Quickstart

Sign up and sign in to the consoleCopy Anchor Link

Open https://ai.myaiexp.com/sign-up and click "Sign up" to create an account; if you already have one, go to https://ai.myaiexp.com/sign-in and click "Sign in".

After signing in you land on the console "Dashboard" (https://ai.myaiexp.com/dashboard), which shows your balance, spending and request count. Make sure your account has a balance before calling the API; see Wallet for how to top up.

Create an API keyCopy Anchor Link

1. Open "API Keys" in the left menu (or go directly to https://ai.myaiexp.com/keys).
2. Click "Create API Key".
3. Enter a name (for example my-first-key) and leave the other options at their defaults for now; if you want to cap spending, give it a quota limit.
4. Save, then copy the key from the list. You get a full key like sk-xxxxxxxx.

export MYAIEXP_API_KEY="sk-your-key"

Make your first callCopy Anchor Link

First confirm the key works and see which models you can call:

curl -sS https://ai.myaiexp.com/v1/models \
  -H "Authorization: Bearer $MYAIEXP_API_KEY"

Each data[].id in the response is a model ID you can put in the model parameter.

Option 1: OpenAI-compatible endpointCopy Anchor Link

The base URL is https://ai.myaiexp.com/v1. Replace your-model-id in the samples with a model ID from the model square (or call GET /v1/models); to switch models, change only model and keep the rest of the code.

curl -sS https://ai.myaiexp.com/v1/chat/completions \
  -H "Authorization: Bearer $MYAIEXP_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "your-model-id",
    "messages": [
      {"role": "user", "content": "Introduce yourself in one sentence."}
    ]
  }'

On success you get JSON like the following (content shown for illustration only); the answer is in choices[0].message.content:

{
  "id": "chatcmpl-...",
  "object": "chat.completion",
  "model": "your-model-id",
  "choices": [
    {
      "index": 0,
      "message": { "role": "assistant", "content": "..." },
      "finish_reason": "stop"
    }
  ],
  "usage": { "prompt_tokens": 14, "completion_tokens": 30, "total_tokens": 44 }
}

Option 2: Claude-native endpointCopy Anchor Link

Pick a model on the model square that supports /v1/messages and use its model ID. With the Anthropic SDKs, the base URL is https://ai.myaiexp.com (no /v1; the SDK requests /v1/messages itself). This endpoint accepts both the Authorization: Bearer and the x-api-key header.

curl -sS https://ai.myaiexp.com/v1/messages \
  -H "x-api-key: $MYAIEXP_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "your-model-id",
    "max_tokens": 1024,
    "messages": [
      {"role": "user", "content": "Introduce yourself in one sentence."}
    ]
  }'

On success the answer is in content[0].text, and usage is in usage.input_tokens and usage.output_tokens.

Check the usage logsCopy Anchor Link

Open "Usage Logs" in the console (https://ai.myaiexp.com/usage-logs) to see the call you just made: model, input / output tokens, cost and latency. If the entry is there, you're all set. See Usage Logs.