Qwen3.5 27B is Alibaba's language model with a 262K context window and up to 82K output tokens, available from 5 providers, starting at $0.26 / 1M input and $2.40 / 1M output. A 27B-parameter dense LLM from the Qwen3.5 series, offering strong general-purpose text generation and reasoning capabilities.
Specifications
Canonical IDalibaba-qwen3-5-27b
TypeLanguage
StatusActive
CreatorAlibabaAlibaba
Providers
Context Window262K tokens
Max Output82K tokens
Input ModalitiesImageTextVideo
Output ModalitiesText
Reasoning Effortsdefault
Parameters27B
HuggingFace Likes951
HuggingFace Downloads (30d)3,247,187
HuggingFace Downloads (all-time)5,302,164
Release Date · 8 months ago
Benchmarks
Intelligence Index
#135
GPQA
#90
HLE
#120
IFBench
#29
Time to First Token
#548
SciCode
#179
LCR
#71
TerminalBench Hard
#86
TAU2
#39
Output TPS
#155

Capabilities

Input3/5
Text✓
Image✓
Audio·
Video✓
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities4/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling·
Structured Outputs✓
Native JSON Schema✓
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Pricing by Provider

US Dollar ($)
Per 1M tokens
ProviderStandardBatch
Input
$ / 1M
Output
$ / 1M
Input
$ / 1M
Output
$ / 1M
Alibaba Qwen logo
Alibaba Qwen
qwen3.5-27b
$0.3$2.40$0.15$1.20
DeepInfra logo
DeepInfra
deepinfra/Qwen/Qwen3.5-27B
$0.26$2.60——
Hugging Face logo
Hugging Face
novita:qwen/qwen3.5-27b
$0.3$2.40——
Novita logo
Novita
novita/qwen/qwen3.5-27b
$0.3$2.40——
OpenRouter logo
OpenRouter
qwen/qwen3.5-27b
$0.26$2.60——

Cost Calculator

US Dollar ($)
Preset:

Cheapest Instances to Run It

Cloud GPU instances that can host Qwen3.5 27B, ranked by cheapest on-demand price. The model needs about 65 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.

All clouds
FP16 (full precision)
US Dollar ($)
Instance
Cloud
GPU
VRAM
Price
Cheapest region
Standard_NP20sAzure2× AMD Alveo U250 FPGA (64GB)128 GB$3.30/hr
g7e.2xlargeAWSRTX PRO Server 600096 GB$3.36/hr
Standard_NC24ads_A100_v4AzureNVIDIA A10080 GB$3.67/hr
7 more instances can run Qwen3.5 27B
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Qwen3.5 9B262K$0.100$0.150Deprecating
Qwen3.5 27B262K$0.260$2.40Current

Model IDs

accounts/fireworks/models/qwen3p5-27b
alibaba-qwen3-5-27b
deepinfra/Qwen/Qwen3.5-27B
huggingface-vlm-qwen3-5-27b
novita/qwen/qwen3.5-27b
openrouter/qwen/qwen3.5-27b
qwen/qwen3.5-27b
Qwen/Qwen3.5-27B
qwen3-5-27b
qwen3-5-27b-non-reasoning
qwen3.5-27b