Credits & Billing

How API keys, credits, and per-model pricing work in Osiris.

Generate an API Key

API keys are required to make requests to the Osiris API. Each key has its own credit balance.

Sign in and go to your Dashboard
Click Create Key
Give it a name (e.g. "Production", "Development")
Copy the key immediately — it will only be shown once

• Keys are prefixed with sk-osiris-

• You can create up to 10 API keys per account

• Each key has its own balance, usage tracking, and rate limit

• Keys can be deleted from the dashboard at any time

Top Up Credits

Credits are purchased in USD and added to a specific API key.

Go to Top Up in your dashboard
Select a credit package ($100 – $2,500 credits)
Select which API key to credit
Choose a payment method: QRIS (GoPay, OVO, Dana, ShopeePay) or Crypto (BTC, USDT, ETH, 350+ coins)
Complete the payment — credits are added automatically

• Prices are displayed in USD (with IDR conversion at live exchange rate)

• Each purchase extends your balance expiry by 1 month (max 3 months)

• Expired credits are forfeited — top up before expiry to keep your balance active

• Trial keys cannot be topped up — create a new key for paid usage

How Credits Work

Osiris uses post-charge billing: your balance is checked before each request, and the actual cost is deducted after the response is complete.

Balance check

Before forwarding your request, Osiris checks that your API key has a positive balance (> $0).

Request forwarded

Your request is sent to the AI model. Streaming responses are relayed in real-time.

Actual cost charged

After the response completes, the actual token usage is counted and the cost is deducted from your balance.

Pricing Formula

Each model has its own input and output price per 1 million tokens. The cost of a request is:

cost = (input_tokens / 1M × input_price) + (output_tokens / 1M × output_price)

Minimum charge is $0.001 per request. Check per-model pricing on the Models page.

Pricing Examples

Cost calculation examples

# Example: claude-opus-4.6
# Input: $5.00/1M tokens, Output: $25.00/1M tokens

Input tokens:  10,000
Output tokens: 2,000

Cost = (10,000 / 1,000,000 × $5.00) + (2,000 / 1,000,000 × $25.00)
     = $0.050 + $0.050
     = $0.100

# Example: deepseek-v3
# Input: $0.27/1M tokens, Output: $1.10/1M tokens

Input tokens:  50,000
Output tokens: 5,000

Cost = (50,000 / 1,000,000 × $0.27) + (5,000 / 1,000,000 × $1.10)
     = $0.0135 + $0.0055
     = $0.019

Rate Limits

Each API key has a rate limit of 40 requests per minute (sliding window). Rate limit info is included in response headers:

X-RateLimit-Limit: 40

X-RateLimit-Remaining: 37

X-RateLimit-Reset: 1713200000

When rate limited, the API returns 429 Too Many Requests with a Retry-After header.

Getting Started — Quick start guide with code examples for making your first API request.