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 8 providers to find the best fit for your use caseInput / 1M
$1.30
Output / 1M
$1.30
Cache
Not sourced
Batch
Not sourced
Setup recipe
Python + curlInstall
pip install replicateAuth
export REPLICATE_API_TOKEN=...Call
import replicate
output = replicate.run(
"qwen2.5-72b-instruct",
input={"prompt": "Hello"}Model ID
qwen2.5-72b-instructRequest 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
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| DeepInfra | $0.36 | $0.40 |
| OpenRouter | $0.36 | $0.40 |
| Fireworks AI | $0.90 | $0.90 |
| Novita AI | $0.38 | $0.40 |
| Chutes AI | $0.18 | $0.54 |
Pricing
| Type | Price (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.
Get Started
Model Specs
Released2024-06-07
Parameters72.7B
Context128k
ArchitectureDecoder Only