Call the Inference API

Get Your Endpoint URL

After your endpoint reaches Running status, open the endpoint detail page to find the endpoint URL. The inference gateway URL follows this pattern (environment-specific):

https://<ddi-gateway-domain>/v1/chat/completions

The endpoint exposes the standard chat completions API.

Call via curl

curl https://<ddi-gateway-domain>/v1/chat/completions \
  -H "Authorization: Bearer sk-vgw-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistralai/Mistral-7B-Instruct-v0.3",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Summarize the benefits of dedicated GPU inference."}
    ],
    "max_tokens": 256
  }'

Replace <ddi-gateway-domain> with the gateway domain from the endpoint detail page, and sk-vgw-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx with your key from the API keys tab.

Call via Python

import requests

url = "https://<ddi-gateway-domain>/v1/chat/completions"
headers = {
    "Authorization": "Bearer sk-vgw-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
    "Content-Type": "application/json",
}
payload = {
    "model": "mistralai/Mistral-7B-Instruct-v0.3",
    "messages": [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello!"},
    ],
    "max_tokens": 256,
}

response = requests.post(url, headers=headers, json=payload)
result = response.json()
print(result["choices"][0]["message"]["content"])

Streaming Responses

import requests, json

url = "https://<ddi-gateway-domain>/v1/chat/completions"
headers = {
    "Authorization": "Bearer sk-vgw-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
    "Content-Type": "application/json",
}
payload = {
    "model": "mistralai/Mistral-7B-Instruct-v0.3",
    "messages": [{"role": "user", "content": "Write a short poem."}],
    "max_tokens": 200,
    "stream": True,
}

with requests.post(url, headers=headers, json=payload, stream=True) as r:
    for line in r.iter_lines():
        if line and line.startswith(b"data: "):
            data = line[6:]
            if data != b"[DONE]":
                chunk = json.loads(data)
                content = chunk["choices"][0]["delta"].get("content", "")
                print(content, end="", flush=True)

Try It in the Playground

Open the endpoint detail page and click the Playground tab to send test requests directly from the browser — no code required. You can adjust Temperature, Top-p, and Max tokens in the Parameters panel on the right.

Common HTTP Errors

Status	Cause	Fix
401 Unauthorized	Missing or invalid API key	Check your API key in the API keys tab
429 rate_limited	Rate limit exceeded (RPM, TPM, or concurrent requests)	Retry after a delay or contact support to increase limits
503 Service Unavailable	Endpoint not in Running state	Wait for the endpoint to reach Running in My endpoints