AlibabaOpen-weight·131K context·72B params·Apache 2.0

Qwen3 72B Instructalibaba/qwen3-72b-instruct

Name: Qwen3 72B Instruct API
Brand: Alibaba
Availability: InStock

Alibaba's Qwen3 72B Instruct is the latest open-weight flagship in the Qwen family, with strong multilingual (especially Chinese) and reasoning capabilities. Apache 2.0 licensed; available on DashScope (official) and major open-weight aggregators.

Cheapest blended:$0.90 / 1M tokenson Together.ai · 2 providers listed

Pricing across providers

Sort by:

Provider	Input /1M	Output /1M	Blended /1M	Latency p50	Format	Freshness	Action
Together.ai Qwen/Qwen3-72B-Instruct	$0.90	$0.90	$0.90	220ms	OpenAI-compatible	Verified 3d ago	Try →
Alibaba Cloud DashScope qwen-72b-instruct	$0.75	$1.50	$0.94	420ms	OpenAI-compatible	Verified 3d ago	Try →

Affiliate disclosure: We may earn a commission from qualified signups. Pricing independence is enforced at the data layer — see our Editorial Independence Policy.

Works with

Point any of these clients at a hosting's base URL — they all speak at least one of this model's endpoint protocols (OPENAI_COMPATIBLE).

Capabilities

chat
reasoning
multilingual
long_context
tool_use

Languages: en, zh, ja, ko, ar, es, fr, de

Benchmarks

MMLU5-shot · official · source
85.9%
HumanEval0-shot pass@1 · official · source
82.1%

Code samples

Example using Together.ai — the cheapest hosting for this model as of last verification. Swap base_url and model to use a different provider from the matrix above.

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.together.xyz/v1",
)

response = client.chat.completions.create(
    model="Qwen/Qwen3-72B-Instruct",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)

Technical specs

Context: 131K
Max output: 8K
Parameters: 72B
Release: 2025-01-28
Training cutoff: 2024-09-01
License: Apache 2.0

Hugging Face →Official blog →

Similar models

Llama 3.3 70B InstructOpen-weight
Meta·70B params·131K ctx

Compare with

Qwen3 72B Instruct vs Llama 3.3 70B Instruct
Comparison planned — not yet published

Frequently asked

How much does Qwen3 72B Instruct cost?+

The cheapest public hosting is $0.90 per 1M blended tokens on Together.ai. 2 total providers are listed above with per-input / per-output / cached pricing.

How do I access Qwen3 72B Instruct from outside China?+

All hostings listed above support global access. The official API (e.g. api.deepseek.com, dashscope-intl.aliyuncs.com) accepts international credit cards and does not require a Chinese mobile number. For privacy-sensitive workloads, third-party aggregators like Together.ai host the model on US/EU infrastructure.

Is Qwen3 72B Instruct open-source? Can I fine-tune it?+

Yes. Qwen3 72B Instruct is open-weight under the Apache 2.0 license. Weights are available on Hugging Face for local inference, fine-tuning, and commercial use (see license for specific terms).

Is Qwen3 72B Instruct OpenAI-compatible?+

Most listed hostings expose an OpenAI-compatible API, so you can point an existing openai SDK client at the Provider's base_url and use the Provider's model name. See the Code Samples above for a copy-pasteable example.

What's the maximum context window for Qwen3 72B Instruct?+

The model supports up to 131,072 tokens of context (input + output). Some hosted versions may impose a smaller limit — check the "Context" column in the pricing matrix for each provider.