fetch for a gateway you call with plain HTTP, or add Stigg to the framework that runs your agents. For how each one works, see How it works. Each page below shows the setup steps and exactly what is reported.
Providers
stigg.wrap(client) recognizes each of these from the client object itself, so you do not name the vendor.
Anthropic
Messages API, streaming included, with the full prompt-caching breakdown
OpenAI
Chat Completions and Responses API, streaming included
Google Gemini
One-shot calls and chats, streaming included, with thinking tokens reported separately
Mistral
Chat, fill-in-the-middle and agent calls, streaming included
Groq
Groq’s own client or the OpenAI client, reported under Groq’s own event name
xAI
Grok models, through the OpenAI client
DeepSeek
DeepSeek’s own models, through the OpenAI client
Perplexity
Models with built-in web search, through the OpenAI client
Together AI
A large catalog of open-source models, through the OpenAI client
Fireworks AI
Open-source and fine-tuned models, through the OpenAI client
Ollama
Models you host yourself: meter and limit your own capacity
vLLM
Your self-hosted model server, through the OpenAI client
TypeSafe
Jev, a model that answers typed questions about your data (yes or no, choice or score) in one call
AI gateways
OpenRouter
Reports the credits actually charged and the model that actually served, through the OpenRouter or OpenAI client
LiteLLM Proxy
Self-hosted or cloud gateway: reports the cost LiteLLM computed for each call
Amazon Bedrock
The Converse API, for every model Bedrock serves
Cloudflare
AI Gateway and Workers AI, with cache hits left unbilled and the model that served
Databricks
Model serving endpoints, with the model that actually answered each call
agentgateway
The open-source, self-hosted gateway: tokens and the model that served, over a client or plain HTTP
Solo.io
Solo.io’s enterprise agentgateway and Gloo AI Gateway, through the agentgateway recipe with your gateway’s URL
Frameworks
One integration in the framework covers every agent it runs, so you do not wrap each agent’s client.Vercel AI SDK
One middleware in
wrapLanguageModel, for generateText, streamText and agentsLangChain and LangGraph
One callback handler in a run’s
callbacks, for createAgent graphs and hand-built StateGraphsGoogle ADK
One plugin in a Runner’s
plugins, for every agent the Runner reachesBring your own
Any OpenAI-compatible API
Point the OpenAI client at any endpoint in OpenAI’s format and it is metered with no extra code
Custom adapter
Any other model or API, including your own: describe where its usage is and the SDK does the rest
Your own framework
Any other framework or harness, through
stigg.middleware() around each step