Reflection AI's Beam now available on AI Gateway for free

Reflection AI's Beam, a low-latency US open-weight reasoning model for coding and agentic tasks, is now available on Vercel's AI Gateway and free to use for a limited launch period. Beam activates only 23B of its 501B parameters per token, supports tool calling and structured outputs, and offers a 1M-token context window with adjustable reasoning effort, with weights released under Apache 2.0. Developers can access it as reflection/beam, which transfers to paid pricing after the free period, or reflection/beam-free, which stops serving when the offer ends.

Beam from Reflection AI https://vercel.com/ai-gateway/models/beam , previously available in stealth as stealth/cat-jam , is now available on AI Gateway https://vercel.com/ai-gateway . Beam is free to use for a limited time during the launch period. Beam is an low latency US open-weight reasoning model for coding and agentic tasks, with weights released under Apache 2.0 https://reflection.ai/blog/beam-is-available . Beam supports tool calling https://vercel.com/docs/ai-gateway/sdks-and-apis/responses/tool-calling and structured outputs https://vercel.com/docs/ai-gateway/sdks-and-apis/openai-chat-completions/structured-outputs , with a 1M-token context window for code, documents, and conversation history. Reasoning effort is adjustable. Beam is designed for speed, activating only 23B of its 501B parameters per token and avoiding tokens a task doesn't need, so it tends to reach answers sooner than larger open models. There are 2 ways to access Beam for free: Using the standard model name reflection/beam . When the free period ends, the model slug will automatically transfer over to pricing with no downtime. Using the -free suffix to the standard name reflection/beam-free . The model will stop serving when the free offer ends. To use it in Claude Code, Codex, Cursor, and more, install the latest Vercel CLI and run setup: Then select reflection/beam or reflection/beam-free in the agent. See the coding agents guide https://vercel.com/docs/ai-gateway/coding-agents for details. Try Beam in the model playground https://vercel.com/ai-gateway/models/beam . AI Gateway provides a unified API for calling models, tracking usage and cost, and configuring retries, failover, and performance optimizations for higher-than-provider uptime. It includes built-in custom reporting https://vercel.com/changelog/custom-reporting-ai-gateway , Zero Data Retention support https://vercel.com/blog/zdr-on-ai-gateway , budgets for API keys https://vercel.com/docs/ai-gateway/authentication-and-byok/api-keys , routing rules https://vercel.com/docs/ai-gateway/models-and-providers/routing-rules , and more. AI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference, including on Bring Your Own Key https://vercel.com/docs/ai-gateway/authentication-and-byok/byok BYOK requests.