Setup

Setup Script

The setup script configures Claude Code and Codex CLI in one pass.

curl -fsSL "https://openlimits.app/setup?token=your-key-here" | bash

Manual setup is below for teams that prefer explicit config files or environment variables.

Claude Code

Anthropic-compatible clients should use the root OpenLimits URL.

{
  "env": {
    "ANTHROPIC_BASE_URL": "https://openlimits.app",
    "ANTHROPIC_AUTH_TOKEN": "your-key-here"
  }
}

Conductor can use the same Claude Code settings. You can also set the variables directly in the app environment.

ANTHROPIC_BASE_URL=https://openlimits.app
ANTHROPIC_API_KEY=your-key-here

Codex CLI / Desktop

Create or edit ~/.codex/config.toml with a custom provider:

model = "openai/gpt-5.5"
review_model = "openai/gpt-5.5"
model_provider = "openlimits"

[model_providers.openlimits]
name = "OpenLimits"
base_url = "https://openlimits.app/v1"
env_key = "OPENAI_API_KEY"
wire_api = "responses"

export OPENAI_API_KEY=your-key-here

To use GPT-5.6 Sol, Terra, or Luna, change the top-level model fields:

model = "openai/gpt-5.6-sol"
review_model = "openai/gpt-5.6-sol"
model_provider = "openlimits"

For Codex Desktop, set Base URL to https://openlimits.app/v1 and API Key to your OpenLimits key.

SDK Examples

Python (Anthropic SDK)

import anthropic

client = anthropic.Anthropic(
    api_key="your-key-here",
    base_url="https://openlimits.app",
)

message = client.messages.create(
    model="anthropic/claude-opus-4.8",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello"}],
)
print(message.content[0].text)

Python (OpenAI SDK)

from openai import OpenAI

client = OpenAI(
    api_key="your-key-here",
    base_url="https://openlimits.app/v1",
)

response = client.chat.completions.create(
    model="anthropic/claude-opus-4.8",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

TypeScript (Anthropic SDK)

import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic({
  apiKey: "your-key-here",
  baseURL: "https://openlimits.app",
});

const message = await client.messages.create({
  model: "anthropic/claude-opus-4.8",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Hello" }],
});
console.log(message.content[0].text);

Environment Variables

Anthropic clients use https://openlimits.app with no /v1. OpenAI clients use https://openlimits.app/v1.

For the full endpoint reference, see API Reference.