Turn this customer email into JSON with intent, urgency and order_id.
customer-email.txtReka Flash 3
by RekaaiReleased 12 March 2025
Reka's 21B general model tuned with reinforcement learning, suited to low-latency, local or on-device deployments at down to 11GB in 4-bit, handling chat, coding and function calls, mainly in English
What it costs
You pay for what each request uses. No subscription, no minimum.
One message, the ordinary use
Every rate
| Meter | ↑ you send | ↓ comes back |
|---|---|---|
| Text tokens | 33,28 DA | 66,57 DA |
per 1M tokens
- 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.
Where your request runs
One company runs this model. OpenDunes sends every request to it. DA per 1M tokens: ↑ what you send · ↓ what comes back.
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.
Two lines to welcome a shop in Oran.
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 LabTry your own request — same model, pre-selected.
Open Chat LabCall it in code
Swap the base URL and the key. Your OpenAI code runs unchanged.
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="rekaai/reka-flash-3",
messages=[{"role": "user", "content": "Two lines to welcome a shop in Oran."}],
)
print(resp.choices[0].message.content)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_kstopseedfrequency_penaltypresence_penaltylogprobstop_logprobsReasoning
Let it think before answering — and see the thinking.
reasoninginclude_reasoningStructured output
Get JSON you can parse instead of prose.
structured_outputsQuestions about Reka Flash 3
How much does Reka Flash 3 cost in dinars?
About 0,067 DA per message. ↑ 33,28 DA · ↓ 66,57 DA per 1M tokens.
Is Reka Flash 3 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 Reka Flash 3 best for?
Reka's 21B general model tuned with reinforcement learning, suited to low-latency, local or on-device deployments at down to 11GB in 4-bit, handling chat, coding and function calls, mainly in English.
How do I pay for Reka Flash 3 without an international card?
Deposit dinars with your Edahabia or CIB card. Every model, Reka Flash 3 included, is paid from that balance. No foreign card, no conversion.
Does Reka Flash 3 work in Arabic, French or Darja?
Reka says it is primarily built for English and should be treated as English-only, with some ability in other languages. Arabic, French and Darja are not named.
Can it read PDFs, images or a whole book?
It reads text. Up to 66K tokens in one request, about 65 pages. It writes up to 44 000 words at once.
Is Reka Flash 3 open source?
Yes, its weights are public. Open weights on Hugging Face
Who makes Reka Flash 3, and when was it released?
Rekaai. Released 12 March 2025. It knows the world up to 31 January 2025.
Other Rekaai models, priced in dinars
See all Rekaai modelsReka Edge reads pictures, video and text together and writes back text, in a small model made for image understanding, video analysis, spotting objects and using connected tools. It keeps about 16 pages of conversation in mind at once, so it suits short clips and a few images rather than long documents.