nano

nano is a efficient-tier language model from AssemblyAI. nano is a proprietary model available exclusively through AssemblyAI's API. The AssemblyAI Nano family is AssemblyAI's model series for this capability tier.

nano is priced at $0.1 per hour. This is a speech-to-text model billed per hour rather than per token — token input/output pricing does not apply.

Its 0-token context window is standard for this tier — adequate for most chat and completion tasks, but may require chunking for long-document workloads. Median latency (P50 time-to-first-token) is approximately 800ms — better suited to batch or async workloads where latency is less critical.

nano is best suited to transcription, speed, cost. Supported capabilities include streaming token output for real-time UIs. When evaluating this model for a specific workload, the most important factors are: context window (does your input fit?), output price (how long are your generations?), and latency (is this interactive or batch?). The pricing table above shows how nano compares to similar models across these dimensions.

nano sits in the efficient tier — optimized for speed and cost while maintaining solid quality, ideal for high-volume or latency-sensitive workloads. Unlike open-weights alternatives, nano is only available via AssemblyAI's API — there is no self-hosted option, which simplifies deployment but creates vendor dependency. When comparing nano to alternatives, use the similar models section on this page to find models at comparable price points with different capability tradeoffs. The intelligence score (0/100) reflects aggregate benchmark performance — a useful proxy for general capability, though real-world performance varies significantly by task type. Always test with your specific prompts and use case before committing to a model for production.