OpenLLM Documentation

Enterprise AI API Platform - Unified access to 200+ AI models, standardized integration, pay-as-you-go

Quick Start

Account Recharge

First, recharge your account. Pay-as-you-go pricing, only pay for what you use.

Recharge Now

Create/Get API Key

Create a new API key on the API Keys page. The key will only be shown once, please store it safely.

Create Key

View API Key and Models

After creating an API key, click the "View Models" button on the right side of the key list to view the Base URL, API Key, and available models.

Your Credentials

Base URL:

API Key:sk-xxxxxxxxxxxxxxxx

Available Models:gpt-4o, claude-opus-4-6, gemini-2.5-flash...

View Base URL

Node 1 (Recommended)

Node 2

Usage Notes:

Anthropic: No /v1 suffix needed
OpenAI: Append /v1 to the Base URL
Gemini: Append /v1beta to the Base URL

OpenAI Usage

Configure OpenClaw

Configuration Note: OpenClaw requires configuring Provider and model list. Use openai API type.

Config file path:

~/.openclaw/openclaw.json

Edit the config file and add:

{
  "models": {
    "mode": "merge",
    "providers": {
      "openllm": {
        "baseUrl": "https://openllm.shop/v1",
        "apiKey": "sk-xxxxxxxxxxxxxxxx",
        "api": "openai-completions",
        "models": [
          {
            "id": "glm-5",
            "name": "glm-5",
            "input": ["text"],
            "contextWindow": 202752,
            "maxTokens": 16384
          }
        ]
      }
    }
  },
  "agents": {
    "defaults": {
      "models": {
        "openllm/glm-5": {}
      }
    }
  }
}

After editing, restart Gateway:

openclaw gateway restart

Configure OpenCode

Config file path: ~/.config/opencode/opencode.json. Create manually if not exists.

~/.config/opencode/opencode.json

{
  "provider": {
    "openai": {
      "options": {
        "baseURL": "https://openllm.shop/v1",
        "apiKey": "sk-xxxxxxxxxxxxxxxx"
      },
      "models": {
        "gpt-5.2": {
          "name": "GPT-5.2",
          "limit": {
            "context": 400000,
            "output": 128000
          },
          "options": {
            "store": false
          },
          "variants": {
            "low": {},
            "medium": {},
            "high": {},
            "xhigh": {}
          }
        }
      }
    }
  },
  "agent": {
    "build": {
      "options": {
        "store": false
      }
    },
    "plan": {
      "options": {
        "store": false
      }
    }
  },
  "$schema": "https://opencode.ai/config.json"
}

Python Usage

Install SDK:

pip install openai

from openai import OpenAI

client = OpenAI(
    api_key="sk-xxxxxxxxxxxxxxxx",
    base_url="https://openllm.shop/v1"
)

response = client.chat.completions.create(
    model="glm-5",
    messages=[{"role": "user", "content": "hi"}]
)
print(response.choices[0].message.content)

cURL Usage

`POST /v1/chat/completions`

Parameter	Type	Required	Description
model	string	Yes	Model name, e.g., glm-5, gpt-5.4
messages	array	Yes	Message list with role and content
temperature	number	No	Temperature parameter controlling randomness
max_tokens	number	No	Maximum output tokens
stream	boolean	No	Enable streaming output

curl -X POST "https://openllm.shop/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxx" \
  -d '{"model": "glm-5", "messages": [{"role": "user", "content": "hi"}], "stream": false}'

💡 Streaming: change "stream": false to "stream": true for SSE response

`POST /v1/responses`

Parameter	Type	Required	Description
model	string	Yes	Model name, e.g., glm-5, gpt-5.4
instructions	string	No	System instructions defining assistant behavior
input	string	Yes	User input content
max_output_tokens	number	No	Maximum output tokens

curl -X POST "https://openllm.shop/v1/responses" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxx" \
  -d '{"model": "gpt-5.4", "instructions": "You are a helpful assistant.", "input": "hi"}'

`POST /v1/images/generations`

Parameter	Type	Required	Description
model	string	Yes	Image generation model, e.g., gpt-image-2
prompt	string	Yes	Image description text
size	string	No	Image size, default 1024x1024
n	number	No	Number of images to generate
quality	string	No	Image quality: standard or high
response_format	string	No	Response format: url or b64_json

curl -X POST "https://openllm.shop/v1/images/generations" \
  -H "Authorization: Bearer sk-xxx" \
  -H "Content-Type: application/json" \
  -d '{"model": "gpt-image-2", "prompt": "A cute baby sea otter", "size": "1024x1024", "n": 1, "quality": "high", "response_format": "url"}'

Anthropic Usage

Configure Claude Code

Claude Code configures Base URL and API Token via environment variables.

Add the following export commands to the end of your shell config file:

~/.zshrc   # macOS default
~/.bashrc  # Linux default

Method 1: Environment Variables (Recommended)

Edit ~/.zshrc or ~/.bashrc, add the following at the end:

export ANTHROPIC_BASE_URL="https://openllm.shop"
export ANTHROPIC_AUTH_TOKEN="sk-xxxxxxxxxxxxxxxx"
export ANTHROPIC_MODEL="claude-sonnet-4-6"
export CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1

After saving, run source to apply, then launch Claude Code:

source ~/.zshrc
claude code

Method 2: Config File

Edit ~/.claude/settings.json and add:

{
  "env": {
    "ANTHROPIC_AUTH_TOKEN": "sk-xxxxxxxxxxxxxxxx",
    "ANTHROPIC_BASE_URL": "https://openllm.shop",
    "ANTHROPIC_MODEL": "claude-sonnet-4-6",
    "ANTHROPIC_REASONING_MODEL": "claude-sonnet-4-6",
    "ANTHROPIC_DEFAULT_SONNET_MODEL": "claude-sonnet-4-6",
    "ANTHROPIC_DEFAULT_HAIKU_MODEL": "claude-sonnet-4-6",
    "ANTHROPIC_DEFAULT_OPUS_MODEL": "claude-sonnet-4-6"
  },
  "includeCoAuthoredBy": false
}

Configure OpenClaw

Configuration Note: Use anthropic-messages API type.

Config file path:

~/.openclaw/openclaw.json

Edit the config file and add:

{
  "models": {
    "mode": "merge",
    "providers": {
      "openllm": {
        "baseUrl": "https://openllm.shop",
        "apiKey": "sk-xxxxxxxxxxxxxxxx",
        "api": "anthropic-messages",
        "models": [
          {
            "id": "claude-sonnet-4-6",
            "name": "claude-sonnet-4-6",
            "input": ["text", "image"],
            "contextWindow": 200000,
            "maxTokens": 64000
          }
        ]
      }
    }
  },
  "agents": {
    "defaults": {
      "models": {
        "openllm/claude-sonnet-4-6": {}
      }
    }
  }
}

After editing, restart Gateway:

openclaw gateway restart

Configure OpenCode

Config file path: ~/.config/opencode/opencode.json. Create manually if not exists.

~/.config/opencode/opencode.json

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "openllm_anthropic": {
      "name": "OpenLLM Anthropic",
      "npm": "@ai-sdk/anthropic",
      "options": {
        "baseURL": "https://openllm.shop/v1",
        "apiKey": "sk-xxxxxxxxxxxxxxxx"
      },
      "models": {
        "claude-opus-4-8": {
          "name": "Claude Opus 4 8 (Anthropic)"
        },
        "claude-sonnet-4-6": {
          "name": "Claude Sonnet 4 6 (Anthropic)"
        }
      }
    }
  },
  "agent": {
    "build": {
      "options": {
        "store": false
      }
    },
    "plan": {
      "options": {
        "store": false
      }
    }
  },
  "model": "openllm_anthropic/claude-opus-4-8",
  "small_model": "openllm_anthropic/claude-sonnet-4-6"
}

Python Usage

Install SDK:

pip install anthropic

from anthropic import Anthropic

client = Anthropic(
    api_key="sk-xxxxxxxxxxxxxxxx",
    base_url="https://openllm.shop"
)

response = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=1024,
    messages=[{"role": "user", "content": "hi"}]
)
print(response.content[0].text)

cURL Usage

`POST /v1/messages`

Required Headers

x-api-key: sk-xxx
anthropic-version: 2023-06-01

Parameter	Type	Required	Description
model	string	Yes	Claude model name, e.g., claude-sonnet-4-6
messages	array	Yes	Message list with role and content
max_tokens	number	Yes	Maximum output tokens
temperature	number	No	Temperature parameter controlling randomness
system	string	No	System prompt
stream	boolean	No	Enable streaming output

curl -X POST "https://openllm.shop/v1/messages" \
  -H "x-api-key: sk-xxx" \
  -H "anthropic-version: 2023-06-01" \
  -H "content-type: application/json" \
  -d '{"model": "claude-sonnet-4-6", "messages": [{"role": "user", "content": "hi"}], "max_tokens": 1024, "stream": false}'

💡 Streaming: change "stream": false to "stream": true for SSE response

Gmini Usage

Configure OpenClaw

Configuration Note: Use google-generative-ai API type.

Config file path:

~/.openclaw/openclaw.json

Edit the config file and add:

{
  "models": {
    "mode": "merge",
    "providers": {
      "openllm": {
        "baseUrl": "https://openllm.shop/v1beta",
        "apiKey": "sk-xxxxxxxxxxxxxxxx",
        "api": "google-generative-ai",
        "models": [
          {
            "id": "gemini-2.5-flash",
            "name": "gemini-2.5-flash",
            "input": ["text", "image"],
            "contextWindow": 1000000,
            "maxTokens": 8192
          }
        ]
      }
    }
  },
  "agents": {
    "defaults": {
      "models": {
        "openllm/gemini-2.5-flash": {}
      }
    }
  }
}

After editing, restart Gateway:

openclaw gateway restart

Configure OpenCode

Config file path: ~/.config/opencode/opencode.json. Create manually if not exists.

~/.config/opencode/opencode.json

{
  "provider": {
    "google": {
      "options": {
        "baseURL": "https://openllm.shop/v1beta",
        "apiKey": "sk-xxxxxxxxxxxxxxxx"
      },
      "models": {
        "gemini-2.5-flash": {
          "name": "Gemini 2.5 Flash",
          "limit": {
            "context": 1000000,
            "output": 8192
          },
          "options": {
            "store": false
          },
          "variants": {
            "low": {},
            "medium": {},
            "high": {},
            "xhigh": {}
          }
        }
      }
    }
  },
  "agent": {
    "build": {
      "options": {
        "store": false
      }
    },
    "plan": {
      "options": {
        "store": false
      }
    }
  },
  "$schema": "https://opencode.ai/config.json"
}

Python Usage

Install SDK:

pip install google-genai

from google import genai

client = genai.Client(
    api_key="sk-xxxxxxxxxxxxxxxx",
    http_options={
        'base_url': 'https://openllm.shop'
    }
)

response = client.models.generate_content(
    model='gemini-3.5-flash',
    contents='hi'
)
print(response.text)

cURL Usage

`POST /v1beta/models/{model_name}:generateContent`

Required Headers

x-goog-api-key: sk-xxx

Parameter	Type	Required	Description
model	string	Yes	Gemini model name (in URL path)
contents	array	Yes	Content array
contents[].parts[].text	string	Yes	Text content
generationConfig	object	No	Generation config (optional)

curl -X POST "https://openllm.shop/v1beta/models/gemini-2.5-flash:generateContent" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: sk-xxx" \
  -d '{"contents": [{"parts": [{"text": "hi"}]}]}'

💡 Streaming: append ?alt=sse to the URL for SSE response

Need help? Contact support