Overview

Pay-i manages the Categories and Resources defined below. The costs, across all unit types, for these resources are automatically kept up to date. Further, Pay-i maintains the history of these prices over time so you can see how price changes affect your business.

Support for significantly more Resources and Providers are in active development. If there is a specific Resource or Provider that you'd like to see us support and maintain automatically please contact [email protected].

If you want to define your own, see Custom Categories and Resources.

When using the Ingest API with these resources, first use the Get all Resources for a Category API to see the complete list of resources and their available unit types.

Model Versions and Time-Based Resolution

In the tables below, you'll find both model aliases (like gpt-4o) and specific versioned models (like gpt-4o-2024-08-06). Model aliases are simplified, non-versioned names that point to specific versioned models based on the timestamp of your request.

How Time-Based Resolution Works

Pay-i uses a time-based partition system for model resolution:

1. Each specific model version (like gpt-4o-2024-08-06) has an associated release date
2. When you use a model name in your code, Pay-i automatically resolves it to the correct version based on the timestamp of the event in your request, not when you call the ingest API
3. The combination of (model name, event timestamp) uniquely resolves to exactly one resource version
4. Model versions are partitioned in time based on their release dates, with the cutoff being midnight UTC

This is especially important for historical data backfilling: when ingesting past events, model names map to the versions that were current at the time of the original requests, not to the current versions.

Model naming conventions vary across providers. Some providers (like OpenAI, Anthropic, and Google Vertex AI) offer model aliases, while others (like Azure OpenAI and AWS Bedrock) typically use specific model version identifiers.

Both approaches have their own benefits and tradeoffs:

• Using model aliases:

  • No need to update code when newer versions are released
  • Simplified usage without remembering specific version dates
  • Important Note: Model aliases are controlled by the provider (e.g., OpenAI, Anthropic), not by Pay-i. When a provider changes what version an alias points to (e.g., OpenAI updating gpt-4o to point to a newer version), your code automatically uses that new version on your next API call. This happens without notification or your explicit approval.

• Using specific model versions:

  • Explicit control over which model version you're using
  • Consistency in behavior across deployments
  • Version locking for compliance or quality control
  • You decide when to upgrade to newer versions, not the provider

You can use either approach in your code based on your specific requirements:

# Using a model name (automatically resolves based on timestamp)
client.ingest.units(
    category="system.openai",
    resource="gpt-4o",  # Will resolve to the appropriate version based on timestamp
    units={"text": {"input": 10, "output": 50}}
)

# Using a specific versioned model
client.ingest.units(
    category="system.openai",
    resource="gpt-4o-2024-08-06",  # Explicitly using this specific version
    units={"text": {"input": 10, "output": 50}}
)

Category: system.openai

Pay-i supports OpenAI models including GPT-4o, GPT-4.1, GPT-4, GPT-3.5 Turbo, and the O-series models, as well as text embeddings and DALL-E image generation. These models offer varying capabilities from basic text completion to multimodal interactions with images and video.

For the most current information on OpenAI models and their capabilities, see OpenAI's Models documentation.

Category: system.anthropic

Pay-i integrates with Anthropic's Claude family of models, including the latest Claude 3.7 Sonnet, Claude 3.5 (Sonnet and Haiku), and the earlier Claude 3 (Opus, Sonnet, and Haiku) versions. Claude models are known for their high-quality reasoning, instruction following, and content generation capabilities.

For complete details on Anthropic's models and their specifications, see Anthropic's Claude model documentation.

Category: system.azureopenai

Pay-i supports Azure-hosted versions of OpenAI models, including GPT-4o, GPT-4, GPT-3.5 Turbo, and text embeddings. Azure OpenAI resources offer deployment options with different pricing based on deployment configuration.

For the most up-to-date information on Azure OpenAI models and deployment options, see Azure OpenAI Service models documentation.

Category: system.aws.bedrock

Pay-i integrates with AWS Bedrock's foundation model ecosystem, including Anthropic Claude models, Meta's Llama 3 (versions 1, 2, and 3) family, and Amazon's own Nova models.

For detailed information on AWS Bedrock models and capabilities, see AWS Bedrock model reference documentation.

Category: system.google.vertex

Pay-i supports Google Vertex AI's Gemini models, including Gemini 1.5 (Pro and Flash variants) and the newer Gemini 2.0 models. These models offer multimodal capabilities, handling text, image, audio, and video inputs with strong reasoning and instruction-following abilities.

For complete details on Google Vertex AI's Gemini models and their capabilities, see Google Cloud Gemini documentation.