Patronus AI
Digital environment simulation and AI evaluation research. Public model releases are distinguished from hosted services whose exact checkpoints remain unverified.
Current DWM preview API reviewed as one managed component with two routes. Published Glider and Lynx weights excluded. Hosted evaluator versions, historical products and private checkpoint identities remain open.
Start with the job your model needs to do. Then narrow by capabilities, provider and price.
Compare every model with the same request.
Estimate = (input tokens × input price + output tokens × output price) / 1,000,000. Include conversation history in input and billed reasoning in output. Input-only decision models ignore the output setting; enter all billed input for one decision, including its question and criteria. Media, tools and discounts are separate.
1 model
| Compare | Model | Input tokensPublished limit* | Output tokensMaximum per response* | Input pricePer 1M tokens | Output pricePer 1M tokens | Cost per question1,000 input + 500 outputEstimated · uncached |
|---|---|---|---|---|---|---|
| Not collected | Native response contains generated content, optional reasoning, finish_reason and token usage. Chat route returns a ChatCompletion envelope. A response envelope does not guarantee schema-constrained generated content.output formats | Usage pricingNot collected | Task-based pricingPrice details ↗ | |||
* Media models show their native limits. A shared context window includes both input and output tokens.
Catalog coverage
Closed-weight model variants and explicitly identified closed-source managed model components across language, code, image, video, audio and other documented modalities. Global provider and historical-release coverage is being expanded; this is not yet exhaustive. 172 company reviews are still open.
See what is being reviewed