Models and pricing

High-quality models at about 30% of standard API pricing

New users get a free cloud computer and $5 worth of credits. Use GPT-6.1-sol and other high-quality models for long-running, multi-step research. Starter is $19/month and includes 60 credits, each covering $1 of usage at standard API prices.

Start researching

Starter

$19/month

60 credits included, about 30% of standard API pricing.

Credits

Model calls

Research results

How it works

Use strong reasoning where it matters

Complex literature decisions, code changes, and experiment diagnosis are handled by high-quality models including GPT-6.1-sol. Model calls do not go through third-party relays, so models are not swapped for cheaper ones.

Long-context research
Complex code and debugging
Multi-round experiment analysis

Credits measured at official prices

1 credit equals $1 of usage at the corresponding provider's standard API prices, so actual usage remains understandable.

$19 monthly plan
60 credits
About 30% of API cost

Spend the budget on more iterations

Research value usually comes from repeated testing and correction. Lower model cost gives the agent room for more useful loops.

Continuous execution
Repeated validation
Reproducible results

Start research with Starter

Start researching

Explore next