20% off all GPT ๐ŸŽ‰ 30% off DeepSeekLearn more

Qwen: Qwen3.5 27B

Chat
qwen/qwen3.5-27b
CompareTry in PlaygroundGet started

Qwen3.5-27B is a dense vision-language model from Alibaba's Qwen3.5 series, incorporating linear attention for fast inference. Its overall capability approaches Qwen3.5-122B-A10B, making it an efficient choice balancing speed and quality. Context: 256K tokens, output: 64K. Accessible via the OpenAI-compatible protocol.

Context Window
256K
Max Output Tokens
64K
Released
2026-02-23
Capabilities
VisionFunction CallingReasoningPrompt CachingWeb SearchVideo Input
Available Providers
Alibaba CloudAliyun
Supported Protocols
openai

Providers

Alibaba Cloudprovider.type: "alicloud"
Input Tokens
$0.29/M
Output Tokens
$2.05/M
Cache Read
$0.29/M
Web Search
$0.01/R
Protocols
openai/v1/chat/completions
Aliyunprovider.type: "aliyun"
Input Tokens
$0.29/M
Output Tokens
$2.05/M
Cache Read
$0.29/M
Web Search
$0.01/R
Protocols
openai/v1/chat/completions

Playground

Open in OfoxChat

Code Examples

from openai import OpenAI


client = OpenAI(
    base_url="https://api.ofox.ai/v1",
    api_key="YOUR_OFOX_API_KEY",
)


response = client.chat.completions.create(
    model="qwen/qwen3.5-27b",
    messages=[
        {"role": "user", "content": "Hello!"}
    ],
)


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

Benchmarks

LMArena โ†—Evaluated as qwen3.5-27b

Qwen: Qwen3.5 27B scores 1408 in the Overall category of the LMArena text leaderboard (style control), ranking #118 of 374 models based on 27,362 human preference votes (updated 2026-07-12).

Benchmark scores for qwen3.5-27b on LMArena
CategoryArena Score95% CIRankVotes
Overall14081404โ€“1413#118 of 37427,362
Hard Prompts14271421โ€“1432#115 of 37417,075
Coding14501443โ€“1457#118 of 3697,526
Math14291414โ€“1443#75 of 3621,651
Creative Writing13581348โ€“1368#137 of 3724,087
Instruction Following14011394โ€“1407#114 of 3748,598
Chinese14711455โ€“1487#79 of 3441,532

Source: LMArena ยท CC BY 4.0 ยท Updated 2026-07-12 ยท Methodology โ†— ยท Ranks compare models within each category of the LMArena text leaderboard (style control). Scores come from third-party human preference evaluations, not from OFOX.

Related Models

More from Qwen

Qwen: Qwen3.8 Max 0902
$1.71/M/$5.14/M
Qwen: Qwen3.8 Flash
$0.11/M/$0.39/M
Qwen: Qwen3.8 27B
$0.5/M/$1.71/M

Similar Models

Anthropic: Claude Opus 5.5
$4/M/$20/M
OpenAI: GPT-6 Luna
$0.1/M/$0.5/M
OpenAI: GPT-6 Sol
$2/M/$10/M

Frequently Asked Questions

Qwen: Qwen3.5 27B on Ofox.ai costs $0.29/M per million input tokens and $2.05/M per million output tokens. Pay-as-you-go, no monthly fees.