mixgateway.io

mixgateway.io Gateway · Quickstart

Overview

mixgateway.io exposes an OpenAI-compatible HTTP API so you can reach multiple model providers (DeepSeek, OpenAI, and others) through a single entrypoint.

  • Base URL: https://api.mixgateway.io/v1
  • Chat Completions: POST /chat/completions
  • Auth: Authorization: Bearer {api_key}
  • Protocol: Largely compatible with OpenAI chat/completions

Getting an API Key

  1. Sign up and sign in on the [console](/dashboard).
  2. Open API Key Management and create a new key.
  3. Copy the generated sk-... string (or your gateway’s key format).
  4. Send it on every request: Authorization: Bearer {api_key}.

Security: Do not hardcode keys in frontend bundles or public repositories. Use server-side config or secrets management.

Non-streaming request example

curl https://api.mixgateway.io/v1/chat/completions \
  -H "Authorization: Bearer sk-xxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek:deepseek-chat",
    "messages": [
      {"role": "user", "content": "Hi, just reply with \"Hi\""}
    ],
    "temperature": 0.7,
    "max_tokens": 128,
    "stream": false
  }'

Sample response

{
  "id": "1a9f9f27-ef53-4b0e-8849-465bf8270314",
  "object": "chat.completion",
  "created": 1772183892,
  "model": "deepseek:deepseek-chat",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hi"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 8,
    "completion_tokens": 1,
    "total_tokens": 9
  }
}

In requests, the model field often uses provider:modelId (for example deepseek:deepseek-chat). The gateway routes to the correct upstream based on that value. Exact available models are listed in your console or provider docs.

Streaming request example

curl https://api.mixgateway.io/v1/chat/completions \
  -H "Authorization: Bearer sk-xxxx" \
  -H "Content-Type: application/json" \
  -N \
  -d '{
    "model": "deepseek:deepseek-chat",
    "messages": [
      {"role": "user", "content": "Introduce yourself in one sentence"}
    ],
    "temperature": 0.7,
    "max_tokens": 256,
    "stream": true
  }'

Typical SSE lines look like:

data: {"id":"...","object":"chat.completion.chunk","choices":[{"delta":{"content":"Hi"}}], ...}

data: {"id":"...","object":"chat.completion.chunk","choices":[{"delta":{"content":", I'm a gateway assistant."}}], ...}

data: {"id":"...","object":"chat.completion.chunk","choices":[{"delta":{"content":""},"finish_reason":"stop"}], "usage":{"prompt_tokens":13,"completion_tokens":10,"total_tokens":23}}

The final chunk may include a usage object for billing and analytics.

Language SDK examples

JavaScript (Node.js, fetch)

const resp = await fetch("https://api.mixgateway.io/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: "Bearer sk-xxxx",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "deepseek:deepseek-chat",
    messages: [{ role: "user", content: "Hi" }],
    stream: false,
  }),
});

const data = await resp.json();
console.log(data.choices[0].message.content);

Python (requests)

import requests

url = "https://api.mixgateway.io/v1/chat/completions"
headers = {
    "Authorization": "Bearer sk-xxxx",
    "Content-Type": "application/json",
}
json_data = {
    "model": "deepseek:deepseek-chat",
    "messages": [{"role": "user", "content": "Hi"}],
    "stream": False,
}

resp = requests.post(url, headers=headers, json=json_data, timeout=30)
data = resp.json()
print(data["choices"][0]["message"]["content"])

Error format

Errors generally follow an OpenAI-style envelope, for example:

{
  "error": {
    "message": "Incorrect API key provided. For details",
    "type": "invalid_request_error",
    "param": null,
    "code": "invalid_api_key"
  },
  "request_id": "9f6b3bb8-9328-91ad-a5b7-1feed430211b"
}

Common codes you may see:

  • invalid_api_key — Key missing, revoked, or not accepted.
  • model_not_found — The model value is not available on this gateway.
  • insufficient_quota or balance errors — Account quota or prepaid balance insufficient.

Next steps