Qwen: Qwen3 4B (free) reasoning
Qwen3-4B is a 4 billion parameter dense language model from the Qwen3 series, designed to support both general-purpose and reasoning-intensive tasks. It introduces a dual-mode architecture—thinking and non-thinking—allowing dynamic switching between high-precision logical reasoning and efficient dialogue generation. This makes it well-suited for multi-turn chat, instruction following, and complex agent workflows.
Capabilities
Context Window 40k tokens
Max Output 0 tokens
Inputs
Outputs
Pricing (per 1M tokens)
Input $-
Output $-
Cache Read -
Cache Write -
Supported Parameters
frequency_penaltyinclude_reasoningmax_tokenspresence_penaltyreasoningresponse_formatstopstructured_outputstemperaturetool_choicetoolstop_ktop_p