Qwen

Qwen3 Coder Next

by Qwentext->text4 endpoints

Overview

Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per...

Capabilities

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

Modalities

Input
Text
Output
Text

Technical Specifications

Context Window
262.1K tokens
Max Output
235.9K tokens
Tokenizer
Qwen
Uptime (24h)
9995.5%

Supported Parameters

frequency_penaltylogit_biaslogprobsmax_tokenspresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

Pricing

Per 1M tokens
Input$0.12
Output$0.80
Cache read$0.07
Added
February 4, 2026
Last synced 9/16/2026