Runtime as featured inForbesRead the article
All open source models

Risk and fraud

The best open source models for chargebacks and disputes

For chargebacks and disputes, our top pick is MiniMax M3 from MiniMax. Reads text, images, and video with a 1M-token context, so a whole dispute file fits in one run. Kimi K3 is a close second, and GLM-5.3 rounds out the list.

Dispute agents gather delivery proof, order history, customer messages, and screenshots, then assemble an evidence packet before the network deadline. That means mixed inputs, long context, and careful writing.

Updated

What matters for chargebacks and disputes

  • Image input for receipts and screenshots
  • Long context for full order histories
  • Clear, structured writing for evidence packets

Our picks

1MiniMax logo

MiniMax M3

MiniMax · MiniMax Community License

Reads text, images, and video with a 1M-token context, so a whole dispute file fits in one run.

A natively multimodal model with sparse attention built for million-token contexts.

Context1M tokens
Parameters428B
Active23B

Input: text, image, video

Harnesses in Runtime

Claude CodeOpenCodeCline
2Moonshot AI logo

Kimi K3

Moonshot AI · Kimi K3 License

The most capable multimodal open model for complex, document-heavy cases.

The first open 3T-class model, natively multimodal with a 1M-token context.

Context1M tokens
Parameters2.8T

Input: text, image, video

Harnesses in Runtime

Claude CodeOpenCodeCline
3Z.ai logo

GLM-5.3

Z.ai · GLM-5.3 License

Strong at long, multi-tool runs that pull from the processor, shipping data, and the help desk.

Z.ai's strongest open-weight model, post-trained for complex coding and long-horizon agent work.

Context1M tokens
Parameters753B

Input: text

Harnesses in Runtime

Claude CodeOpenCodeCline

Put a chargebacks and disputes agent to work

01

Write the SOP as a skill

Turn the steps your team already follows into a skill the agent reads before every run.

02

Pick and test the model

Run two or three of these models against past cases. Evals show which one passes at the lowest cost.

03

Run it in your cloud

The agent works on its own computer in your VPC, with role-based access and an approval before sensitive actions.

Questions about models for chargebacks and disputes

What is the best open source model for chargebacks and disputes?

+

For chargebacks and disputes, our top pick is MiniMax M3 from MiniMax. Reads text, images, and video with a 1M-token context, so a whole dispute file fits in one run. Kimi K3 is a close second, and GLM-5.3 rounds out the list.

What matters when choosing a model for chargebacks and disputes?

+

Image input for receipts and screenshots. Long context for full order histories. Clear, structured writing for evidence packets. 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.

Can I run an open source model for chargebacks and disputes without sending data to a third party?

+

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.

Which of these models can I use commercially?

+

MiniMax M3 (MiniMax Community License), Kimi K3 (Kimi K3 License), GLM-5.3 (GLM-5.3 License) use custom licenses, so read the terms first.