reflection
Reflection: Beam 1.0 501B A23B
Try in chat →Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows. It uses a sparse mixture-of-experts architecture with 501B total and 23B active parameters per token, and a...
Context
1M tokens
Input / 1M tokens
$0.28
Output / 1M tokens
$1.10
Benchmark
—
Uptime & performance
Loading…
Pricing
Input tokens$0.28 per 1M tokens
Output tokens$1.10 per 1M tokens
Cache read$0.06 per 1M tokens
Apps and activity
Loading…
Technical details
Model IDreflection/beam-1.0-501b-a23b
Context window1M tokens
Input modalitiestext
Output modalitiestext
TokenizerOther
Max output tokens131,072
Use with MegaBrain
import OpenAI from 'openai'
const client = new OpenAI({
baseURL: 'https://getmegabrain.com/api/gateway/v1',
apiKey: process.env.MEGABRAIN_API_KEY,
})
const response = await client.chat.completions.create({
model: 'reflection/beam-1.0-501b-a23b',
messages: [{ role: 'user', content: 'Hello!' }],
})Ready to use Reflection: Beam 1.0 501B A23B?
Try it in the browser first, then get an API key and start making requests in minutes.