Beam 1.0 is an open-weight reasoning model developed by Reflection. It is built to handle complex coding tasks and long-horizon agentic workflows through a sparse mixture-of-experts architecture.
The model is designed to reason before providing answers, ensuring high-quality outputs. It supports tool calling and structured data generation to integrate seamlessly into technical environments.
The model is architected to reason before answering to improve output quality.
Native support for tool calling allows the model to interact with external systems.
The model is capable of generating structured outputs for programmatic use.
It operates over a 1M-token context window to manage extensive information.
Developing complex software applications through automated coding assistance.
Managing long-horizon agentic workflows that require multi-step reasoning.
Extracting and formatting data into structured outputs for downstream processing.
Interacting with external tools to execute multi-stage technical tasks.
import requests r = requests.post( "https://api.aimlapi.com/v1/chat/completions", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "reflection/beam-1.0-501b-a23b", "messages": [ { "role": "user", "content": "Hello!" } ] }, ) print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/chat/completions", { method: "POST", headers: { Authorization: `Bearer ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ "model": "reflection/beam-1.0-501b-a23b", "messages": [ { "role": "user", "content": "Hello!" } ] }), }); console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/chat/completions \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"reflection/beam-1.0-501b-a23b","messages":[{"role":"user","content":"Hello!"}]}'
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
Billed per token: $0.34385 / 1M input tokens and $1.3754 / 1M output tokens. Reasoning tokens are billed as output.
Developing complex software applications through automated coding assistance.
Managing long-horizon agentic workflows that require multi-step reasoning.
Extracting and formatting data into structured outputs for downstream processing.
Interacting with external tools to execute multi-stage technical tasks.
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Beam 1.0 501B A23B This page | Coding and long-horizon agentic workflows | |||
| Agentic workflows and structured output | ||||
| Reasoning + agents | ||||
| Agentic workflows and structured output | ||||
| High-throughput chat & agents |
Beam 1.0 501B A23B costs $0.34385 / 1M tokens for input and $1.3754 / 1M tokens for output on AI/ML API.
The model supports a 1M-token context window.
Yes, the model includes native support for tool calling.
It is a sparse mixture-of-experts model with 501B total and 23B active parameters.
Yes, structured output generation is a core capability of this model.