DeepSeek-R1-0528-Qwen3-8B

reasoningmit8.2B
Context
131K

Capabilities

Reasoning & Interaction
Tool Calling
Infrastructure
Streaming
Fine-tuning

Details

Model IDdeepseek-ai/DeepSeek-R1-0528-Qwen3-8B
Creator DeepSeek
Family—
Licensemit
Status—
Typereasoning
Input modalitiestext
Output modalitiestext
Open weightYes
Parameters8.2B
Architecturetransformer
Context window131K tokens
Max input—
Max output—
Reasoning tokens—
Knowledge cutoff—
Release date
Sourceofficial

Tools

Function Callingfunction_calling
Call external functions and APIs

API

GET/v1/models/huggingface/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B