How much does a 500K-token prompt cost?

Scenario: 500,000 tokens in (over 262K, so input bills at 1.5×), 2,000 tokens out.

The long-context rate applies to the whole input once a prompt is over 262K tokens.

How it's calculated: input tokens × input price + output tokens × output price, per 1M tokens, rounded up per call to the next millionth of a dollar. Prices: Flash $1.60 / $3.40, Max $1.80 / $3.80, Heavy $2.00 / $4.40; prompts over 262K tokens bill their whole input at 1.5×. These are estimates from the list prices; Max and Heavy usually write more output tokens than Flash for the same task because they reason first.

See How much does SuperCosmos cost?.

Good to know#

• Not sure which tier? auto lets the product choose per step. What auto does
• Every tier shares the same 1M-token context window (1,048,576 tokens). Context window
• SuperCosmos 1.1 is built to say "I don't know" rather than invent facts. How it's built to be honest

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.