Qwen

Qwen3.8 2.4T A95B (batch)

by Qwentext->text1 endpoint

Overview

Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of Qwen3.8 Max, with 95 billion active parameters out of 2.4 trillion total. It is suited for coding, research, complex reasoning, and agentic workflows.

Capabilities

Text generation
Tool use / Function calling
Structured output
Extended reasoning
Prompt caching
Long context
Top-P sampling
Stop sequences
Log probabilities

Modalities

Input
Text
Output
Text

Technical Specifications

Context Window
1.0M tokens
Max Output
909K tokens
Tokenizer
Qwen

Supported Parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

Pricing

Per 1M tokens
Input$2.00
Output$6.00
Cache read$0.25
Added
August 12, 2026
Last synced 9/18/2026