Qwen3.5-397B-A17B

Native multimodal model with efficient hybrid architecture for global deployment.

About model

Qwen3.5 is a native vision-language foundation model with 397B total parameters (17B activated) using sparse MoE architecture. Through early fusion training on multimodal tokens, Qwen3.5 achieves cross-generational parity with Qwen3 while outperforming Qwen3-VL models across reasoning, coding, agents, and visual understanding benchmarks. The model features Gated Delta Networks combined with sparse Mixture-of-Experts, delivering 8.6x-19x faster decoding than Qwen3-Max with minimal latency overhead. Reinforcement learning scaled across million-agent environments enables robust real-world adaptability, while expanded support to 201 languages and dialects enables inclusive worldwide deployment on Together AI's production infrastructure.

Total Parameters (17B activated)

397B

Native multimodal MoE architecture

Faster Decoding

8.6-19x

Hybrid Gated Delta Networks vs Qwen3-Max

Languages & Dialects

201

Global deployment with cultural understanding

Model key capabilities

Native Multimodal Foundation: Early fusion training across text, images, and video—87.8% MMLU-Pro, 88.6% MathVision, 87.5% VideoMME
Hybrid Efficiency: Gated Delta Networks + sparse MoE delivering 8.6-19x faster decoding with 17B activated parameters
Global Multilingual: 201 languages and dialects—88.5% MMMLU, 78.9% WMT24++ across 55 languages
Production-Ready Infrastructure: 99.9% SLA, available on serverless and dedicated infrastructure

Quickstart guides

Agents

How to Build Coding Agents

RAG

Building a RAG Workflow

Integrations

Using Together with Vercel's AI SDK

API usage

cURL
Python
Typescript

Endpoint:

Qwen/Qwen3.5-397B-A17B

curl -X POST https://api.together.xyz/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $TOGETHER_API_KEY" \
  -d '{
    "model": "Qwen/Qwen3.5-397B-A17B",
    "messages": [{
      "role": "user",
      "content": "Given two binary strings `a` and `b`, return their sum as a binary string"
    }]
  }'

from together import Together

client = Together()
response = client.chat.completions.create(
  model="Qwen/Qwen3.5-397B-A17B",
  messages=[
  	{
	    "role": "user", 
      "content": "Given two binary strings `a` and `b`, return their sum as a binary string"
    }
 ],
)

print(response.choices[0].message.content)

import Together from "together-ai";

const together = new Together();

async function main() {
  const response = await together.chat.completions.create({
    model: "Qwen/Qwen3.5-397B-A17B",
    messages: [{
      role: "user",
      content: "Given two binary strings `a` and `b`, return their sum as a binary string"
    }]
  });
  
  console.log(response.choices[0]?.message?.content);
}

main();

Model card
Architecture Overview:
• Native vision-language foundation model with early fusion training on multimodal tokens
• 397B total parameters with 17B activated per forward pass via sparse MoE routing
• 512 experts with 10 routed + 1 shared expert activated per token
• Hybrid architecture: Gated Delta Networks + sparse Mixture-of-Experts
• 60 layers with 15 × (3 × (Gated DeltaNet → MoE) → 1 × (Gated Attention → MoE)) layout
• Gated DeltaNet: 64 linear attention heads for V, 16 for QK, head dimension 128
• Gated Attention: 32 heads for Q, 2 for KV, head dimension 256, RoPE dimension 64
• 248,320 token vocabulary (padded) with 15-25% lower token counts on technical datasets
• 256K native context (262,144 tokens), extensible to 1M tokens via YaRN scaling
• High-resolution vision: up to 1344x1344 pixels, UI screenshots with pixel-perfect element detection

Training Methodology:
• Early fusion multimodal training achieving near-100% efficiency vs text-only training
• Reinforcement learning scaled across million-agent environments with progressively complex task distributions
• Asynchronous RL frameworks supporting massive-scale agent scaffolds and environment orchestration
• Trained for robust real-world adaptability across reasoning, coding, agents, and visual understanding
• 201 languages and dialects with nuanced cultural and regional understanding
• Multi-token prediction (MTP) training for enhanced inference efficiency

Performance Characteristics:
• Reasoning Excellence: 87.8% MMLU-Pro, 91.3% AIME26, 83.6% LiveCodeBench v6, 88.4% GPQA
• Coding Leadership: 76.4% SWE-Bench Verified, 69.3% SWE-Bench Multilingual, 68.3% SecCodeBench
• Agentic Performance: 69.0/78.6% BrowseComp, 74.0% WideSearch, 72.9% BFCL-V4, 86.7% TAU2-Bench
• Multilingual SOTA: 88.5% MMMLU, 84.7% MMLU-ProX (29 languages), 78.9% WMT24++ (55 languages)
• Vision Language: 88.6% MathVision, 90.3% MathVista, 85.0% MMMU, 79.0% MMMU-Pro
• Video Understanding: 87.5% VideoMME (w/ sub), 84.7% VideoMMMU, 86.7% MLVU
• Document Understanding: 90.8% OmniDocBench1.5, 93.1% OCRBench, 82.0% CC-OCR
• Efficiency: 8.6x-19x faster decoding vs Qwen3-Max at 32k-256k context lengths
‍
Applications & use cases
Native Multimodal Reasoning:
• Vision-language foundation with early fusion training across text, image, and video
• 87.8% MMLU-Pro, 91.3% AIME26, 83.6% LiveCodeBench v6, 88.4% GPQA Diamond
• Math vision: 88.6% MathVision, 90.3% MathVista (mini), 87.9% We-Math
• High-resolution image understanding: up to 1344x1344 pixels, UI element detection
• Video understanding: 87.5% VideoMME (w/ subtitles), 84.7% VideoMMMU, 86.7% MLVU
• Document processing: 90.8% OmniDocBench1.5, 93.1% OCRBench, 82.0% CC-OCR

SOTA Coding & Agentic Performance:
• Autonomous coding: 76.4% SWE-Bench Verified, 69.3% SWE-Bench Multilingual, 68.3% SecCodeBench
• Agentic workflows: 69.0/78.6% BrowseComp, 74.0% WideSearch, 86.7% TAU2-Bench
• Tool orchestration: 72.9% BFCL-V4, 38.3% Tool Decathlon, 46.1% MCP-Mark
• Visual agents: 65.6% ScreenSpot Pro, 62.2% OSWorld-Verified, 66.8% AndroidWorld
• Search with tools: 48.3% HLE w/ tool, 70.3% BrowseComp-zh

Global Multilingual Deployment:
• 201 languages and dialects with nuanced cultural and regional understanding
• Multilingual excellence: 88.5% MMMLU, 84.7% MMLU-ProX (29 languages)
• Translation quality: 78.9% WMT24++ across 55 languages using XCOMET-XXL
• Cross-lingual reasoning: 59.1% NOVA-63, 85.6% INCLUDE, 89.8% Global PIQA
• Multilingual math: 73.3% PolyMATH, 88.2% MAXIFE across 23 settings
• Instruction following: 76.5% IFBench, 67.6% MultiChallenge across languages

Production Efficiency at Scale:
• 8.6x-19x faster decoding than Qwen3-Max at 32k-256k context lengths
• Hybrid Gated Delta Networks architecture with minimal latency overhead
• 397B total parameters with only 17B activated per token via sparse MoE
• 256K native context (262,144 tokens), extensible to 1M via YaRN RoPE scaling
• Multi-token prediction (MTP) for enhanced inference throughput
• 248,320 token vocabulary reducing token counts 15-25% on technical datasets

Visual Agentic Workflows:
• Desktop screenshot understanding with UI element identification and workflow planning
• Pixel-perfect element detection for UI automation and testing
• Executable action generation for autonomous task completion
• Native tool calling for web search, code execution, and API orchestration
• Visual agents: 65.6% ScreenSpot Pro, 62.2% OSWorld-Verified, 66.8% AndroidWorld

Long-Context Knowledge Work:
• 256K native context supporting entire codebases, video transcripts, technical reports
• Extensible to 1M tokens for processing hour-scale videos and massive documents
• Long-context benchmarks: 63.2% LongBench v2, 68.7% AA-LCR
• Document understanding: 90.8% OmniDocBench1.5 with long-form comprehension
• Eliminates chunking for large-scale technical documentation and research

Thinking Mode for Complex Reasoning:
• Default thinking mode generates step-by-step reasoning before final responses
• Enhanced performance on math competitions (91.3% AIME26), coding challenges (83.6% LiveCodeBench)
• Disableable for direct responses in conversational or low-latency applications
• Configurable via API parameters without model changes
• Optimal for complex problem-solving, mathematical proofs, algorithm design
‍

Related models

Model specifications

Model data

Model provider
Qwen
Type
Code
Chat
Main use cases
Function Calling
Vision
Features
Function Calling
JSON Mode
Speed
Medium
Intelligence
Very High
Deployment
Serverless
Monthly Reserved
Endpoint
Qwen/Qwen3.5-397B-A17B
Parameters
403.4B
Context length
256K
Input price
$0.60 / 1M tokens
Output price
$3.60 / 1M tokens
Input modalities
Text
Image
Output modalities
Text

Released
February 15, 2026
Last updated
February 15, 2026
Quantization level
FP4
External link
Provider docs
Category
Code

Run in Playground

Quickstart docs

Deploy model

Qwen3.5-397B-A17B

About model

API usage

Model card

Applications & use cases