opendunes

Beam 1.0 501B A23B

New

by ReflectionReleased 16 October 2026

Beam 1.0 reads text and writes text, and it keeps about 1,000 pages in mind at once. It thinks before it answers, with an adjustable amount of effort, and is built for coding, long multi-step jobs that use connected tools, and maths and science problems, with a stress on reaching answers economically. You can download it and run it yourself under the Apache 2.0 licence.

TakesText
GivesText
Open in chatCreate API keyCompare

What it costs

You pay for what each request uses. No subscription, no minimum.

≈ 0,27 DA per message3 000 DA buys about 11 000 messages

One message, the ordinary use

1 000 tokens sent× 99,85 DA per 1M0,10 DA
500 tokens back× 332,84 DA per 1M0,17 DA
Total≈ 0,27 DA

Every rate

Meter↑ you send↓ comes back
Text tokens99,85 DA332,84 DA
Cached tokens read13,31 DA

per 1M tokens

Draft and debug a feature end to end, pasting specs and error logs and getting working code≈ 5,66 DA
Summarize a full book-length document with reasoning on, keeping the whole text in the window≈ 21,63 DA
Let the agent plan and execute a multi-hour task, metering every prompt and step it writes≈ 79,88 DA
Refactor a large repository in one pass, sending the full tree and reading back the patched files≈ 109,84 DA
When you pay
After the answer, from your balance. Nothing is held.
Why it varies
A longer question or a longer answer costs more.
After each one
The exact charge shows on the request.
DepositDeposits from 50 DA, with Edahabia or CIB.

Where your request runs

Five companies run this model. OpenDunes sends each request to one of them, picked by price and speed. If it fails, the next one takes it. DA per 1M tokens: ↑ what you send · ↓ what comes back.

Nebius…
↑ Sent, per 1M
83,21 DA
↓ Back, per 1M
332,84 DA
Cache read
16,64 DA
Latency
…
Throughput
…
CoreWeaveUnited States…
↑ Sent, per 1M
99,85 DA
↓ Back, per 1M
332,84 DA
Cache read
13,31 DA
Latency
…
Throughput
…
DigitalOcean…
↑ Sent, per 1M
133,13 DA
↓ Back, per 1M
399,40 DA
Cache read
13,31 DA
Latency
…
Throughput
…
BaseTen…
↑ Sent, per 1M
133,13 DA
↓ Back, per 1M
399,40 DA
Cache read
13,31 DA
Latency
…
Throughput
…
Together…
↑ Sent, per 1M
133,13 DA
↓ Back, per 1M
399,40 DA
Cache read
13,31 DA
Latency
…
Throughput
…
Provider↑ Sent↓ BackCache readLatencyThroughputUptime
Nebius83,21 DA332,84 DA16,64 DA………
CoreWeaveUnited States99,85 DA332,84 DA13,31 DA………
DigitalOcean133,13 DA399,40 DA13,31 DA………
BaseTen133,13 DA399,40 DA13,31 DA………
Together133,13 DA399,40 DA13,31 DA………

You pay the price of the provider that served your request. Prices read 15:48 · speed over the last 30 minutes · uptime over 3 days.

See it in action

Real requests, real replies. Try any of them yourself — one click, pre-filled.

Structured output
You send

Turn this customer email into JSON with intent, urgency and order_id.

customer-email.txt
It replied

{ "intent": "refund", "urgency": "high", "order_id": "OD-58421" }

Try in Chat Lab
Writing
You send

Two lines to welcome a shop in Oran.

It replied

Welcome to our new shop in Oran — fresh bread every morning, and coffee the way the city likes it. Come in, the first cup is on us.

Try in Chat Lab

Try your own request — same model, pre-selected.

Open Chat Lab

Call it in code

Swap the base URL and the key. Your OpenAI code runs unchanged.

POST /v1/chat/completions
Base URL
https://opendunes.com/v1
Model ID
reflection/beam-1.0-501b-a23b
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://opendunes.com/v1",
    api_key=os.environ["OPENDUNES_API_KEY"],
)

resp = client.chat.completions.create(
    model="reflection/beam-1.0-501b-a23b",
    messages=[{"role": "user", "content": "Two lines to welcome a shop in Oran."}],
)

print(resp.choices[0].message.content)
pip install openaiFull reference for this route
Sign in to run it

Runs this request once on your balance.

Parameters you can send

Standard OpenAI fields, grouped by what they control. Anything not listed is accepted and ignored.

Shaping the reply

How long, how varied, where to stop.

max_tokenstemperaturetop_ptop_kmin_pstopseedfrequency_penaltypresence_penaltyrepetition_penaltylogit_biaslogprobstop_logprobs

Reasoning

Let it think before answering — and see the thinking.

reasoningreasoning_effortinclude_reasoning

Structured output

Get JSON you can parse instead of prose.

response_formatstructured_outputs

Tools

Let the model call your functions.

toolstool_choice

Questions about Beam 1.0 501B A23B

  • How much does Beam 1.0 501B A23B cost in dinars?

    About 0,27 DA per message. ↑ 99,85 DA · ↓ 332,84 DA per 1M tokens.

  • Is Beam 1.0 501B A23B free? Can I try it?

    No. You pay per use from your balance, with no subscription. Try it in Chat at the same price.

  • What is Beam 1.0 501B A23B best for?

    Beam 1.0 reads text and writes text, and it keeps about 1,000 pages in mind at once. It thinks before it answers, with an adjustable amount of effort, and is built for coding, long multi-step jobs that use connected tools, and maths and science problems, with a stress on reaching answers economically. You can download it and run it yourself under the Apache 2.0 licence.

  • How do I pay for Beam 1.0 501B A23B without an international card?

    Deposit dinars with your Edahabia or CIB card. Every model, Beam 1.0 501B A23B included, is paid from that balance. No foreign card, no conversion.

  • Does Beam 1.0 501B A23B work in Arabic, French or Darja?

    Reflection names no languages for Beam 1.0 501B A23B. Arabic, French and Darja: not stated.

  • Can it read PDFs, images or a whole book?

    It reads text. Up to 1M tokens in one request, about 1 000 pages. It writes up to 708 000 words at once.

  • Is Beam 1.0 501B A23B open source?

    Yes, its weights are public. Open weights on Hugging Face

  • Who makes Beam 1.0 501B A23B, and when was it released?

    Reflection. Released 16 October 2026. It knows the world up to 30 June 2026.