Documentation

Quick Start · 33 models, one endpoint

Every model below speaks the same OpenAI-compatible API. Switch by changing one string — no new SDK, no new auth, no rewrite.

Get an API key Models API reference
Base URLhttps://claudekeys.store/v1
Quick start

Up and running in 4 steps

ClaudeKeys is a drop-in replacement for the OpenAI API. Point your existing client at https://claudekeys.store/v1, use your ClaudeKeys key, and pick any model ID.

1Get a keyCreate an API key on claudekeys.store.
2Set base URLUse claudekeys.store/v1 in any OpenAI client.
3Send a requestCall /chat/completions.
4Switch modelsChange the model string. That's it.
Step 1

Get an API key

Create an account at claudekeys.store, generate an API key, and keep it secret. Store it in an environment variable rather than in your code:

Terminal
export ClaudeKeys_API_KEY="YOUR_API_KEY"

Send the key as a Bearer token on every request: Authorization: Bearer $ClaudeKeys_API_KEY.

Step 2 & 3

Make your first request

Use the official OpenAI SDK (or plain HTTP) — only the base URL and key change.

# pip install openai
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://claudekeys.store/v1",
    api_key=os.environ["ClaudeKeys_API_KEY"],
)

response = client.chat.completions.create(
    model="claude-sonnet-5",
    messages=[{"role": "user", "content": "Hello!"}],
)

print(response.choices[0].message.content)
// npm install openai
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://claudekeys.store/v1",
  apiKey: process.env.ClaudeKeys_API_KEY,
});

const response = await client.chat.completions.create({
  model: "claude-sonnet-5",
  messages: [{ role: "user", content: "Hello!" }],
});

console.log(response.choices[0].message.content);
curl https://claudekeys.store/v1/chat/completions \
  -H "Authorization: Bearer $ClaudeKeys_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-5",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
Step 4

Switch models with one string

Every model ID in the model list works with the same code. Change model and nothing else:

for model in ["gpt-5.6-sol", "gemini-3.1-pro", "deepseek-v4-pro-max"]:
    r = client.chat.completions.create(
        model=model,
        messages=[{"role": "user", "content": "Explain recursion in one line."}],
    )
    print(model, "→", r.choices[0].message.content)
for (const model of ["gpt-5.6-sol", "gemini-3.1-pro", "deepseek-v4-pro-max"]) {
  const r = await client.chat.completions.create({
    model,
    messages: [{ role: "user", content: "Explain recursion in one line." }],
  });
  console.log(model, "→", r.choices[0].message.content);
}
# Only the "model" value changes
curl https://claudekeys.store/v1/chat/completions \
  -H "Authorization: Bearer $ClaudeKeys_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "gemini-3.1-pro", "messages": [{"role": "user", "content": "Hi"}]}'
Guides

Streaming

Set stream=True to receive tokens as server-sent events. Available on every model (⚡ Streaming).

stream = client.chat.completions.create(
    model="gpt-5.6-luna",
    messages=[{"role": "user", "content": "Write a haiku about APIs."}],
    stream=True,
)
for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="")
const stream = await client.chat.completions.create({
  model: "gpt-5.6-luna",
  messages: [{ role: "user", content: "Write a haiku about APIs." }],
  stream: true,
});
for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}
curl https://claudekeys.store/v1/chat/completions \
  -H "Authorization: Bearer $ClaudeKeys_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "gpt-5.6-luna", "stream": true,
       "messages": [{"role": "user", "content": "Write a haiku about APIs."}]}'

Vision

Models tagged 🖼️ Vision accept image input. Pass an image_url part alongside your text.

Python
response = client.chat.completions.create(
    model="gemini-3.7-flash",
    messages=[{
        "role": "user",
        "content": [
            {"type": "text", "text": "What is in this image?"},
            {"type": "image_url", "image_url": {"url": "https://example.com/photo.jpg"}},
        ],
    }],
)

Tools (function calling)

Models tagged 🔧 Tools can call functions you define. Describe them in tools and the model returns tool_calls when it wants one run.

Python
tools = [{
    "type": "function",
    "function": {
        "name": "get_weather",
        "description": "Get current weather for a city",
        "parameters": {
            "type": "object",
            "properties": {"city": {"type": "string"}},
            "required": ["city"],
        },
    },
}]

response = client.chat.completions.create(
    model="claude-opus-5.5",
    messages=[{"role": "user", "content": "Weather in Mumbai?"}],
    tools=tools,
)
print(response.choices[0].message.tool_calls)

JSON output

Models tagged 📄 JSON support structured JSON output. Ask for it with response_format:

Python
response = client.chat.completions.create(
    model="qwen3.8-max",
    messages=[{"role": "user", "content": "List 3 colors as JSON."}],
    response_format={"type": "json_object"},
)
Reasoning and Web search are built into the models that carry those tags (🧠 Reasoning, 🌐 Web). Check the capability list before relying on a feature.

Errors

Errors use standard HTTP status codes.

StatusMeaningWhat to do
401Missing or invalid API keyCheck the Authorization header.
404Unknown model IDUse an ID from the list or GET /v1/models.
429Too many requestsBack off and retry.
5xxTemporary server problemRetry after a short delay.
Reference

Models API

List every available model, with its capabilities, at runtime:

for m in client.models.list():
    print(m.id)
const models = await client.models.list();
for await (const m of models) console.log(m.id);
curl https://claudekeys.store/v1/models \
  -H "Authorization: Bearer $ClaudeKeys_API_KEY"

Capabilities are returned by GET /v1/models, so your code can check them at runtime.

Models

33 models, one endpoint

Tap a model ID to copy it. Prices are per 1M tokens.

33 models

What the capabilities mean

🧠
ReasoningThinks step by step before answering
🖼️
VisionAccepts image input
🔧
ToolsFunction / tool calling
⚡
StreamingServer-sent event streaming
📄
JSONStructured JSON output
🌐
WebBuilt-in web search

Capabilities are returned by GET /v1/models, so your code can check them at runtime. See the Models API.