Can I run the benchmark myself?

Benchmark 2 lists a harness (prompts and grading rules) among its raw data files, and it was run through the public Model API. With the harness and your own Model API key, you could run the same cases; you'd pay normal per-token prices from your credits (at Benchmark 2's efficiency numbers, 1,000 tasks cost about $1.64 on Flash). Check the Benchmark 2 page for what's available to download.

Good to know#

• Prices per 1M input / output tokens: Flash $1.60 / $3.40, Max $1.80 / $3.80, Heavy $2.00 / $4.40. All prices
• SuperCosmos 1.1 is built to say "I don't know" rather than invent facts. How it's built to be honest
• Line Code was retired on Nov 1, 2026; its ids answer 410 model_retired. Line Code retirement

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.