Unknown: 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 ("") 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.
价格
在线时长
性能
使用量与排名
支持的参数
所有提供方:为该模型提供服务的每个上游都支持。部分提供方:取决于处理请求的上游。默认值:未设置时发送的值。
| 参数 | 提供方 | 默认值 |
|---|---|---|
| frequency_penalty | 所有提供方 | 默认不发送 |
| include_reasoning | 所有提供方 | - |
| logprobs | 所有提供方 | - |
| max_tokens | 所有提供方 | - |
| presence_penalty | 所有提供方 | 默认不发送 |
| reasoning | 所有提供方 | - |
| repetition_penalty | 部分提供方 | 默认不发送 |
| seed | 所有提供方 | - |
| stop | 所有提供方 | - |
| structured_outputs | 所有提供方 | - |
| temperature | 所有提供方 | 默认不发送 |
| top_k | 所有提供方 | 默认不发送 |
| top_logprobs | 所有提供方 | - |
| top_p | 所有提供方 | 默认不发送 |