Skip to content

Qwen3-Next-Instruct-T

Pricing

API Pricing (USD)

Type Cost
Request $0.0024/request

Points-based Pricing

Type Cost
Total Cost 80 points/message
Initial Points Cost 80 points

Last Checked: 2025-10-15 16:47:05.829543

Bot Information

Creator: @togetherai

Description: Qwen3-Next Instruct features a highly sparse MoE structure that activates only 3B of its 80B parameters during inference. Supports only instruct mode without thinking blocks, delivering performance on par with Qwen3-235B-A22B-Instruct-2507 on certain benchmarks while using less than 10% training cost and providing 10x+ higher throughput on contexts over 32K tokens.

Extra: Powered by a server managed by @togetherai. Learn more

Architecture

Input Modalities: text

Output Modalities: text

Modality: text->text

Technical Details

Model ID: Qwen3-Next-Instruct-T

Object Type: model

Created: 1759346886115

Owned By: poe

Root: Qwen3-Next-Instruct-T

API Last Updated: 2025-10-15 16:36:09.624969