Alibaba logo

Qwen3 Next 80B A3B Instruct

Deprecates
Pricing & Specs API
Free REST API for prices, specs and benchmarks
Qwen3 Next 80B A3B Instruct is Alibaba's language model with a 262K context window and up to 66K output tokens, available from 10 providers, starting at $0.1 / 1M input and $0.9 / 1M output. An instruction-tuned Qwen3 Next MoE model with 80B total and 3B activated parameters, optimized for text generation and conversational tasks.
Specifications
Canonical IDalibaba-qwen3-next-80b-a3b-instruct
TypeLanguage
StatusDeprecating
CreatorAlibabaAlibaba
Providers
Context Window262K tokens
Max Output66K tokens
Input ModalitiesText
Output ModalitiesText
Parameters80B
HuggingFace Likes1,012
HuggingFace Downloads (30d)292,470
HuggingFace Downloads (all-time)14,864,763
Release Date · 10 months ago
Knowledge Cutoff · 10 months ago
Deprecation Date
Benchmarks
Intelligence Index
13.7
#244
Math Index
66.3
#98
MMLU-Pro
0.8
#71
GPQA
0.7
#172
HLE
0.1
#203
LiveCodeBench
0.7
#73
IFBench
0.4
#240
Time to First Token
1.01s
#363
SciCode
0.3
#235
AIME 2025
0.7
#98
LCR
0.5
#150
TerminalBench Hard
0.1
#218
TAU2
0.2
#298
Output TPS
184.5
#34

Capabilities

Input1/5
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
Cache Read
$ / 1M
Input
$ / 1M
Output
$ / 1M
Alibaba Qwen logo
Alibaba Qwen
qwen3-next-80b-a3b-instruct
$0.15$1.20N/A$0.075$0.6
DeepInfra logo
DeepInfra
deepinfra/Qwen/Qwen3-Next-80B-A3B-Instruct
$0.14$1.40N/A——
Fireworks AI logo
Fireworks AI
fireworks_ai/accounts/fireworks/models/qwen3-next-80b-a3b-instruct
$0.9$0.9N/A——
Google Gemini logo
Google Gemini
qwen3-next-80b-a3b-instruct
$0.15$1.20N/A——
Google Vertex AI logo
Google Vertex AI
qwen3-next-80b-a3b-instruct
$0.15$1.20N/A——
Hugging Face logo
Hugging Face
novita:qwen/qwen3-next-80b-a3b-instruct
$0.15$1.50N/A——
Novita logo
Novita
novita/qwen/qwen3-next-80b-a3b-instruct
$0.15$1.50N/A——
OpenRouter logo
OpenRouter
qwen/qwen3-next-80b-a3b-instruct
$0.1$1.10$0.07——
Together AI logo
Together AI
together_ai/Qwen/Qwen3-Next-80B-A3B-Instruct
$0.15$1.50N/A——
Vercel AI Gateway logo
Vercel AI Gateway
alibaba/qwen3-next-80b-a3b-instruct
$0.15$1.20N/A——

Cost Calculator

US Dollar ($)
Preset:

Cheapest Instances to Run It

Cloud GPU instances that can host Qwen3 Next 80B A3B Instruct, ranked by cheapest on-demand price. The model needs about 192 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_NP40sAzure4× AMD Alveo U250 FPGA (64GB)256 GB$6.60/hrwestus2
g2-standard-96GCP8× nvidia-l4192 GB$7.98/hrus-east4
g7e.12xlargeAWS2× RTX PRO Server 6000192 GB$8.29/hrus-east-1
7 more instances can run Qwen3 Next 80B A3B Instruct
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Qwen3 Coder Next262K$0.110$0.800Available
Qwen3 Next 80B A3B Instruct262K$0.100$0.900Current
Qwen3 Next 80B A3B Thinking262K$0.098$0.780Available

Model IDs

accounts/fireworks/models/qwen3-next-80b-a3b-instruct
alibaba-qwen3-next-80b-a3b-instruct
alibaba/qwen3-next-80b-a3b-instruct
dashscope/qwen3-next-80b-a3b-instruct
deepinfra/Qwen/Qwen3-Next-80B-A3B-Instruct
fireworks_ai/accounts/fireworks/models/qwen3-next-80b-a3b-instruct
huggingface-reasoning-qwen3-next-80b-a3b-instruct
novita/qwen/qwen3-next-80b-a3b-instruct
qwen/qwen3-next-80b-a3b-instruct
Qwen/Qwen3-Next-80B-A3B-Instruct
qwen/qwen3-next-80b-a3b-instruct:free
qwen3-next-80b-a3b-instruct
together_ai/Qwen/Qwen3-Next-80B-A3B-Instruct