LiteLLM + APIMaster.ai

Connect APIMaster.ai OpenAI-compatible API via LiteLLM Python SDK or LiteLLM Proxy.

LiteLLM provides a unified LLM SDK and a local Proxy server. APIMaster.ai exposes an OpenAI-compatible API — use the openai/<model id> format and set api_base.

Get an API Key first. Copy the exact model id from the marketplace.

Base URL:

https://apimaster.ai/v1

LiteLLM model name format:

openai/<APIMaster model id>

Example: openai/claude-sonnet-4-6.

Prerequisites

Python 3.10+ (3.11+ recommended).
An APIMaster API Key from the console.
A target model id from the marketplace.

Step 1 — Install LiteLLM

SDK only:

pip install litellm

With Proxy support:

pip install "litellm[proxy]"

Step 2 — Minimal Python SDK test

Create minimal_apimaster_test.py:

import litellm

API_KEY = "your APIMaster key"

response = litellm.completion(
    model="openai/claude-sonnet-4-6",
    api_base="https://apimaster.ai/v1",
    api_key=API_KEY,
    messages=[
        {"role": "user", "content": "Say hi in one short sentence."},
    ],
    max_tokens=64,
)

print(response.choices[0].message.content)

Or download the sample script.

python minimal_apimaster_test.py

Step 3 — LiteLLM Proxy config

Create config.apimaster.yaml:

model_list:
  - model_name: apimaster-claude-sonnet
    litellm_params:
      model: openai/claude-sonnet-4-6
      api_base: https://apimaster.ai/v1
      api_key: os.environ/APIMASTER_API_KEY

general_settings:
  master_key: sk-local-test

Or download the sample config.

Key	Purpose
`APIMASTER_API_KEY`	Real APIMaster key — LiteLLM uses this upstream
`master_key`	Local Proxy access key — clients use this

Step 4 — Start LiteLLM Proxy

export APIMASTER_API_KEY="your APIMaster key"
litellm --config config.apimaster.yaml --port 4000

If litellm is not on PATH:

python -m litellm --config config.apimaster.yaml --port 4000

Step 5 — Test local Proxy

curl http://localhost:4000/v1/chat/completions \
  -H "Authorization: Bearer sk-local-test" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "apimaster-claude-sonnet",
    "messages": [{"role": "user", "content": "Say hi in one short sentence."}],
    "max_tokens": 64
  }'

Step 6 — Multiple models

model_list:
  - model_name: apimaster-claude-sonnet
    litellm_params:
      model: openai/claude-sonnet-4-6
      api_base: https://apimaster.ai/v1
      api_key: os.environ/APIMASTER_API_KEY

  - model_name: apimaster-gpt
    litellm_params:
      model: openai/gpt-5.4
      api_base: https://apimaster.ai/v1
      api_key: os.environ/APIMASTER_API_KEY

general_settings:
  master_key: sk-local-test

Clients call apimaster-gpt, not openai/gpt-5.4.

Troubleshooting

401 Invalid token

Key is wrong or disabled. Verify:

curl https://apimaster.ai/v1/models \
  -H "Authorization: Bearer YOUR_KEY"

Model not found

Use marketplace model id with openai/ prefix:

model: openai/claude-sonnet-4-6

Wrong api_base

Must include /v1:

api_base: https://apimaster.ai/v1

Recommended verification order

Python SDK minimal script — validates APIMaster key and model.
Start LiteLLM Proxy.
Call local Proxy with OpenAI-compatible JSON.

Checklist

Installed litellm (litellm[proxy] for Proxy)
SDK: openai/<model id> + api_base=https://apimaster.ai/v1
Proxy: APIMASTER_API_KEY vs master_key configured separately
SDK or Proxy test returns a reply