Qwen3 30B A3B Thinking 2507
by Qwentext->text1 endpoint
Overview
Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces are separated...
Capabilities
Text generation
Tool use / Function calling
Structured output
Extended reasoning
Top-P sampling
Stop sequences
Deterministic seed
Modalities
Input
Text
Output
Text
Technical Specifications
Context Window
81.9K tokens
Max Output
32.8K tokens
Knowledge Cutoff
2025-06-30
Tokenizer
Qwen3
Uptime (24h)
10000.0%
Supported Parameters
frequency_penaltyinclude_reasoningmax_tokenspresence_penaltyreasoningresponse_formatseedstoptemperaturetool_choicetoolstop_ktop_p
Pricing
Per 1M tokens
Input$0.20
Output$2.40
Added
August 28, 2025
Last synced 9/17/2026