Underwriting
For merchant underwriting, our top pick is GLM-5.3 from Z.ai. The strongest open-weight model for long agentic runs that chain KYB, sanctions, and internal data. Kimi K3 is a close second, and DeepSeek V4 Pro rounds out the list.
Underwriting agents pull KYB, sanctions, and credit data, review the merchant's website, and draft a decision memo for a human underwriter. Ongoing re-reviews repeat this across the whole portfolio, so long investigations with many tools are the norm.
Updated
The strongest open-weight model for long agentic runs that chain KYB, sanctions, and internal data.
Z.ai's strongest open-weight model, post-trained for complex coding and long-horizon agent work.
Input: text
Harnesses in Runtime
Reads website screenshots and documents natively, useful for spotting fake storefronts.
The first open 3T-class model, natively multimodal with a 1M-token context.
Input: text, image, video
Harnesses in Runtime
Careful reasoning for borderline cases, under an MIT license.
The official DeepSeek V4 Pro release, with stronger agentic skills and an MIT license.
Input: text
Harnesses in Runtime
Turn the steps your team already follows into a skill the agent reads before every run.
Run two or three of these models against past cases. Evals show which one passes at the lowest cost.
The agent works on its own computer in your VPC, with role-based access and an approval before sensitive actions.
For merchant underwriting, our top pick is GLM-5.3 from Z.ai. The strongest open-weight model for long agentic runs that chain KYB, sanctions, and internal data. Kimi K3 is a close second, and DeepSeek V4 Pro rounds out the list.
Long, multi-tool investigations. Reads websites and documents. Clear decision memos with cited evidence. Test two or three candidates against your own past cases before you commit, and keep a human approval on any step that moves money or changes a customer's status.
Yes. Download the weights and serve them with vLLM or SGLang in your own cloud, or use Amazon Bedrock or Google Vertex AI in your account. With Runtime, the agent's computer also runs in your VPC, so card data and PII stay in your environment.
DeepSeek V4 Pro (MIT) is permissive and fine for commercial use. GLM-5.3 (GLM-5.3 License), Kimi K3 (Kimi K3 License) use custom licenses, so read the terms first.
