Reflection AI's Beam now available on AI Gateway for free
Quick Answer
Reflection AI's Beam, a low-latency US open-weight reasoning model, is now available for free on AI Gateway during its launch period.
Quick Take
It features a 1M-token context window and efficiently utilizes only 23B of its 501B parameters per token, making it faster than larger models.
Key Points
- Beam supports and structured outputs for coding tasks.
- Access Beam for free using either reflection/beam or reflection/beam-free.
- AI Gateway offers a unified API for model calls and usage tracking.
- No platform fees on inference, including Bring Your Own Key requests.
- Beam is optimized for speed, reaching answers faster than larger models.
DeepSignal Analysis
What happened
Reflection AI's Beam model is now accessible for free on AI Gateway during its launch phase. This model is designed for low-latency reasoning tasks and features a 1M-token context window, utilizing only a fraction of its parameters for efficiency.
Key evidence
- Beam is a low-latency reasoning model with a context window of 1M tokens, optimized for coding and agentic tasks.
- The model activates only 23B of its 501B parameters per token, allowing it to deliver faster responses compared to larger models.
- Users can access Beam for free through two methods: the standard model name or a version with a '-free' suffix, with the latter ceasing after the promotional period.
Why it matters
The introduction of Beam at no cost could enhance accessibility for developers and researchers, potentially accelerating innovation in AI applications. Its efficient parameter usage may also set a new benchmark for performance in reasoning tasks, challenging existing models.
What to watch
Monitor user adoption rates and feedback during the free access period to gauge Beam's impact on the market. Additionally, observe how Reflection AI plans to transition users to paid options after the promotional phase.
📖 Reader Mode
~2 min readBeam from Reflection AI, previously available in stealth as stealth/cat-jam, is now available on 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. Beam supports tool calling and 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
-freesuffix 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:
npx vercel ai-gateway setup
Then select reflection/beam or reflection/beam-free in the agent. See the coding agents guide for details.
Try Beam in the model playground.
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, Zero Data Retention support, budgets for API keys, 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 (BYOK) requests.
— Originally published at vercel.com
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from Vercel AI
See more →
The Agent Stack
The Agent Stack by Vercel AI provides essential building blocks for creating production-grade agents, enabling seamless integration across multiple AI models and secure operations. It features components like AI Gateway for model routing, Workflow SDK for durable execution, and Vercel Connect for scoped access, streamlining agent development and deployment across various platforms.
