Qwen3.5 35B-A3B

AlibabaMCP Tool CallReasoning
alibaba/qwen3.5-35b-a3bOpen Weights

Qwen vision-language model for visual reasoning, documents, and agent tasks

Benchmark Pricing$0.25 / 1M in$2.00 / 1M out
Context: 262,144 tokens•Max Output: 65,536 tokens•Released: 2026-02-23

TECHNICAL SPECIFICATIONS

Context Window262,144262.1K tokens
Max Output65,53665.5K tokens
LicenseOpen SourceSelf-hostable
Input Modalities
TextVisionVideo
Function / Tool CallingSupported (MCP Ready)
Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ Qwen3.5 35B-A3B natively supports OpenAI / Anthropic format tool calling and is fully compatible with MCP servers and agent loops.

MCP Context Window Recommendations

With a context capacity of 262,144 tokens, this model can handle moderately large MCP tool definitions and multi-turn conversation logs comfortably.

API CALL INVOCATION EXAMPLE

// Example: Calling Qwen3.5 35B-A3B via OpenAI SDK
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.ALIBABA_API_KEY,
});

const response = await client.chat.completions.create({
  model: "alibaba/qwen3.5-35b-a3b",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

console.log(response.choices[0].message.content);

PRICING BY PROVIDER

15 providers
Alibabaqwen3.5-35b-a3b
$0.25 / $2.00
NanoGPTqwen/qwen3.5-35b-a3b:thinking
$0.14 / $1.00$0.05 cache
Jalapeno CloudQwen3.5-35B-A3B
$0.25 / $2.00
Novita AIqwen/qwen3.5-35b-a3b
$0.25 / $2.00
302.AIqwen3.5-35b-a3b
$0.06 / $0.46
LLM Gatewayalibaba/qwen3.5-35b-a3b
$0.25 / $2.00
AIHubMixqwen3.5-35b-a3b
$0.06 / $0.45
Ofoxbailian/qwen3.5-35b-a3b
$0.29 / $1.83$0.29 cache
Merge Gatewayqwen/qwen3.5-35b-a3b
$0.06 / $0.46$0.02 cache
Hugging FaceQwen/Qwen3.5-35B-A3B
$0.25 / $2.00
Kilo Gatewayqwen/qwen3.5-35b-a3b
$0.16 / $1.30
DevPass (LLM Gateway)qwen3.5-35b-a3b
$0.25 / $2.00
SiliconFlowQwen/Qwen3.5-35B-A3B
$0.24 / $1.80$0.15 cache
Mixlayerqwen/qwen3.5-35b-a3b
$0.25 / $1.30
Requestyqwen3.5-35b-a3b
$0.14 / $1.00$0.05 cache

Rates in USD per 1M tokens. Rates synchronized from models.dev public catalog.