Clipia AI Gateway

A single OpenAI-compatible API to Claude, GPT, Gemini, DeepSeek and Grok, billed in rubles. Get a key and make your first request in minutes.

Clipia AI Gateway is a single OpenAI-compatible API to flagship language models: Claude, GPT, Gemini, DeepSeek and Grok. One key, one contract, billed with your Clipia account credits — no foreign card required. It is a drop-in: if you already have code on the openai SDK or LangChain, just point base_url at https://api.clipia.ai/v1 and use a Clipia key.

Base URL

https://api.clipia.ai/v1 — compatible with OpenAI Chat Completions. Authenticate with a regular Clipia API key: Authorization: Bearer clipia_.... It's the same key and the same credit balance you use for image/video generation — no separate Gateway key needed: the generate scope already grants chat (details — Authentication). Both clipia_live_… and clipia_test_… work.

What's inside

Chat Completions

POST /v1/chat/completions — streaming and non-streaming responses, tool calling, structured outputs.

Models & pricing

The GET /v1/models catalog and prices in rubles per 1M tokens.

LangChain

ChatOpenAI with our base_url — chat, tools and agents.

Quickstart

Get an API key

Create a key in the developer console → API keys tab. The full key is shown only once — save it immediately. It is a server-side secret; never put it in a browser or a public repository.

export CLIPIA_API_KEY=clipia_live_xxxxxxxxxxxxxxxxxxxxxx

Make your first request

Use the official openai SDK — change only base_url and the key. The model is passed as a string (see the catalog).

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["CLIPIA_API_KEY"],
    base_url="https://api.clipia.ai/v1",
)

resp = client.chat.completions.create(
    model="claude-opus-5",
    messages=[
        {"role": "user", "content": "Hi! Tell me three facts about Mars."},
    ],
)

print(resp.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.CLIPIA_API_KEY,
  baseURL: "https://api.clipia.ai/v1",
});

const resp = await client.chat.completions.create({
  model: "claude-opus-5",
  messages: [
    { role: "user", content: "Hi! Tell me three facts about Mars." },
  ],
});

console.log(resp.choices[0].message.content);

curl https://api.clipia.ai/v1/chat/completions \
  -H "Authorization: Bearer $CLIPIA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-5",
    "messages": [
      { "role": "user", "content": "Hi! Tell me three facts about Mars." }
    ]
  }'

Read the response

The response is a standard chat.completion object. The text is in choices[0].message.content, the spend is in usage.

{
  "id": "chatcmpl-3f9a1c7e2b41",
  "object": "chat.completion",
  "created": 1782300000,
  "model": "claude-opus-5",
  "provider": "Clipia",
  "choices": [
    {
      "index": 0,
      "message": { "role": "assistant", "content": "1. ...\n2. ...\n3. ..." },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 18,
    "completion_tokens": 72,
    "total_tokens": 90,
    "cost": 0.05
  }
}

usage.cost is the cost of the request in credits (charged to the account balance). Billing is per input and output token — see pricing.

Sandbox, no charge

A key prefixed clipia_test_ runs in test mode — handy for debugging your integration before going live. See Sandbox.

Compatibility

The gateway responds in the OpenAI Chat Completions format, so clients built for the OpenAI contract work out of the box: the openai SDK (Python and Node.js), LangChain, and agent tools that accept a custom base_url. Streaming (SSE with data: [DONE]), tool/function calling, structured outputs (response_format) and the standard OpenAI error envelope are all supported.

What's next

Chat Completions — parameters, streaming, tools, structured outputs.
Models & pricing — catalog and rates.
LangChain — chat and agents.
Account & limits — GET /v1/key, GET /v1/generation, rate limits.
More about the product on the Clipia AI Gateway page.

The same models are available as an MCP chat tool — see the MCP section.