DeepSeek Text

Model ID: tuanxedich28/DeepSeek-V4.1-Flash

Family

DeepSeek

Context

Not specified

Input / 1M tokens

0.0145 $

Cache hit rate

64.8%

Requests

108.6K

Success

96.1%

Tokens

5.72B

Uptime 96.15%

24h agoNow

Observed token response speed

Up to 500 recent requests with a measured response time

500 recent requests

Observed output speed23.5 tok/s

Response time P508,870 ms

Response time P9574,081 ms

Samples500

Observed output speed: 27.8 tok/s · Output: 245 token · Response time: 8.9 s · 16 requests

Up to 500 recent requests with a measured response time04/11/2026 - 23:09:55

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

Direct results for this model

Included in this model’s score

No direct comparison with this model yet

Other reference tests

Not used to evaluate this model

Reference onlyReference model: deepseek-v4.1-flash 99.8%Reference only

Check with my API key

Pricing

Input / 1M tokens

0.0145 $

Output / 1M tokens

0.0145 $

Minimum charge / request

0.000052 $

Prompt Cache 64.8%

Cache read / 1M tokens

0.00676 $

Cache write / 1M tokens

0.00676 $

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.

Past Since 17/10/2026 - 04:04:04

Input / 1M tokens0.0145 $ Output / 1M tokens0.0145 $ Minimum charge / request0.000052 $ Cache read / 1M tokens0.0052 $ Cache write / 1M tokens0.0052 $

Current Since 22/10/2026 - 14:25:15

Input / 1M tokens0.0145 $ Output / 1M tokens0.0145 $ Minimum charge / request0.000052 $ Cache read / 1M tokens0.00676 $ Cache write / 1M tokens0.00676 $

Cost estimator

Input tokens / request Output tokens / request Requests

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/tuanxedich28/DeepSeek-V4.1-Flash:generateContent

https://api.xah.io/api/chat

https://api.xah.io/api/generate

Method POST · application/json

Auth Bearer token (API key)

API kinds Text

Quick CLI setup

Pick your CLI. Install it first (step 1), then run the config command (step 2) to write the config file for this model.

Operating system

Step 1 — Install the CLI first (if not installed)

Skip this if you already have the CLI installed.

Step 2 — Config command (run once)

Open Terminal (macOS/Linux) or PowerShell (Windows), paste the command, then enter your API key when prompted.

Uninstall — remove config & CLI

Run one command to restore your previous config (or remove the CKEY config) and see how to uninstall the CLI.

Endpoint: Stream

curl 'https://api.xah.io/v1/chat/completions' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "tuanxedich28/DeepSeek-V4.1-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": "tuanxedich28/DeepSeek-V4.1-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\": \"tuanxedich28/DeepSeek-V4.1-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": "tuanxedich28/DeepSeek-V4.1-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

★ 1.0 / 1 reviews

Loading reviews...

Pricing

Share

Try it