Models API

Get available models and calculate usage costs.

GET/v1/models

Get available models with current pricing information.

List models

curl -X GET "https://api.credits.dev/v1/models?provider=openai&tier=flagship" \
  -H "X-API-Key: YOUR_API_KEY"

Response

{
  "success": true,
  "models": [
    {
      "modelId": "gpt-4o",
      "provider": "openai",
      "displayName": "GPT-4o",
      "modelType": "multimodal",
      "pricing": {
        "text": {
          "inputPerMillion": 2.5,
          "outputPerMillion": 10,
          "cachedInputPerMillion": 1.25
        },
        "contextWindow": 128000
      },
      "tier": "flagship"
    }
  ]
}

GET/v1/models?modelId=gpt-4o

Get a specific model by ID.

Get model by ID

curl -X GET "https://api.credits.dev/v1/models?modelId=gpt-4o" \
  -H "X-API-Key: YOUR_API_KEY"

Response

{
  "success": true,
  "model": {
    "modelId": "gpt-4o",
    "provider": "openai",
    "displayName": "GPT-4o",
    "pricing": {
      "text": {
        "inputPerMillion": 2.5,
        "outputPerMillion": 10
      }
    }
  }
}

POST/v1/models/calculate

Calculate estimated cost for a given model and token count without recording usage.

Calculate usage cost

curl -X POST "https://api.credits.dev/v1/models/calculate" \
  -H "X-API-Key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "modelId": "gpt-4o",
    "inputTokens": 5000,
    "outputTokens": 1000,
    "cachedTokens": 2000
  }'

Request Body

{
  "modelId": "gpt-4o",
  "inputTokens": 5000,
  "outputTokens": 1000,
  "cachedTokens": 2000
}

Response

{
  "success": true,
  "modelId": "gpt-4o",
  "modelName": "GPT-4o",
  "estimatedCostUsd": 0.0175,
  "pricing": {
    "inputPerMillion": 2.5,
    "outputPerMillion": 10,
    "cachedInputPerMillion": 1.25
  }
}