# Using Gradio API Replica URL's / Issue with --replica
**URL:**
**Author:**  [@awacke1](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fawacke1)%5C
**Post date:** [April 23, 2024, 4:57pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fusing-gradio-api-replica-urls-issue-with-replica%2F83362%2F1 "2024-04-23T16:57:47Z")
When I rebuild a T4 GPU docker my URL keeps changing to indicate the replica. E.g.:
[https://awacke1-speech-recognition-canary-nvidiat4.hf.space/--replicas/y35z0/](https://awacke1-speech-recognition-canary-nvidiat4.hf.space/--replicas/y35z0/)
When I call the gradio app as API I would like to make the consumer impervious to a change in URL.
Will it work if I don’t include replica in the URL. e.g.
**[https://awacke1-speech-recognition-canary-nvidiat4.hf.space/](https://awacke1-speech-recognition-canary-nvidiat4.hf.space/) ?**
My calling code uses the URL as follows:
def transcribeWavtoTxt(filename):
from gradio\_client import Client
with open(filename, “rb”) as f:
data = f.read()
url=‘[https://awacke1-speech-recognition-canary-nvidiat4.hf.space/--replicas/4j9xb/](https://awacke1-speech-recognition-canary-nvidiat4.hf.space/--replicas/4j9xb/)’
client = Client(url)
```
#old URL from last build --- client = Client("https://awacke1-speech-recognition-canary-nvidiat4.hf.space/--replicas/0wdf4/")
result = client.predict(
filename,
"English", # Literal['English', 'Spanish', 'French', 'German'] in 'Input audio is spoken in:' Dropdown component
"English", # Literal['English', 'Spanish', 'French', 'German'] in 'Transcribe in language:' Dropdown component
True, # bool in 'Punctuation & Capitalization in transcript?' Checkbox component
api_name="/transcribe"
)
return result
```
---
**Author:**  [@radames](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fradames)%5C
**Post date:** [April 23, 2024, 5:22pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fusing-gradio-api-replica-urls-issue-with-replica%2F83362%2F2 "2024-04-23T17:22:31Z")
Hello @awacke1, yes, you’re correct; there’s no need to be concerned with the replica suffix at the end of the URL, as your internal proxy will handle that aspect effectively.
---
**Author:**  [@awacke1](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fawacke1)%5C
**Post date:** [April 23, 2024, 5:36pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fusing-gradio-api-replica-urls-issue-with-replica%2F83362%2F3 "2024-04-23T17:36:21Z")
You’re the best. Thankyou sir for quick response. Much appreciated!
–Aaron
---
**Author:**  [@kampaa201](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fkampaa201)%5C
**Post date:** [January 4, 2025, 9:50am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fusing-gradio-api-replica-urls-issue-with-replica%2F83362%2F4 "2025-01-04T09:50:44Z")
```auto
from gradio_client import Client
# Connect to the Gradio client
client = Client("black-forest-labs/FLUX.1-schnell")
# Call the inference endpoint
result = client.predict(
"/infer", # Endpoint
{
"prompt": "Hello!!", # Input parameters
"seed": 0,
"randomize_seed": True,
"width": 256,
"height": 256,
"num_inference_steps": 1
}
)
result
```
this is the code and the output of code is
```auto
Loaded as API: https://black-forest-labs-flux-1-schnell.hf.space ✔
('/tmp/gradio/489613c1bc4fe4fcf1b0e5a1d10b5977449d157f9eae4ccd9b8117765eabca12/image.webp',
653764749)
```
after that i tried to get the actual generated image and it’s not showing
the full url look like
[https://black-forest-labs-flux-1-schnell.hf.space/file=/tmp/gradio/489613c1bc4fe4fcf1b0e5a1d10b5977449d157f9eae4ccd9b8117765eabca12/image.webp](https://black-forest-labs-flux-1-schnell.hf.space/file=/tmp/gradio/489613c1bc4fe4fcf1b0e5a1d10b5977449d157f9eae4ccd9b8117765eabca12/image.webp)
```auto
{"detail":"File not found: /tmp/gradio/489613c1bc4fe4fcf1b0e5a1d10b5977449d157f9eae4ccd9b8117765eabca12/image.webp."}
```