API Protocols

LMU AI supports three inbound protocols: Anthropic, OpenAI Compatible, and Gemini native v1beta. Every endpoint uses your LMU AI sk- API key, and the models you can actually call are decided by the key's group.

Pick your protocol at a glance

All three protocols use the LMU AI key that starts with sk-:

• Anthropic protocol: Authorization: Bearer <YOUR_API_KEY> or x-api-key: <YOUR_API_KEY>
• OpenAI Compatible: Authorization: Bearer <YOUR_API_KEY>
• Gemini native: x-goog-api-key: <YOUR_API_KEY> recommended, Bearer also accepted

Anthropic protocol

Base URL: https://api.lmuai.com (no /v1)

Endpoints:

• POST /v1/messages — message conversation
• POST /v1/messages/count_tokens — token counting
• GET /v1/models — available model list

Python SDK example:

from anthropic import Anthropic

client = Anthropic(
    base_url="https://api.lmuai.com",
    api_key="sk-xxxxxxxx",
)

resp = client.messages.create(
    model="claude-sonnet-5",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello"}],
)
print(resp.content[0].text)

curl example:

curl -X POST https://api.lmuai.com/v1/messages \
  -H "Authorization: Bearer sk-xxxxxxxx" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-5",
    "max_tokens": 1024,
    "messages": [{"role":"user","content":"Hello"}]
  }'

OpenAI protocol

Base URL: https://api.lmuai.com/v1 (with /v1)

Endpoints:

• POST /chat/completions — standard Chat Completions API
• POST /responses — OpenAI Responses API (including the /responses/{id} sub-paths)
• POST /images/generations, POST /images/edits — image generation / editing

Python SDK example:

from openai import OpenAI

client = OpenAI(
    base_url="https://api.lmuai.com/v1",
    api_key="sk-xxxxxxxx",
)

resp = client.chat.completions.create(
    model="gpt-5.6-sol",
    messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)

curl example:

curl -X POST https://api.lmuai.com/v1/chat/completions \
  -H "Authorization: Bearer sk-xxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.6-sol",
    "messages": [{"role":"user","content":"Hello"}]
  }'

Gemini native protocol

Base URL: https://api.lmuai.com

Main endpoints:

• GET /v1beta/models — list Gemini native models
• GET /v1beta/models/{model} — query a specific model
• POST /v1beta/models/{model}:generateContent — text generation, text-to-image, and image-to-image
• POST /v1beta/models/{model}:streamGenerateContent?alt=sse — streaming generation

Authentication:

x-goog-api-key: YOUR_API_KEY

Minimal text-to-image example:

curl --request POST \
  'https://api.lmuai.com/v1beta/models/gemini-3.1-flash-image:generateContent' \
  -H 'x-goog-api-key: YOUR_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
    "contents": [{
      "role": "user",
      "parts": [{"text": "an orange cat wearing an astronaut helmet"}]
    }],
    "generationConfig": {
      "responseModalities": ["TEXT", "IMAGE"],
      "imageConfig": {"aspectRatio": "1:1", "imageSize": "1K"}
    }
  }'

Protocol and available models are two different things

Which models your key can call is decided entirely by the upstream account mounted on its group, independent of which protocol you call with:

So:

• Choosing the Anthropic, OpenAI Compatible, or Gemini native protocol determines the inbound request format; the actual model range is still decided by the API key's group.
• To see which models your current key can call, check the group's model list on the API Keys detail page or the Available Models page in the console.

About the Claude Max group

Troubleshooting

For more troubleshooting see the FAQ.

Next steps

Once you have the protocol and Base URL right, pick the tool you want:

• CC Switch (one-click import, recommended for Claude Code users)
• Claude Code CLI · Desktop · VS Code extension
• Codex CLI · Windows · Mac/Linux · Server
• Codex App desktop · VS Code / Cursor / Trae extension
• OpenCode · Cherry Studio · IDEA Kilo Code · Hermes Agent
• Gemini Image API · GPT Image API · Grok Image API · Gemini Batch Image API

Last updated: 2026-08-26