Qwen3.6 35B A3B | Qwen Multimodal LLM API Pricing

Name: Qwen3.6 35b A3b API
Brand: qwen
Price: 0.25 USD
Availability: InStock

Uso da API

Use os exemplos de código abaixo para integrar com nossa API:

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://llm.wavespeed.ai/v1"
)

response = client.chat.completions.create(
    model="qwen/qwen3.6-35b-a3b",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)

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

Introdução do modelo

Qwen: Qwen3.6 35B A3B

Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35B total parameters and 3B active parameters per token. It uses a hybrid sparse Mixture-of-Experts architecture combining Gated DeltaNet linear attention with standard attention layers, giving it strong efficiency for coding, agentic workflows, long-context reasoning, and multimodal understanding.

Why It Looks Great

Open-weight 35B sparse MoE model with only 3B active parameters per token
Hybrid architecture combining Gated DeltaNet linear attention, standard attention, and MoE feed-forward layers
Native multimodal support for text, image, and video understanding
262K-token context window for long prompts, large documents, codebases, and multi-turn workflows
Efficient active-parameter design for cost-sensitive production inference
Supports both thinking and non-thinking modes for flexible latency and reasoning trade-offs
Function calling and tool-use support for agentic application workflows
Structured output support for JSON responses and schema-constrained generation

Key Features

Total Parameters: 35B
Active Parameters: 3B per token
Architecture: Sparse Mixture-of-Experts
Context Window: 262,144 tokens
Max Input: Not listed
Max Output: Not listed
Input: Text, Image, Video
Output: Text
Vision: Supported
Function Calling: Supported
Structured Outputs: Supported
Thinking Mode: Supported
Audio Input: Not listed
Image Generation: Not listed
Supported Parameters: frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p

Specifications

Specification	Value
Provider	alibaba
Model Type	Chat Completions model
Architecture	Sparse MoE, 35B total / 3B active
Attention	Gated DeltaNet + standard attention
Modalities	text+image+video->text
Context Window	262,144 tokens
Max Input	Not listed
Max Output	Not listed
Input	Text, Image, Video
Output	Text
Vision	Supported
Function Calling	Supported
Structured Outputs	Supported
Thinking Mode	Supported
Release	April 2026

Pricing

Token Type	Cost
Input	$0.149 per million tokens
Output	$1.00 per million tokens

How to Use

Write your prompt - describe the task, provide context, and specify the desired output format.
Submit - the model processes your request and returns the response.

API Integration

Base URL: https://llm.wavespeed.ai/v1
API Endpoint: chat/completions
Model ID: qwen/qwen3.6-35b-a3b

API Usage

Python SDK

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://llm.wavespeed.ai/v1"
)

response = client.chat.completions.create(
    model="qwen/qwen3.6-35b-a3b",
    messages=[{"role": "user", "content": "Hello!"}]
)

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

cURL

curl https://llm.wavespeed.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "qwen/qwen3.6-35b-a3b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Notes

Model: qwen/qwen3.6-35b-a3b
Provider: alibaba
Best suited for efficient multimodal reasoning, coding, agentic workflows, long-context document understanding, and structured extraction

Qwen3.6 35b A3b API

qwen/qwen3.6-35b-a3b

Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35B total parameters and 3B active parameters per token. It uses a hybrid sparse Mixture-of-Experts architecture that combines Gated DeltaNet linear attention with standard attention layers, giving it strong efficiency for coding, agentic workflows, long-context reasoning, and multimodal understanding. The model supports text, image, and video inputs, a 262K-token context window, thinking and non-thinking modes, function calling, and structured outputs.

Perguntas frequentes sobre Qwen3.6 35b A3b

Quanto custa Qwen3.6 35b A3b via API?+

Preços no WaveSpeedAI: $0.25 por milhão de tokens de entrada e $2.00 por milhão de tokens de saída. Prompt caching e batch processing são cobrados separadamente e reduzem o custo efetivo em cargas longas e repetitivas.

Qual é a janela de contexto do Qwen3.6 35b A3b?+

Qwen3.6 35b A3b suporta até 262K tokens de contexto e até — tokens de saída por requisição.

Qwen3.6 35b A3b é compatível com OpenAI?+

Sim. O WaveSpeedAI expõe o Qwen3.6 35b A3b através de um endpoint compatível com OpenAI em https://llm.wavespeed.ai/v1. Aponte o SDK oficial da OpenAI para esta base URL com sua chave API do WaveSpeedAI — sem outras alterações no código.

Como começo a usar o Qwen3.6 35b A3b?+

Entre no WaveSpeedAI, crie uma chave API em Access Keys, então envie uma requisição para https://llm.wavespeed.ai/v1/chat/completions com o model id mostrado acima. Contas novas recebem créditos grátis para avaliar o Qwen3.6 35b A3b.

Preços

Experimentar o modelo