Reka Flash 3
Reka Flash 3 is a 21-billion parameter, instruction-tuned language model developed by Reka. It is designed for general-purpose chat, coding, and instruction-following tasks. The model supports reasoning capabilities and handles text-based inputs and outputs.
Reka Flash 3 specs and pricing
- Provider: rekaai
- Released: March 12, 2025
- Context window: 66K tokens
- Max output: 59K tokens
- Input: text
- Output: text
- Price: $0.10 input / $0.20 output per 1M tokens
- Reasoning: yes
What Reka Flash 3 is good at
- General conversational assistance
- Writing and debugging code
- Following complex instructions
To-dos to try with Reka Flash 3
- Draft a Python script to automate a repetitive data entry task
- Write a detailed response to a complex customer support inquiry
- Explain the logic behind a specific programming error in a provided snippet
FAQ
- Who developed Reka Flash 3? Reka Flash 3 was developed by Reka.
- What types of tasks is this model designed for? The model is built for general chat, coding tasks, and following specific instructions.
- How much does Reka Flash 3 cost? Reka Flash 3 costs $0.10 per million input tokens and $0.20 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 0.31 credits ($1 = 100 credits).
- What is the context window of Reka Flash 3? Reka Flash 3 can read up to 66K tokens at once and write up to 59K tokens in one reply.
- Can I use Reka Flash 3 without coding? Yes. In todo.is you pick Reka Flash 3 as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.