API

A complete Model Gate API reference in five minutes.

API

Model Gate exposes two compatible inference interfaces:

Anthropic — POST /v1/messages for the Anthropic SDK, Claude Code, and compatible clients.
OpenAI — POST /v1/chat/completions for the OpenAI SDK and compatible clients.

One mg_live_... key works in both modes. Routing and billing are handled by Model Gate.

Base URL

https://api.model-gate.com

OpenAI-compatible clients normally use https://api.model-gate.com/v1.

Quick start

curl: Anthropic

curl https://api.model-gate.com/v1/messages \
  -H "x-api-key: mg_live_..." \
  -H "anthropic-version: 2023-06-01" \
  -H "content-type: application/json" \
  -d '{"model":"claude-opus-4.8","max_tokens":1024,"messages":[{"role":"user","content":"Hello"}]}'

curl: OpenAI

curl https://api.model-gate.com/v1/chat/completions \
  -H "Authorization: Bearer mg_live_..." \
  -H "content-type: application/json" \
  -d '{"model":"claude-opus-4.8","messages":[{"role":"user","content":"Hello"}]}'

Python: OpenAI SDK

from openai import OpenAI
client = OpenAI(api_key="mg_live_...", base_url="https://api.model-gate.com/v1")
response = client.chat.completions.create(model="claude-opus-4.8", messages=[{"role":"user","content":"Hello"}])
print(response.choices[0].message.content)

Python: Anthropic SDK

from anthropic import Anthropic
client = Anthropic(api_key="mg_live_...", base_url="https://api.model-gate.com")
response = client.messages.create(model="claude-opus-4.8", max_tokens=1024, messages=[{"role":"user","content":"Hello"}])
print(response.content[0].text)

Supported capabilities

Streaming, prompt caching, vision, tool use/function calling, extended thinking, and large-context models are passed through when supported by the selected model.

Limits

RPM and concurrency can be configured per account and per key. A key also has a resettable spending usage counter and a lifetime total_spent counter. Exceeding a rate limit returns 429 with Retry-After.

API