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...

Input Cost
$0.10
per 1M tokens
Output Cost
$0.20
per 1M tokens
Context Window
65,536
tokens
Compare vs GPT-4o
Developer ID: rekaai/reka-flash-3

Related Models

rekaai
$0.10/1M

Reka Edge

Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image...

📝 16,384 ctx Compare →
google
$0.13/1M

Google: Gemma 4 26B A4B

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google Deep...

📝 262,144 ctx Compare →
google
$0.14/1M

Google: Gemma 4 31B

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and...

📝 262,144 ctx Compare →