Documentation

CheapLM gives you Claude-compatible API access through one API key. It works with both the Anthropic Messages API and the OpenAI Chat Completions API, so you can plug it into SDKs, editors, agents, and automation tools that support a custom base URL.

Base URL: https://api.cheaplm.xyz/v1

Models: Claude Opus 4.6, Opus 4.5, Sonnet 4.6, Sonnet 4.5, Sonnet 4, Haiku 4.5

Works with: Cursor, Claude Code, VS Code extensions, OpenAI SDK, Anthropic SDK, and cURL

Quick Start

Get started with CheapLM in minutes. First, get your API key from your account dashboard.

Anthropic format

curl https://api.cheaplm.xyz/v1/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: sk-cl-YOUR_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "claude-sonnet-4",
    "max_tokens": 512,
    "messages": [
      {"role": "user", "content": "Say hello from CheapLM."}
    ]
  }'

OpenAI-compatible format

curl https://api.cheaplm.xyz/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-cl-YOUR_KEY" \
  -d '{
    "model": "claude-sonnet-4",
    "messages": [
      {"role": "user", "content": "Say hello from CheapLM."}
    ]
  }'

Authentication

Authenticate your requests using your API key in the x-api-key header or as a Bearer token in the Authorization header.

# Anthropic-compatible (recommended)
curl https://api.cheaplm.xyz/v1/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: sk-cl-YOUR_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "claude-sonnet-4",
    "max_tokens": 1024,
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

# OpenAI-compatible
curl https://api.cheaplm.xyz/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-cl-YOUR_KEY" \
  -d '{
    "model": "claude-sonnet-4",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

Available Models

CheapLM supports all Claude models with both OpenAI and Anthropic naming conventions. Use the shorter IDs (with dots) for new integrations.

Model	Model ID	Max Input	Max Output	Thinking	Vision
Claude Opus 4.6	`claude-opus-4.6`	200K	32K	Yes	Yes
Claude Opus 4.5	`claude-opus-4.5`	200K	32K	Yes	Yes
Claude Sonnet 4.6	`claude-sonnet-4.6`	200K	8192	Yes	Yes
Claude Sonnet 4.5	`claude-sonnet-4.5`	200K	8192	Yes	Yes
Claude Sonnet 4	`claude-sonnet-4`	200K	16K	Yes	Yes
Claude Haiku 4.5	`claude-haiku-4.5`	200K	8192	No	Yes

Pricing (USD per 1M tokens)

Model	Input	Cache Write	Cache Read (90% off)	Output
`claude-opus-4.6`	$5.00	$5.00	$0.50	$25.00
`claude-opus-4.5`	$5.00	$5.00	$0.50	$25.00
`claude-sonnet-4.6`	$3.00	$3.00	$0.30	$15.00
`claude-sonnet-4.5`	$3.00	$3.00	$0.30	$15.00
`claude-sonnet-4`	$3.00	$3.00	$0.30	$15.00
`claude-haiku-4.5`	$1.00	$1.00	$0.10	$5.00

Balance is in USD. Every $1 you pay buys $30 of API value. See Billing for pricing.

Messages API

Anthropic-compatible Messages endpoint. Supports streaming, system prompts, tools, and extended thinking.

POST https://api.cheaplm.xyz/v1/messages

Core request fields

modelrequired

Model ID: claude-opus-4.6, claude-sonnet-4.6, claude-haiku-4.5, etc.

messagesrequired

Array of message objects with role (user/assistant) and content (string or content blocks for multimodal)

max_tokensrequired

Maximum response tokens to generate

systemoptional

System prompt (string or content blocks)

temperatureoptional

Sampling temperature 0-2 (default: 1.0)

toolsoptional

Tool definitions for function calling

streamoptional

Set true for SSE streaming, false for normal response

thinkingoptional

Extended thinking: { "type": "enabled", "budget_tokens": 8192 }

Example request

curl https://api.cheaplm.xyz/v1/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: sk-cl-YOUR_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "claude-sonnet-4",
    "max_tokens": 1024,
    "system": "You are a concise coding assistant.",
    "messages": [
      {"role": "user", "content": "Explain recursion in one paragraph."}
    ]
  }'

Example response

{
  "id": "msg_01XFD...",
  "type": "message",
  "role": "assistant",
  "content": [
    { "type": "text", "text": "Recursion is when a function calls itself..." }
  ],
  "model": "claude-sonnet-4",
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 25,
    "output_tokens": 150,
    "cache_creation_input_tokens": 0,
    "cache_read_input_tokens": 0
  }
}

Key notes:

Stable short model IDs (claude-sonnet-4) are recommended
Streaming: set stream: true
Non-streaming: set stream: false
Per-key restrictions may block specific models, streaming, or IPs before the request reaches the model

Chat Completions (OpenAI-compatible)

Use this endpoint if you're integrating with tools that expect the OpenAI Chat Completions API. Note: model availability can differ from /v1/messages. If a model returns "not available", call GET /v1/models and pick one of the returned IDs.

curl https://api.cheaplm.xyz/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-cl-YOUR_KEY" \
  -d '{
    "model": "claude-sonnet-4.5",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ],
    "max_tokens": 256
  }'

Models

Use GET /v1/models to list available model IDs for OpenAI-compatible calls. For detailed pricing info, use GET /v1/models/info.

curl https://api.cheaplm.xyz/v1/models \
  -H "Authorization: Bearer sk-cl-YOUR_KEY"

Streaming

Streaming is supported on the Anthropic-compatible /v1/messages endpoint via Server-Sent Events (SSE). OpenAI-style streaming on /v1/chat/completions is not currently supported.

curl https://api.cheaplm.xyz/v1/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: sk-cl-YOUR_KEY" \
  -d '{
    "model": "claude-sonnet-4",
    "max_tokens": 256,
    "stream": true,
    "messages": [{"role": "user", "content": "Write a haiku about databases"}]
  }'

Errors

Different endpoints return slightly different error shapes (OpenAI vs Anthropic compatibility). When in doubt: check HTTP status + the error field.

// Example (OpenAI-compatible)
{
  "error": {
    "message": "Model \"...\" is not available.",
    "type": "invalid_request_error",
    "code": 400
  }
}

Rate Limits

We apply anti-abuse rate limits on signup/login and may apply additional throttles for free-tier usage. Limits can change over time.

Extended Thinking

Extended thinking is supported by Opus and Sonnet models. Pass the thinking parameter to enable it:

{
  "model": "claude-opus-4.6",
  "max_tokens": 4096,
  "thinking": {
    "type": "enabled",
    "budget_tokens": 8192
  },
  "messages": [{"role": "user", "content": "..."}]
}

CheapLM filters out thinking blocks from streamed responses for client compatibility. The thinking budget is controlled entirely client-side — set higher values for more complex reasoning.

Python SDK

Use AWstore with either the official Anthropic SDK or the OpenAI SDK.

Anthropic SDK

pip install anthropic

import anthropic

client = anthropic.Anthropic(
    api_key="sk-cl-YOUR_KEY",
    base_url="https://api.cheaplm.xyz/v1"
)

message = client.messages.create(
    model="claude-sonnet-4",
    max_tokens=1024,
    messages=[
        {"role": "user", "content": "Explain recursion in one paragraph."}
    ]
)

print(message.content[0].text)

Anthropic streaming

with client.messages.stream(
    model="claude-sonnet-4",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Write a haiku."}]
) as stream:
    for text in stream.text_stream:
        print(text, end="", flush=True)

OpenAI SDK

pip install openai

from openai import OpenAI

client = OpenAI(
    api_key="sk-cl-YOUR_KEY",
    base_url="https://api.cheaplm.xyz/v1"
)

response = client.chat.completions.create(
    model="claude-sonnet-4",
    messages=[{"role": "user", "content": "Hello from CheapLM"}]
)

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

TypeScript SDK

Use AWstore with either the Anthropic TypeScript SDK or the OpenAI SDK.

Anthropic SDK

npm install @anthropic-ai/sdk

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

const client = new Anthropic({
  apiKey: "sk-cl-YOUR_KEY",
  baseURL: "https://api.cheaplm.xyz/v1",
});

const message = await client.messages.create({
  model: "claude-sonnet-4",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Explain TypeScript generics." }],
});

console.log(message.content[0].type === "text" ? message.content[0].text : "");

Anthropic streaming

const stream = client.messages.stream({
  model: "claude-sonnet-4",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Write a poem." }],
});

for await (const event of stream) {
  if (event.type === "content_block_delta" && event.delta.type === "text_delta") {
    process.stdout.write(event.delta.text);
  }
}

OpenAI SDK

npm install openai

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "sk-cl-YOUR_KEY",
  baseURL: "https://api.cheaplm.xyz/v1",
});

const response = await client.chat.completions.create({
  model: "claude-sonnet-4",
  messages: [{ role: "user", content: "Hello from CheapLM" }],
});

console.log(response.choices[0].message.content);

cURL Examples

Anthropic API request

curl https://api.cheaplm.xyz/v1/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: sk-cl-YOUR_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "claude-sonnet-4",
    "max_tokens": 1024,
    "messages": [
      {"role": "user", "content": "Write a fizzbuzz in Python."}
    ]
  }'

Anthropic API streaming

curl https://api.cheaplm.xyz/v1/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: sk-cl-YOUR_KEY" \
  -H "anthropic-version: 2023-06-01" \
  --no-buffer \
  -d '{
    "model": "claude-sonnet-4",
    "max_tokens": 1024,
    "stream": true,
    "messages": [
      {"role": "user", "content": "Tell me a short story."}
    ]
  }'

OpenAI-compatible request

curl https://api.cheaplm.xyz/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-cl-YOUR_KEY" \
  -d '{
    "model": "claude-sonnet-4",
    "messages": [
      {"role": "user", "content": "Hello from CheapLM"}
    ]
  }'

System endpoints

# List models
curl https://api.cheaplm.xyz/v1/models

# Model info and pricing
curl https://api.cheaplm.xyz/v1/models/info

# Health check
curl https://api.cheaplm.xyz/health

IDE Integration

CheapLM works with popular AI coding assistants. Configure them to use our API endpoint.

Claude Code

# Set environment variables
export ANTHROPIC_API_KEY="sk-YOUR_KEY"
export ANTHROPIC_BASE_URL="https://api.cheaplm.xyz"

# Or use config file
claude config set apiKey sk-YOUR_KEY
claude config set baseUrl https://api.cheaplm.xyz

# Then run
claude

Cursor

Requires paid Cursor plan — custom API access needs Pro or higher. The 7-day Pro trial does NOT unlock this feature.

Open Cursor Settings → API keys
Turn on OpenAI API Key → paste your CheapLM API key
Turn on OpenAI Base URL → set to https://api.cheaplm.xyz/v1

Recommended models: claude-opus-4.6, claude-sonnet-4.6, claude-haiku-4.5

Continue

Edit ~/.continue/config.json

{
  "models": [
    {
      "title": "Claude Opus 4.6",
      "provider": "anthropic",
      "model": "claude-opus-4.6",
      "apiKey": "sk-cl-YOUR_KEY",
      "apiBase": "https://api.cheaplm.xyz/v1"
    }
  ]
}

Cline (VS Code)

Open the Cline extension settings and configure:

Select Anthropic as the provider
Set API Key: sk-YOUR_KEY
Set Base URL: https://api.cheaplm.xyz/v1
Choose your model

Roo Code

Open Roo Code settings and configure:

Select Anthropic as provider
Enter your API key and base URL: https://api.cheaplm.xyz
Select the model to use

OpenCode

export ANTHROPIC_API_KEY="sk-YOUR_KEY"
export ANTHROPIC_BASE_URL="https://api.cheaplm.xyz/v1"
opencode

Any Anthropic-Compatible Tool

For any tool that supports Anthropic API, set these two values:

Base URL: https://api.cheaplm.xyz/v1
API Key: sk-YOUR_KEY

Any OpenAI-Compatible Tool

For any tool that supports OpenAI API, set these two values:

Base URL: https://api.cheaplm.xyz/v1
API Key: sk-YOUR_KEY

Use model names like claude-sonnet-4, claude-opus-4.6, etc.

Reseller Transfer API

Transfer balance from your account to another user. Useful for resellers who buy API value in bulk and distribute it to clients.

Endpoint

POST /api/user/transfer
x-api-key: sk-cl-YOUR_API_KEY
Content-Type: application/json

{
  "toUsername": "client-username",
  "amount": 100
}

Parameters

Field	Type	Description
`toUsername`	string	The recipient's CheapLM username
`amount`	number	Dollar amount to transfer from your balance

Response

{
  "success": true,
  "amount": 100,
  "from": "reseller-account",
  "to": "client-username",
  "senderNewBalance": 450.50,
  "receiverNewBalance": 100.00
}

cURL Example

curl -X POST https://cheaplm.xyz/api/user/transfer \
  -H "x-api-key: sk-cl-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"toUsername": "client-username", "amount": 100}'

Important Notes

Transfers are instant and atomic — either both accounts update or neither does
You cannot transfer to yourself
The recipient must already have a CheapLM account
Amount is deducted from your balance and added to the recipient's
Rate limited to prevent abuse

Error Responses

Status	Error	Meaning
`400`	Insufficient balance	You don't have enough balance for this transfer
`404`	User not found	The recipient username doesn't exist
`400`	Cannot transfer to yourself	toUsername matches your own username
`401`	Unauthorized	Invalid or missing authentication token

Simple, Transparent Pricing

Pick an amount. Every $1 buys you $30 of API value.

You pay

$10

You get

$305

$1$500

Model

Per 1M input

Per 1M output

Opus 4.6

claude-opus-4-6

$5.00

$25.00

Opus 4.5

claude-opus-4-5

$5.00

$25.00

Opus 4

claude-opus-4

$15.00

$75.00

Sonnet 4.6

claude-sonnet-4-6

$3.00

$15.00

Sonnet 4.5

claude-sonnet-4-5

$3.00

$15.00

Sonnet 4

claude-sonnet-4

$3.00

$15.00

Haiku 4.5

claude-haiku-4-5

$1.00

$5.00

Haiku 3.5

claude-haiku-3-5

$0.80

$4.00

Need help? Contact us at support@cheaplm.xyz