Introduction
BlazeInfer is a high-performance inference API. It serves open-weight models on GPUs that E2E Networks owns and runs. These docs show you how to connect your code and the tools you already use to BlazeInfer: the OpenAI and Anthropic Messages APIs, coding agents, agent workspaces, SDKs and frameworks.
Connect your tool
OpenAI API
Call BlazeInfer from any OpenAI SDK or OpenAI-compatible tool.
Anthropic Messages API
For models the console lists with Messages API support.
OpenCode
Open-source terminal coding agent.
OpenCode desktop
OpenCode desktop app on macOS, Linux and Windows.
Kilo Code
Coding agent for VS Code, JetBrains and the terminal.
Pi
Minimal terminal coding agent.
Orca
Run coding agents side by side.
SDKs and frameworks
OpenAI SDKs, LangChain, LlamaIndex and the Vercel AI SDK.
LiteLLM
Route through the LiteLLM proxy or SDK, with session IDs forwarded.
Any other tool
The five settings every OpenAI-compatible tool needs.
Try it first
Make one request to check that your key works, then set up your tool.
curl https://blaze.e2enetworks.net/v1/chat/completions \
-H "Authorization: Bearer $BLAZE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "google/gemma-4-31b-it",
"messages": [{"role": "user", "content": "Say hello in one sentence."}]
}'Already using the OpenAI SDK?
Only three things change: the base URL (https://blaze.e2enetworks.net/v1),
the API key (BLAZE_API_KEY) and the model ID.