Rekaai

Reka Flash 3

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...

Context Window
66K tokens
Parameters
21B
Input Price
$0.10/1M
Output Price
$0.20/1M
Price Tier
budget
Provider
Rekaai

How to Use Reka Flash 3

With CoreAI, you can start chatting with Reka Flash 3 instantly — no separate subscription needed. CoreAI lets you chat with Reka Flash 3 alongside 300+ other AI models from Rekaai and other providers like OpenAI, Anthropic, Google, Meta, and more.

  1. Download the CoreAI app for iOS, Android, or use the Web App
  2. Select Reka Flash 3 from the model selector
  3. Start chatting, comparing, or creating with AI

Reka Flash 3 at a Glance

Measured against all 392 chat models CoreAI serves, Reka Flash 3 sits at #355 for context capacity — 66K tokens, roughly 49,152 words or 98 pages of text in a single conversation. On price, it is the #48 cheapest of 128 budget-tier models by input cost. It joined the catalog on 2025-03-12. It supports step-by-step reasoning (thinking mode).

Reka Flash 3 Compared to Its Closest Alternatives

SpecReka Flash 3Reka EdgeAllenAI: Olmo 3 32B ThinkinclusionAI: Ling-2.6-flash
ProviderRekaaiRekaaiAllenaiInclusionai
Input $/1M tokens$0.1$0.1$0.15$0.01
Output $/1M tokens$0.2$0.1$0.5$0.03
Context window66K16K66K262K
Reasoning modeYesNoYesNo
Image inputNoYesNoNo
Price tierbudgetbudgetbudgetbudget

Every model in this table is available on CoreAI — open the web app and run the same prompt through Reka Flash 3 and Reka Edge side by side to judge with your own eyes.

What Reka Flash 3 Actually Costs in Practice

A typical question (about 1,000 tokens in, 500 out) runs $0.00020 on Reka Flash 3's raw per-token rates; a heavy session with a 50K-token document costs about $0.006. On CoreAI you don't juggle these numbers — one subscription covers Reka Flash 3 and 300+ other models under a plan usage limit, with no API keys. See plans.

More Rekaai Models

Rekaai

Reka Edge

Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is
16K budget

Frequently Asked Questions about Reka Flash 3

What is Reka Flash 3's context window?

Reka Flash 3 handles 66K tokens of context — roughly 49,152 words, or about 98 pages of text in one conversation.

How much does Reka Flash 3 cost?

Reka Flash 3's underlying rates are $0.1 per 1M input tokens and $0.2 per 1M output tokens. On CoreAI it is included in one subscription alongside 300+ models, so there is no per-token billing to manage.

Can Reka Flash 3 process images?

No — Reka Flash 3 is text-only. If you need image understanding, its budget-tier peers with vision are listed in the comparison table above.

Does Reka Flash 3 support reasoning or thinking mode?

Yes. Reka Flash 3 can work through problems step by step before answering; on CoreAI you can toggle thinking mode per message.

How can I use Reka Flash 3 without an API key?

Open the CoreAI web app or the iOS/Android app, pick Reka Flash 3 in the model selector, and chat — no API key, no per-token billing. One subscription covers Reka Flash 3 and 300+ other models.

What are the best alternatives to Reka Flash 3?

The closest alternatives on CoreAI are Reka Edge, AllenAI: Olmo 3 32B Think, inclusionAI: Ling-2.6-flash — similar tier and capability. The fastest way to choose is running one prompt through them side by side in CoreAI's Compare view.

Try Reka Flash 3 Now

Chat with Reka Flash 3 and 300+ other AI models — all in one app.

Use Web App Download App →