legacy STS is the original speech-to-speech conversion model kept for older voice conversion projects.
sts-legacy is a Text model from Resemble AI (US). HotON.ai tracks it at $0.00 per 1M input tokens and $0.00 per 1M output tokens, with a 1K-token context window, ~171 tokens/sec throughput and 99.4% availability. Its composite efficiency score is 88/100 at an estimated $0.000 per successful task.
Compare sts-legacy
Related market news
Frequently asked questions
How much does sts-legacy cost per 1M tokens?+
sts-legacy is tracked at $0.00 per 1M input tokens and $0.00 per 1M output tokens. A typical 3:1 output-to-input workload blends to roughly $0.00 per 1M tokens. Figures are illustrative demo data.
What is sts-legacy best for?+
General-purpose text generation, chat, summarization and content workloads where broad capability and low cost matter most.
How fast is sts-legacy?+
sts-legacy delivers about 171 tokens/sec with 99.4% tracked availability, suitable for latency-sensitive, real-time applications.
Is sts-legacy cheaper than other AI models?+
Within the HotON.ai tracked set, sts-legacy is cheaper than 43% of models on input price and ranks #807 of 1105 by overall efficiency.
Related models
Pricing is real (via the TestKey catalog, updated daily). Quality (Arena Elo) is real where the model is ranked on LMArena. Speed, availability and efficiency are modeled estimates.