Qwen3.6 35B A3B

Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token.

Input / output price: $0.07 / $0.42 per 1M
Context: 262K tokens
Released: Apr 16, 2026

Try Respan for free

Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "qwen3.6-35b-a3b".

from openai import OpenAI

client = OpenAI(

    base_url="https://api.respan.ai/api/",

    api_key="YOUR_RESPAN_API_KEY",

)

response = client.chat.completions.create(

    model="qwen3.6-35b-a3b",

    messages=[{"role": "user", "content": "Hello!"}],

)

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

import OpenAI from "openai";

const client = new OpenAI({

  baseURL: "https://api.respan.ai/api/",

  apiKey: "YOUR_RESPAN_API_KEY",

});

const response = await client.chat.completions.create({

  model: "qwen3.6-35b-a3b",

  messages: [{ role: "user", content: "Hello!" }],

});

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

curl https://api.respan.ai/api/chat/completions \

  -H "Authorization: Bearer YOUR_RESPAN_API_KEY" \

  -H "Content-Type: application/json" \

  -d '{

    "model": "qwen3.6-35b-a3b",

    "messages": [{"role": "user", "content": "Hello!"}]

}'

Read docs

Providers

7 providers, cheapest first, OpenRouter last, priced per 1M tokens after gateway discounts.

Provider	Context	Input	Output	Cache read
EmpirioLabs`empiriolabs/qwen3-6-35b-a3b`	131K	$0.07/M	$0.42/M	$0.035/M
DeepInfra`deepinfra/Qwen/Qwen3.6-35B-A3B`	262K	$0.10/M	$0.95/M	$0.10/M
Parasail`parasail/Qwen/Qwen3.6-35B-A3B`	262K	$0.15/M	$1.00/M	$0.015/M
IO.net`ionet/Qwen/Qwen3.6-35B-A3B`	262K	$0.184/M	$1.21/M	$0.092/M
Featherless`featherless_ai/Qwen/Qwen3.6-35B-A3B`	33K	$0.186/M	$1.1138/M	$0.50/M
Novita`novita/qwen/qwen3.6-35b-a3b`	262K	$0.248/M	$1.485/M	$0.00/M
OpenRouter`openrouter/qwen/qwen3.6-35b-a3b`	262K	$0.10/M	$0.90/M	$0.025/M

Is a provider down? OpenRouter status

Pricing

Averaged across 7 providers, in USD per 1M tokens after gateway discounts.

Average input: $0.15 per 1M
Average output: $1.01 per 1M
Average cache read: $0.11 per 1M

Cost by volume

Total cost from 0 to 1T tokens on the cheapest and most expensive provider.

Highest$0.248/MNovitaLowest$0.07/MEmpirioLabs

Throughput and latency

30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.

Output speed

Higher is better

59tokens/sacross providers

Faster than 66% of the other 472 models on the gateway

Response latency

Lower is better

2.1sacross providers

Faster than 57% of the other 497 models on the gateway

Benchmarks

The Respan Index plus 10 published scores from 4 sources, each linked to where it was published.

26.9/ 100

Respan Index#94 of 162

162 ranked models. The shaded band is this model's 95% interval, 17.4 to 41.6. Mistral Medium 3.5 and Step 3.5 Flash fall inside it, so the gap is within the margin of error.

Published scores

Benchmark	Score	Source	Published
SWE-bench VerifiedQwen	73.4%	Qwen	Apr 21, 2026
WeirdMLHåvard Tveit Ihle	34.5%	Håvard Tveit Ihle	Oct 5, 2026
SWE-rebench 2026-05-15 to 2026-07-01Nebius	24.7%	Nebius	Oct 5, 2026

Benchmark	Score	Source	Published
GPQA DiamondQwen	86%	Qwen	Apr 21, 2026
GPQA DiamondEpoch AI	84.8%	Epoch AI	Oct 5, 2026
Chess PuzzlesEpoch AI	26%	Epoch AI	Oct 5, 2026
Mystery Game PuzzlesEpoch AI	22%	Epoch AI	Oct 5, 2026

Benchmark	Score	Source	Published
OTIS Mock AIME 2024-2025Epoch AI	86.7%	Epoch AI	Oct 5, 2026
FrontierMath Tiers 1-3 v2Epoch AI	20.4%	Epoch AI	Oct 5, 2026

Benchmark	Score	Source	Published
MMLU-ProQwen	85.2%	Qwen	Apr 21, 2026

How the Respan Index works

How Qwen compares: DeepSeek vs Qwen, Claude vs Qwen, Gemini vs Qwen

Apps

Use Qwen3.6 35B A3B in the tools you already run. Each guide points the app at the Respan gateway.

Setup guides for more apps are in the integration docs.

Qwen3.6 35B A3B FAQ

Short answers, built from the data on this page.

Qwen3.6 35B A3B is a model from Qwen, released on Apr 16, 2026. Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token.

On the Respan gateway, Qwen3.6 35B A3B costs from $0.07 per 1M input tokens and $0.42 per 1M output tokens on EmpirioLabs, after gateway discounts. Averaged across its 7 providers, it costs $0.15 per 1M input tokens and $1.01 per 1M output tokens.

Qwen3.6 35B A3B is available through 7 providers: EmpirioLabs, DeepInfra, Parasail, IO.net, Featherless, Novita, and 1 more.

Qwen3.6 35B A3B accepts up to 262K tokens of context on its largest provider route.

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "qwen3.6-35b-a3b". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Qwen3.6 35B A3B scores 26.9 out of 100 on the Respan Index v1.1, ranking #94 of 162 models. By category: Coding 4.1, Agents 32.1 (estimated), Reasoning 33.5, Knowledge & language 21.2, and Human preference 49.2 (estimated). The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.

Qwen3.6 35B A3B has 10 published benchmark scores, including SWE-bench Verified 73.4%, GPQA Diamond 86%, and OTIS Mock AIME 2024-2025 86.7%. Each score links to where it was published; the data is collected by Respan.