Alibaba logo

Qwen2.5 72B Instruct

Pricing & Specs API
Free REST API for prices, specs and benchmarks
Qwen2.5 72B Instruct is Alibaba's language model with a 131K context window and up to 16K output tokens, available from 7 providers, starting at $0.12 / 1M input and $0.3 / 1M output. A 72-billion-parameter instruction-tuned LLM from Alibaba's Qwen2.5 series, excelling at natural language understanding, summarization, and dialogue.
Specifications
Canonical IDalibaba-qwen2-5-72b-instruct
TypeLanguage
StatusActive
CreatorAlibabaAlibaba
Providers
Context Window131K tokens
Max Output16K tokens
Input ModalitiesText
Output ModalitiesText
Parameters72B
HuggingFace Likes927
HuggingFace Downloads (30d)457,915
HuggingFace Downloads (all-time)5,817,981
Release Date · 2 years ago
Knowledge Cutoff · 2 years ago
Benchmarks
Intelligence Index
9.6
#301
Math Index
14.0
#213
MMLU-Pro
0.7
#190
GPQA
0.5
#341
HLE
0.0
#385
LiveCodeBench
0.3
#223
AIME
0.2
#98
IFBench
0.4
#272
Time to First Token
0.00s
#9
SciCode
0.3
#294
MATH-500
0.9
#81
AIME 2025
0.1
#213
LCR
0.2
#265
TerminalBench Hard
0.0
#259
TAU2
0.3
#215
Output TPS
0.0
#265

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
ProviderStandard
Input
$ / 1M
Output
$ / 1M
DeepInfra logo
DeepInfra
deepinfra/Qwen/Qwen2.5-72B-Instruct
$0.12$0.39
Fireworks AI logo
Fireworks AI
fireworks_ai/accounts/fireworks/models/qwen2p5-72b-instruct
$0.9$0.9
Hugging Face logo
Hugging Face
novita:qwen/qwen-2.5-72b-instruct
$0.38$0.4
Hyperbolic logo
Hyperbolic
hyperbolic/Qwen/Qwen2.5-72B-Instruct
$0.12$0.3
Nebius logo
Nebius
nebius/Qwen/Qwen2.5-72B-Instruct
$0.13$0.4
Novita logo
Novita
novita/qwen/qwen-2.5-72b-instruct
$0.38$0.4
OpenRouter logo
OpenRouter
qwen/qwen-2.5-72b-instruct
$0.36$0.4

Cost Calculator

US Dollar ($)
Preset:

Cheapest Instances to Run It

Cloud GPU instances that can host Qwen2.5 72B Instruct, ranked by cheapest on-demand price. The model needs about 173 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 Qwen2.5 72B Instruct
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Dolphin 2.9.2 Qwen2 72B—131K$0.900$0.900Available
Cogito V1 Preview Qwen 14B—131K$0.200$0.200Available
Cogito V1 Preview Qwen 32B—131K$0.900$0.900Available
QwQ 32B131K$0.150$0.200Deprecated
Qwen2.5 Coder 32B Instruct131K$0.050$0.100Available
Qwen2.5 7B Instruct131K$0.040$0.070Available
Qwen2.5 72B Instruct131K$0.120$0.300Current
QwQ 32B Preview—33K$0.900$0.900Available
Qwen2.5 32B Instruct—128K$0.060$0.200Available
Qwen2 72B Instruct—33K$0.900$0.900Available
Qwen2.5 Coder 7B Instruct—33K$0.010$0.030Available

Model IDs

accounts/fireworks/models/qwen2p5-72b-instruct
alibaba-qwen2-5-72b-instruct
deepinfra/Qwen/Qwen2.5-72B-Instruct
fireworks_ai/accounts/fireworks/models/qwen2p5-72b-instruct
huggingface-llm-qwen2-5-72b-instruct
hyperbolic/Qwen/Qwen2.5-72B-Instruct
nebius/Qwen/Qwen2.5-72B-Instruct
novita/qwen/qwen-2.5-72b-instruct
qwen/qwen-2.5-72b-instruct
Qwen/Qwen2.5-72B-Instruct
qwen2-5-72b-instruct
qwen2.5-72b-instruct