Beam 1.0 501B A23B
Beam 1.0 501B A23B is an open-weight reasoning model from Reflection for coding and long-horizon agentic workflows. It accepts and generates text, supports tool calling, and has a 1,048,576-token context window.
Beam 1.0 501B A23B specs and pricing
- Provider: Reflection
- Released: October 16, 2026
- Context window: 1M tokens
- Max output: 131K tokens
- Input: text
- Output: text
- Price: $0.25 input / $1.00 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What Beam 1.0 501B A23B is good at
- Coding tasks
- Long-horizon agentic workflows
- Reasoning over long text
To-dos to try with Beam 1.0 501B A23B
- Review this code and suggest fixes for potential bugs.
- Read this long document and summarize its main points.
- Use the available tools to investigate this coding issue and propose a fix.
FAQ
- Who makes Beam 1.0 501B A23B? Reflection makes Beam 1.0 501B A23B. It is an open-weight reasoning model.
- Can Beam 1.0 501B A23B read images? No. It accepts text input and produces text output.
- How much does Beam 1.0 501B A23B cost? Beam 1.0 501B A23B costs $0.25 per million input tokens and $1.00 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 0.84 credits ($1 = 100 credits).
- What is the context window of Beam 1.0 501B A23B? Beam 1.0 501B A23B can read up to 1M tokens at once and write up to 131K tokens in one reply.
- Can I use Beam 1.0 501B A23B without coding? Yes. In todo.is you pick Beam 1.0 501B A23B as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.