Reka Flash 3on Krater.ai
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
Released March 12, 2025
Specifications
Reka Flash 3 at a glance
Context
65.5K tokens
Max output
65.5K tokens
Input
Text
Output
Text
Input price
$0.10 / 1M
Output price
$0.20 / 1M
Knowledge cutoff
2025-01-31
Capabilities
What it is good at
Catalog capabilities
- Generates text responses
- Supports structured outputs
Good for
Compare
Compare Reka Flash 3
Reka Flash 3 vs Reka Edge
Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs.
Open comparisonReka Flash 3 vs DeepSeek V4 Flash 0423
V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window.
Open comparisonReka Flash 3 vs DeepSeek V4 Flash 0731
V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.
Open comparisonFAQ
Questions about Reka Flash 3
Clear answers based on the model catalog and Krater access.
Use Reka Flash 3 in your API
Connect with Krater's unified API.