LLM ReferenceLLM Reference
Replicate API

Qwen2.5-72B-Instruct on Replicate API

Qwen2.5 · Alibaba

Serverless

Last refreshed 2026-04-19. Next refresh: weekly.

Why use Qwen2.5-72B-Instruct on Replicate API?

Replicate API offers Qwen2.5-72B-Instruct with pay-as-you-go pricing at $1.30/1M input tokens. Replicate is a cloud-based platform that enables users to run machine learning models easily and efficiently.

Compare Qwen2.5-72B-Instruct across 7 providers to find the best fit for your use case
Input / 1M
$1.30
Output / 1M
$1.30
Cache
Not sourced
Batch
Not sourced

Setup recipe

Python + curl
Install
pip install replicate
Auth
export REPLICATE_API_TOKEN=...
Call
import replicate
output = replicate.run(
    "qwen2.5-72b-instruct",
    input={"prompt": "Hello"}
Model ID
qwen2.5-72b-instruct

Request example

import replicate

# reads REPLICATE_API_TOKEN from env
# qwen2.5-72b-instruct format: "owner/model-name" (latest version) or "owner/model-name:version-hash"
output = replicate.run(
    "qwen2.5-72b-instruct",
    input={"prompt": "Hello"}
)
# Output is a list or generator depending on the model
print("".join(output))

Gotchas

  • Replicate uses "owner/model-name" format (e.g. "meta/meta-llama-3-8b-instruct") for the latest version, or "owner/model-name:version-sha" to pin to a specific version. The REST endpoint splits owner and model-name into the path: /v1/models/{owner}/{model-name}/predictions.
  • The examples expect REPLICATE_API_TOKEN; rename it only if your application config maps the new variable.

Compare Qwen2.5-72B-Instruct Across Providers

ProviderInput (per 1M)Output (per 1M)
DeepInfra$0.36$0.40
OpenRouter$0.36$0.40
Fireworks AI$0.90$0.90
Novita AI$0.20$0.60
Chutes AI$0.18$0.54
View all 7 providers →

Pricing

TypePrice (per 1M)
Input tokens$1.30
Output tokens$1.30

Capabilities

Structured Outputs

About Qwen2.5-72B-Instruct

Instruction-optimized flagship variant for demanding production applications requiring high-accuracy complex problem-solving across industries.

FAQ

What does Qwen2.5-72B-Instruct cost on Replicate API?

On Replicate API, Qwen2.5-72B-Instruct costs $1.3 per 1M input tokens and $1.3 per 1M output tokens.

What is the context window for Qwen2.5-72B-Instruct on Replicate API?

Qwen2.5-72B-Instruct supports a 128,000 token context window on Replicate API.

How does Replicate API compare to other Qwen2.5-72B-Instruct providers?

Qwen2.5-72B-Instruct is available from 7 providers. The cheapest input pricing is $0.18/1M tokens from Chutes AI.

Who created Qwen2.5-72B-Instruct?

Qwen2.5-72B-Instruct was created by Alibaba as part of the Qwen2.5 model family.

Is Qwen2.5-72B-Instruct open source?

Qwen2.5-72B-Instruct is open source under Apache 2.0 according to the seed data.

Get Started

Model Specs

Released2024-06-07
Parameters72.7B
Context128K
ArchitectureDecoder Only

Related Models on Replicate API