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

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

Utilisation de l'API

Utilisez les exemples de code suivants pour intégrer notre API :

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["WAVESPEED_API_KEY"],
    base_url="https://llm.wavespeed.ai/v1",
    timeout=120.0,
    max_retries=2,
)

try:
    response = client.chat.completions.create(
        model="qwen/qwen3.6-35b-a3b",
        messages=[{"role": "user", "content": "Hello!"}],
    )
    print(response.choices[0].message.content or "")
except Exception as exc:
    raise SystemExit(f"LLM request failed: {exc}") from exc

Introduction au modèle

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.

Questions fréquentes sur Qwen3.6 35b A3b

Combien coûte l'API Qwen3.6 35b A3b ?+

Tarification sur WaveSpeedAI : $0.25 par million de tokens d'entrée et $2.00 par million de tokens de sortie. Le prompt caching et le traitement par batch sont facturés séparément et réduisent le coût effectif sur les charges longues et répétitives.

Quelle est la fenêtre de contexte de Qwen3.6 35b A3b ?+

Qwen3.6 35b A3b prend en charge jusqu'à 262K tokens de contexte et jusqu'à — tokens de sortie par requête.

Qwen3.6 35b A3b est-il compatible avec OpenAI ?+

WaveSpeedAI expose Qwen3.6 35b A3b à https://llm.wavespeed.ai/v1 via l’interface Chat Completions compatible OpenAI. La plupart des clients du SDK OpenAI fonctionnent en changeant l’URL de base et la clé API ; les champs facultatifs dépendent du modèle.

Comment démarrer avec Qwen3.6 35b A3b ?+

Connectez-vous à WaveSpeedAI, créez une clé API dans Access Keys, puis envoyez une requête à https://llm.wavespeed.ai/v1/chat/completions avec l’id du modèle affiché ci-dessus. Consultez le catalogue actuel pour la disponibilité, les capacités et les tarifs.

Tarification

Essayer le modèle