uttapen

Reka Flash 3 API: toman pricing and code

rekaai/reka-flash-3

reasoningjson
Input · per 1M tokens
29,013 toman
Output · per 1M tokens
58,025 toman
One 1,000-word request ≈
113 toman

You are billed for the usage the request actually reported. Prices follow the market.Pricing and top-ups

Reka Flash 3 example: JSON output against a schema

The example is picked from this model's own capabilities. Drop in your key and it runs as is.

from openai import OpenAI
import json

client = OpenAI(base_url="https://api.uttapen.ir/v1", api_key="sk-up-…")

schema = {
    "name": "ticket",
    "schema": {
        "type": "object",
        "properties": {
            "category": {"type": "string", "enum": ["fani", "mali", "forush"]},
            "priority": {"type": "integer", "minimum": 1, "maximum": 5},
            "summary": {"type": "string"},
        },
        "required": ["category", "priority", "summary"],
        "additionalProperties": False,
    },
    "strict": True,
}

resp = client.chat.completions.create(
    model="rekaai/reka-flash-3",
    messages=[{"role": "user", "content": "Ticket: "For two days I cannot download my invoice and I was charged twice.""}],
    response_format={"type": "json_schema", "json_schema": schema},
)
print(json.loads(resp.choices[0].message.content))

What is Reka Flash 3 good for?

Reka Flash 3 is one of Reka's models. Put "rekaai/reka-flash-3" in the model field and the rest of your code stays as it is. Reka Flash 3 keeps 65,536 tokens in view at once, and that number is what caps the conversation history in your product. A single response can run to 58,982 tokens. On price it sits in the "very cheap" band — cheaper than 33 and dearer than 373 of the other paid models in the catalogue.

Capabilities available on this id: it returns schema-valid JSON through response_format, ready to hand to your code; it has a reasoning mode that pays off on multi-step problems, maths and debugging. All of it works through the standard parameters of the official OpenAI SDK — no custom client, no wrapper. Keep in mind that reasoning tokens are output tokens and do appear on the bill.

For a back-of-envelope figure: about 113 toman per 1,000-word exchange (29,013 in, 58,025 out, per 1M tokens). You are always charged for the usage the request actually reported, never for the estimate, and a failed request costs nothing.

The closest alternative with the same capabilities from a different provider is gpt-oss-20b (batch): Reka Flash 3 works out roughly 1.2× more expensive, and its context window is smaller. Both run on the same key and the same code, so trying the other one is a single string change.

To make the figure concrete: 100,000 toman of credit buys roughly 885 thousand-word requests on Reka Flash 3, and every 1,000 toman is about 8,850 words of round trip. A job with one million input tokens and one million output tokens comes to 87,038 toman in total. Filling this model's 65,536-token window costs 1,901 toman on the input side alone, which is the real reason to keep conversation history short.

Reka has 2 models in our catalogue; the cheapest is Reka Edge at 75 toman per thousand words and the dearest Reka Flash 3 at 113. Among the less common parameters it accepts logprobs, top_k, top_logprobs — all through the standard request body. It does not support response_format, tool_choice, tools, which most models here do, so test before switching if your code relies on them. By context size the nearest option from another provider is Nano Banana Pro (Gemini 3 Pro Image Preview) at 65,536 tokens.

What to use it for: high-volume work such as classification, tagging and bulk summarising, logic puzzles and code review, extracting data against a fixed schema.

Provider's own description

Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka. It excels at general chat, coding tasks, instruction-following, and function calling. Featuring a...

Three real jobs, priced on this model

Each figure is derived from the prices above and moves when they do.

JobTokensCost
One chat turn with a medium history1,500 in + 400 out67 toman
Summarising a ten-page document4,000 in + 600 out151 toman
Classifying a thousand short rows120,000 in + 20,000 out4,642 toman

Frequently asked

How do I call Reka Flash 3 from Iran?
Sign up with your mobile number, top the wallet up in toman, create an API key, then in the official OpenAI SDK point base_url at https://api.uttapen.ir/v1 and set model to "rekaai/reka-flash-3". Nothing else in your code changes.
What does Reka Flash 3 cost in toman?
29,013 toman per 1M input tokens and 58,025 toman per 1M output tokens; a 1,000-word request is around 113 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
How much input does Reka Flash 3 take?
Up to 65,536 tokens per request, roughly 49k words. A single answer can reach 58,982 tokens.
Can I stream Reka Flash 3's output?
Yes — with stream=true you get SSE events as the tokens are produced. This model has no tool calling and no image input, so pick a different one if you need either.