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 32K context length and optimized through reinforcement learning (RLOO), it provides competitive performance comparable to proprietary models within a smaller parameter footprint. Ideal for low-latency, local, or on-device deployments, Reka Flash 3 is compact, supports efficient quantization (down to 11GB at 4-bit precision), and employs explicit reasoning tags ("<reasoning>") to indicate its internal thought process. Reka Flash 3 is primarily an English model with limited multilingual understanding capabilities. The model weights are released under the Apache 2.0 license.
Capabilities
Technical Specs
Pricing
Pay per use, no monthly fees| Billing Type | Unit | Price |
|---|---|---|
| Text Input | — | $0.1000/M tokens |
| Text Output | — | $0.2000/M tokens |
Quick Start
from openai import OpenAI
client = OpenAI(
base_url="https://api.uniontoken.ai/v1",
api_key="YOUR_UNIONTOKEN_API_KEY",
)
response = client.chat.completions.create(
model="rekaai/reka-flash-3",
messages=[
{"role": "user", "content": "Hello!"}
],
)
print(response.choices[0].message.content)FAQ
Related Models
View All → →Ready to get started?
Get 1M free tokens on registration, no monthly fees or minimum spend
Register Now →