DeepSeek
DeepSeek Text
Model ID: ngovutuananh/deepseek-v4-flash
Family
DeepSeek
Context
256,000
Input / 1M tokens
0.008 $
Cache hit rate
42.1%
Requests
298
Success
82.6%
Tokens
6.77M
Uptime
24h agoNow
7 days agoNow
Observed token response speed
Up to 500 recent requests with a measured response time
500 recent requests
Observed output speed8.2 tok/s
Response time P503,616 ms
Response time P9510,227 ms
Samples9
Observed output speed: 17.2 tok/s · Output: 62 token · Response time: 3.6 s · 1 requests
Up to 500 recent requests with a measured response time19/10/2026 - 12:24:26
Response similarity to the reference model
The percentage reflects similarity between tested responses and reference data; it does not determine whether a model is genuine or fake.
No reference data yetNot enough data
Direct comparisonsNo direct comparisons yet
Check with my API key

Pricing

Input / 1M tokens
0.008 $
Output / 1M tokens
0.032 $
Minimum charge / request
0.00076 $
Prompt Cache 42.1%
Cache read / 1M tokens
0.002 $
Cache write / 1M tokens
0.0032 $

Repeated prompts are cached — reads are far cheaper than input, applied automatically via the API.

Price history

Price levels previously applied. The row tagged "current" is the live price.

Current Since 30/07/2026 - 21:06:01
Input / 1M tokens0.008 $ Output / 1M tokens0.032 $ Minimum charge / request0.00076 $ Cache read / 1M tokens0.002 $ Cache write / 1M tokens0.0032 $
Cost estimator
Estimated total 0 $
Average / request 0 $

Estimate based on list prices. Caching usually makes it cheaper.

Supported endpoints
https://api.xah.io/v1/chat/completions
https://api.xah.io/v1/completions
https://api.xah.io/v1/messages
https://api.xah.io/v1/responses
https://api.xah.io/v1beta/models/ngovutuananh/deepseek-v4-flash:generateContent
https://api.xah.io/api/chat
https://api.xah.io/api/generate
Method POST · application/json
Auth Bearer token (API key)
Rate limit 35 req/min
API kinds Text

Share

curl 'https://api.xah.io/v1/chat/completions' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "ngovutuananh/deepseek-v4-flash",
    "messages": [
        {
            "role": "user",
            "content": "Hello, who are you?"
        }
    ]
}'
// Node.js / Browser
const res = await fetch('https://api.xah.io/v1/chat/completions', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    "model": "ngovutuananh/deepseek-v4-flash",
    "messages": [
        {
            "role": "user",
            "content": "Hello, who are you?"
        }
    ]
})
});
const data = await res.json();
console.log(data);
import json, requests

url = 'https://api.xah.io/v1/chat/completions'
headers = {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json',
}
payload = json.loads("{\n    \"model\": \"ngovutuananh/deepseek-v4-flash\",\n    \"messages\": [\n        {\n            \"role\": \"user\",\n            \"content\": \"Hello, who are you?\"\n        }\n    ]\n}")

res = requests.post(url, headers=headers, json=payload, timeout=120)
print(res.status_code, res.json())
{
    "model": "ngovutuananh/deepseek-v4-flash",
    "messages": [
        {
            "role": "user",
            "content": "Hello, who are you?"
        }
    ]
}

Try it

Send a prompt with your API key — uses real credits, streams back instantly.

Reviews & comments
★ 0.0 / 0 reviews
Loading reviews...
Contact Support
We are always ready to help you