API reference

The API exposes the Completions / Responses API and the Messages API. Both are served from the same host and authenticated with the same per-user API keys.

Authentication

Create an API key in the account dashboard and send it as a bearer token:

Authorization: Bearer sk-...

Keys are scoped to an invoice-able account, carry optional spend limits and expiry, and select which regions may process their requests. They can be created, revoked, and inspected at any time from Account → API keys. See Key controls and Regions.

Endpoints

Chat completions

from openai import OpenAI
 
client = OpenAI(base_url="https://zro.moonmath.ai/v1", api_key="sk-...")
 
response = client.chat.completions.create(
    model="deepseek-v4.1-flash",
    messages=[
        {"role": "system", "content": "You are a helpful coding assistant."},
        {"role": "user", "content": "Explain what a KV cache is."},
    ],
    temperature=0.2,
)
print(response.choices[0].message.content)

Streaming

Set stream: true to receive server-sent events. All models stream, and usage is included in the final chunk.

stream = client.chat.completions.create(
    model="deepseek-v4.1-flash",
    messages=[{"role": "user", "content": "Write a haiku about GPUs."}],
    stream=True,
)
for chunk in stream:
    delta = chunk.choices[0].delta.content
    if delta:
        print(delta, end="", flush=True)

Messages API

Claude Code and other Messages clients point at the endpoint root (not /v1).

export ANTHROPIC_BASE_URL="https://zro.moonmath.ai"
export ANTHROPIC_AUTH_TOKEN="$ZRO_API_KEY"
export ANTHROPIC_MODEL="deepseek-v4.1-flash"

import anthropic
 
client = anthropic.Anthropic(
    base_url="https://zro.moonmath.ai",
    api_key="sk-...",
)
 
message = client.messages.create(
    model="kimi-k3",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Summarize this diff."}],
)

Tool calling

The standard tools / tool_choice interface and the full tool-call loop are supported. This is what lets coding agents run shell commands, edit files, and call MCP tools.

tools = [{
    "type": "function",
    "function": {
        "name": "get_weather",
        "description": "Get the current weather for a city.",
        "parameters": {
            "type": "object",
            "properties": {"city": {"type": "string"}},
            "required": ["city"],
        },
    },
}]
 
response = client.chat.completions.create(
    model="deepseek-v4.1-flash",
    messages=[{"role": "user", "content": "Weather in Lisbon, Portugal?"}],
    tools=tools,
)
print(response.choices[0].message.tool_calls)

Reasoning effort

Models that expose reasoning accept a reasoning_effort parameter. The supported values differ per model. See the reasoning chips on the Models page.

response = client.chat.completions.create(
    model="glm-5.3",
    messages=[{"role": "user", "content": "Prove that sqrt(2) is irrational."}],
    reasoning_effort="max",
)

For models with adaptive reasoning (for example MiniMax-style thinking), clients can also request per-request thinking. Unsupported reasoning fields are dropped rather than rejected. A request never fails because a harness sent a parameter the selected model does not use.

Errors

Errors follow the standard error shape ({ "error": { "message", "type", ... } }).

Compatibility notes

• Standard request fields (temperature, top_p, max_tokens, frequency_penalty, presence_penalty, stop, seed) are accepted.
• Unsupported provider parameters are dropped instead of erroring. Clients built for other providers keep working.
• Both the bare model ID and its zro/ alias are accepted on every endpoint.