Spiral gives your agent every tool with one account. Browse the tools →

Claude Code · LLMReleased 2026-10-16

How to Use Beam 1.0 501B A23B in Claude Code

Beam 1.0 501B A23B is built for coding, reasoning, and tasks that use tools across multiple steps. Its 1M-token context supports working with substantial text, while its English focus makes other languages worth testing first.

Prompts to try with Beam 1.0 501B A23B in Claude Code

Copy an example into Claude Code, or ask in your own words.

Use Beam 1.0 501B A23B to investigate the failing tests in this project. Reproduce one failure, trace its cause, make a focused fix, and run the relevant tests. Report what changed and any remaining failures.

Beam 1.0 501B A23BClaude Code
Try asking
  • Use Beam 1.0 501B A23B to review the current diff for correctness. For each finding, cite the file and line, describe a concrete failure, and suggest a regression test. Skip formatting preferences.

  • Use Beam 1.0 501B A23B to trace this project's authentication flow from request entry to authorization. Cite the relevant files and explain where permissions are checked. Mark any behavior you cannot establish from the code.

  • Use Beam 1.0 501B A23B to diagnose the latest build failure from the available logs and configuration. Rank the likely causes, run checks that distinguish them, and verify any fix with another build.

  • Use Beam 1.0 501B A23B with high reasoning effort to review this project's migration plan. Compare it with the implementation, identify compatibility risks, and propose tests for the riskiest assumptions.

How to set up Beam 1.0 501B A23B in Claude Code

Pick the way that suits you. Each takes about two minutes.

Use Spiral's MCP server

  1. Add the hosted server

    This adds Spiral to the current project. Add --scope user to use it in every project.

    claude mcp add --transport http spiral https://api.spiral.ai/mcp
  2. Sign in

    Start claude, type /mcp, choose spiral and Authenticate. Sign in to Spiral in the browser and click Authorize. No API key.

Use the Spiral skill

  1. Send Claude Code this message

    Your agent reads Spiral's skill and sets itself up.

    set up https://spiral.ai/SKILL.md
  2. Sign in or paste a key

    Approve Spiral in the browser, or give the agent a key from the console.

Use the Spiral CLI

  1. Install and sign in

    Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

    npx -y spiral-cli@latest init

Call the Spiral API

  1. Create an API key

    In the console, under API keys.

  2. Run Beam 1.0 501B A23B

    One request; the result comes back by polling or a webhook.

    curl https://api.spiral.ai/v1/runs \
      -H "Authorization: Bearer $SPIRAL_API_KEY" \
      -H "Content-Type: application/json" \
      -H "Idempotency-Key: $(uuidgen)" \
      -d '{
        "provider": "openrouter",
        "model": "reflection/beam-1.0-501b-a23b",
        "input": {
          "messages": [
            {
              "role": "system"
            }
          ]
        }
      }'

Then paste one of the prompts above: Claude Code finds Beam 1.0 501B A23B on Spiral, shows the price and runs it.

Beam 1.0 501B A23B providers and prices

Spiral runs Beam 1.0 501B A23B through OpenRouter. Open a card for today's price, with every fee included.

OpenRouterLLM
Reflection: Beam 1.0 501B A23B
reflection/beam-1.0-501b-a23b

Settings you can ask for

Ask Claude Code for any of these in your prompt.

SettingAllowed valuesDefaultDescription
Seeda whole number
Min p0 to 1
Top ka whole number from 0
Top p0 to 1
Logprobson or off
Max tokens1 to 943718

The most output tokens to generate.

Temperature0 to 2
Top logprobs0 to 20
Presence penalty-2 to 2
Reasoning effortlow, medium, high, xhigh, or maxmax

How much the model reasons.

Frequency penalty-2 to 2
Repetition penalty0 to 2

Every API field of Reflection: Beam 1.0 501B A23B is on its tool page: open its card above.

What can you do with Beam 1.0 501B A23B in Claude Code?

Beam 1.0 can help turn repository questions and reproducible failures into code changes you can inspect. Give the agent relevant files, expected behavior, and a testable definition of success.

Repair a reproducible bug

Give Beam 1.0 the error, expected behavior, and relevant code. Ask for a focused fix and a regression check tied to the original failure.

Review a proposed code change

Ask Beam 1.0 to examine a patch for behavior changes, missed edge cases, and missing tests. Require each finding to identify the affected code and a concrete failure scenario.

Investigate a terminal failure

Use Beam 1.0 to analyze build output or deployment logs, rank possible causes, and propose commands that distinguish between them.

Explain an unfamiliar code path

Provide relevant source text and ask Beam 1.0 to trace a request from entry point to result, identifying dependencies and unanswered questions.

Summarize technical documents

Ask Beam 1.0 to turn lengthy specifications or incident reports into decisions, unresolved issues, and follow-up work, with supporting passages.

Extract records from text

Have Beam 1.0 convert notes into JSON records with explicit rules for missing values. Check the extracted values against the original text.

Research a technical question with tools

Let Beam 1.0 use the agent's search or retrieval tools to investigate a question. Request a source-backed answer that separates evidence from inference.

Questions about Beam 1.0 501B A23B in Claude Code

Can Claude Code use Beam 1.0 501B A23B?

Yes. Add Spiral to Claude Code as an MCP server, and Claude Code can find and run Beam 1.0 501B A23B like any built-in tool.

How much does Beam 1.0 501B A23B cost in Claude Code?

Up to $0.00534 per run at the default inputs. $0.39 per 1M input tokens, $1.30 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Claude Code plan is separate.

Do I need an OpenRouter account to use Beam 1.0 501B A23B in Claude Code?

No. Spiral runs Beam 1.0 501B A23B on its own OpenRouter account. You sign in to Spiral once and never paste a key.

How long does it take to set up Beam 1.0 501B A23B in Claude Code?

About two minutes: add the hosted server, then sign in.

Does Claude Code wait while Beam 1.0 501B A23B runs?

Beam 1.0 501B A23B runs in the background. Claude Code starts the run, checks on it and gives you the text, json when it's ready.

What is Beam 1.0 best suited for?

Beam 1.0 targets coding, reasoning, and tasks that require several tool calls. Useful starting points include debugging, reviewing code, and investigating questions with retrieved evidence.

How much text can Beam 1.0 handle?

Reflection documents a 1M-token context window and a maximum output of 131,072 tokens. Input and reserved output must fit together, and reasoning consumes part of the output budget.

Can Beam 1.0 interpret screenshots or recordings directly?

Beam 1.0 takes text and returns text. Supply a screenshot's extracted text or a recording's transcript for analysis.

Which languages should I use with Beam 1.0?

Beam 1.0 was developed predominantly for English. Test representative examples before relying on it for work in other languages.

Which settings are a useful starting point?

Reflection recommends temperature 0.7 and top_p 0.99. Use lower reasoning effort for simple requests and higher effort for difficult debugging or planning.

Get started

Start using Beam 1.0 501B A23B in Claude Code

One Spiral account for every tool your agent needs. No subscription; you pay per run.

Paste this into Claude Code:

Set up Claude Code

set up https://spiral.ai/SKILL.md
Are you an AI agent? See setup options