Run Harbor evals and Terminal-Bench on Vercel Sandbox
You can now run Harbor evaluations, including Terminal-Bench and other benchmarks like SWE-bench and OSWorld, on Vercel Sandbox. Each trial runs in an isolated Firecracker microVM with network policy enforcement and optional credential injection, allowing you to parallelize benchmarking beyond local machine capabilities and test multiple models via AI Gateway.
You can now run Harbor evals on Vercel Sandbox.
is the open-source harness behind , whose registry includes many other benchmarks such as SWE-bench, tau3-bench and OSWorld. Pass to and each trial executes in its own isolated Firecracker microVM, so you can parallelize far beyond what your local machine is capable of. HarborTerminal-Bench--env vercelharbor run
A task's network policy is enforced at the sandbox firewall, outside the VM. Optional credential injection attaches secrets to matching outbound requests at that firewall, so they never enter the sandbox.
Paired with , one reaches hundreds of models from multiple providers, and benchmarking another model is the same command with a different :AI GatewayAI_GATEWAY_API_KEY--model
Swap to to run the same benchmark against an OpenAI model. --modelvercel_ai_gateway/openai/gpt-5.6-luna
Requires Harbor or later. Follow the for setup, configuration, and troubleshooting. Learn more in the .0.22.0step-by-step guideSandbox documentation
Source: original entry ↗
More from Vercel
Follow Vercel to get its new changes in your feed and email digest.
Updates to Hobby and Pro Terms of Service
Vercel is updating Terms of Service for Hobby and Pro customers effective October 19, 2026, clarifying credit policies, managed accounts, auto-renewal practices, and adding statutory cancellation and refund rights for UK and EU consumers, including protections for service changes with negative impact.
Mercury 3 now available on AI Gateway
Inception's Mercury 3 model is now available on Vercel's AI Gateway with 50% launch pricing and generation speeds exceeding 1,000 tokens per second. The model enables parallel text refinement with a 1M-token context window, ideal for real-time applications like browser agents and customer support.
MiniMax M3.1 Flash now available on AI Gateway for free
MiniMax M3.1 Flash, an open-weight multimodal model with 1M-token context window for coding and agentic work, is now available on Vercel's AI Gateway at no cost through October 20. The model excels at complex agent tasks, coding applications, and cybersecurity work, and can be used through multiple APIs and coding agents.