How much slower is Heavy than Flash?

In Benchmark 2, median time per task was:

Heavy also wrote about 3.6× as many output tokens as Flash per task (median 204 vs 57). Times include some queueing because several requests ran at once. Longer real tasks scale up from there.

Good to know#

• Not sure which tier? auto lets the product choose per step. What auto does
• Insulting or cursing at the assistant earns a warning, then a 24-hour pause on a second strike within 30 days. Abuse policy
• Every tier shares the same 1M-token context window (1,048,576 tokens). Context window

Still need help?#

• General support: support@clatterlabs.com or team@clatterlabs.xyz
• Infrastructure questions, or permanent deletion of your data (your whole account or one service): infrastructure@clatterlabs.xyz

We usually reply within the first hour, and always within 24 hours. A full support team is with you.