Capabilities
7-day heat trend
−19.1%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 32% of tracked models
- Efficiency rank: #442 of 1105
Best suited for
General-purpose text generation, chat, summarization and content workloads where broad capability and low cost matter most.
About sonar-small-online
Sonar Small Online is retained as a legacy Perplexity online-search route for older integrations and catalog migrations.
sonar-small-online is a Text model from Perplexity (US). HotON.ai tracks it at $0.00 per 1M input tokens and $0.00 per 1M output tokens, with a 32K-token context window, ~139 tokens/sec throughput and 97.9% availability. Its composite efficiency score is 89/100 at an estimated $0.000 per successful task.
Compare sonar-small-online
Related market news
Frequently asked questions
How much does sonar-small-online cost per 1M tokens?+
sonar-small-online 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 sonar-small-online best for?+
General-purpose text generation, chat, summarization and content workloads where broad capability and low cost matter most.
How fast is sonar-small-online?+
sonar-small-online delivers about 139 tokens/sec with 97.9% tracked availability, suitable for latency-sensitive, real-time applications.
Is sonar-small-online cheaper than other AI models?+
Within the HotON.ai tracked set, sonar-small-online is cheaper than 43% of models on input price and ranks #442 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.