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.
rekaai/reka-flash-3
- Context
- 66k tokens
- Completion cap
- 65,536
- Tools
- No
- JSON
- Yes
- Released
- 2025-03-12
Call it from Geek Hub
Same OpenAI SDK. Change the base URL and the model id.
curl https://api.geekhub.mx/v1/chat/completions \
-H "Authorization: Bearer $GEEKHUB_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "rekaai/reka-flash-3",
"messages": [{"role": "user", "content": "Hola"}]
}'Frequently asked questions
- What is 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. Reka Flash 3 runs on the Geek Hub API (OpenAI-compatible). Model id: rekaai/reka-flash-3.
- Is Reka Flash 3 free?
- No. Input is $0.109 per 1M tokens and output is $0.218 per 1M tokens on Geek Hub (markup included).
- What is the context length of Reka Flash 3?
- Reka Flash 3 has a 66k tokens context window. It supports up to 65,536 completion tokens.
- Does Reka Flash 3 support tool calling and structured outputs?
- Reka Flash 3 does not advertise tool calling on this endpoint. It also supports structured outputs via a JSON schema in response_format.
- When was Reka Flash 3 released?
- Reka Flash 3 was released on 2025-03-12.