Does Beam 1.0 support zero data retention?

No. The routes serving Beam 1.0 retain content; see the per-route data-handling section for each route's logging stance and retention window.

Where is Beam 1.0 hosted?

See the per-route table for Beam 1.0 hosting locations and residency details.

Is Beam 1.0 trained on prompts and outputs?

No. Every hosting route for Beam 1.0 is configured so customer prompts and outputs are not used to train models by default.

Is a GDPR DPA available for Beam 1.0?

Yes. A GDPR Data Processing Agreement is available on at least one route serving Beam 1.0. Contact hello@opper.ai to receive it.

Beam 1.0

by Reflection

Beam 1.0 is the first open-weight model from Reflection, generally available since October 16, 2026 after an early-access period. It is a sparse mixture-of-experts text model with 501B total parameters and about 23B active per token: 52 layers (3 dense and 49 mixture-of-experts) over 256 experts, with gated grouped-query attention and sliding-window layers. Reflection built Beam for software engineering, agentic tool use and math and science reasoning, with an emphasis on token efficiency: it reports quality comparable to leading open models with about a third of the reasoning tokens. Beam always reasons before it answers, at an effort from low to max, and supports tool calling and structured outputs. Its context window is 1M tokens with up to 128K output tokens, and its knowledge cutoff is June 30, 2026. The weights are released under Apache 2.0 in BF16, FP8 and NVFP4, with a model card and a separate safety technical report. Beam was developed predominantly for English.

Call Beam 1.0 on Opper with the OpenAI SDK. Sign up without a credit card. Get started

Get your API key Try in chat Compare

Key info

Input

Output

Features

Context window

Max output

131K

Input price

$0.25 /1M

Output price

$1.00 /1M

No training by default
GDPR DPA available

Available routes

Beam 1.0 runs on 1 route through the Opper gateway. Compare residency, zero data retention and training posture at a glance, with full data-handling detail per route below.

Provider	Region	Zero data retention	Training	Input	Output	Cache read
Nebius	Multi		No	$0.25	$1.00	Input price

Live routes and prices as JSON: api.opper.ai/v3/models?q=nebius%2Freflection%2Fbeam

Uptime and availability

Beam 1.0 runs on a single route through the Opper gateway today, so its availability is that provider's availability.

78.68%route uptime, last 30 days

Single route, no failover target within this model.

Name a second model in the same request and the gateway tries it on retriable errors, so a busy hour never has to reach your users. Set up a fallback chain.

Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. See uptime for every provider Opper monitors.

Data handling per route

Each route hosting Beam 1.0 has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

Nebius — Multi-region

Content is retained: provider logging. No training on customer data. GLOBAL; SCCs; DPA available.

Zero data retention: Retained: provider logging.
Training: No training on customer data.
Logging: Other
Abuse monitoring: No classifier
GDPR DPA: DPA available
Transfer mechanism: SCCs

Get started

Call Beam 1.0 through the Opper gateway with one API key. Opper is drop-in compatible with the OpenAI, Anthropic and Google AI SDKs.

Beam 1.0 is a premium model on Opper. Sign up needs no credit card: you get an API key straight away and the free models work in the playground and the API. Add a card to use premium models, pay-as-you-go with no minimum.

Set it up with your agent

Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up Opper for you.

Or call it directly

1import OpenAI from "openai";
2
3const client = new OpenAI({
4  apiKey: process.env.OPPER_API_KEY,
5  baseURL: "https://api.opper.ai/v3/compat",
6});
7
8const completion = await client.chat.completions.create({
9  model: "nebius/reflection/beam",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);