Source: https://www.tera.gw/news/live-on-two-gateways Retrieved: 2026-09-29T06:18:19.524Z (page retrieval, not inventory verification) Content SHA-256: aa306c4e0209d1236a392e42e74154f8d99341a6ec5c7259256480c39397321c [← News]() June 25, 2026 Press release # Tera is now live on two LLM gateways Developers can reach Tera's open-model inference through Respan and Merge, with more gateway listings in progress. United States, June 25, 2026. Tera, a U.S.-based provider of open-source model inference, is now listed on two LLM gateways: [Respan]() and [Merge](). Developers building on either platform can route requests to Tera's open models through their existing setup, with no change to their code. Tera serves widely used open-weight models, including Llama, Qwen, DeepSeek, Mistral, and Kimi, through an OpenAI-compatible API. The same models are available directly at [api.tera.gw]() and now through gateway partners that aggregate inference providers for developers. Gateways let developers compare and route across providers from a single integration. By listing on Respan and Merge, Tera meets developers where they already work rather than asking them to adopt a new tool. Most teams reach open models through a gateway today. Being listed where developers already build is the fastest way to put low-cost inference in front of them. Deepak Atyam, Co-founder, Tera Additional gateway listings are in progress. Tera's focus is producing open-model tokens at the lowest cost, then making them available through every channel developers use. About Tera. Tera is a U.S.-based inference provider for open-source large language models, including Llama, Qwen, DeepSeek, Mistral, and Kimi. Tera serves these models through an OpenAI-compatible API and leading LLM gateways, with a focus on producing open-model inference at the lowest cost. The company is built by an operating team with deep experience in industrial-scale compute and data centers. Learn more at tera.gw. Media and partnerships. [deepak@tera.gw]() --- Interactive controls above are described, not submitted. Reading does not reserve capacity or authorize payment. For GPU requirements: https://www.tera.gw/gpu-rentals#capacity-brief