API ModelsAPI Models
Docs/Language Models API
LLM

Language Models API

Claude API proxy with pay-per-token pricing. Compatible with Anthropic API format.

Overview

The Messages API is compatible with the official Anthropic API format. It supports streaming, vision, tool use, and extended thinking features.

Endpoint

POST/api/v1/messages

Available Models

Prices are per 1M tokens

ModelInputOutputDescription
claude-haiku-4-5-20251001¥2.40¥12.00Fast, affordable
claude-haiku-4-5-20251001-thinking¥2.40¥12.00Haiku + Thinking
claude-sonnet-4-20250514¥7.20¥36.00Balanced
claude-sonnet-4-20250514-thinking¥7.20¥36.00Sonnet + Thinking
claude-sonnet-4-5-20250929¥7.20¥36.00Sonnet 4.5
claude-sonnet-4-5-20250929-thinking¥7.20¥36.00Sonnet 4.5 + Thinking
claude-sonnet-4-6¥18.00¥90.00Latest Sonnet
claude-sonnet-4-6-thinking¥18.00¥90.00Latest Sonnet + Thinking
claude-opus-4-6¥30.00¥150.00Latest Opus
claude-opus-4-6-thinking¥30.00¥150.00Latest Opus + Thinking
claude-opus-4-20250514¥36.00¥180.00Opus 4
claude-opus-4-20250514-thinking¥36.00¥180.00Opus 4 + Thinking
claude-opus-4-5-20251101¥12.00¥60.00Opus 4.5
claude-opus-4-5-20251101-thinking¥12.00¥60.00Opus 4.5 + Thinking

Request Parameters

modelrequiredstring
The model to use (see table above)
messagesrequiredarray
Array of messages with role (user/assistant) and content
max_tokensinteger
Maximum tokens to generate. Default: 1024
systemstring
System prompt to set context
streamboolean
Enable streaming responses. Default: false
temperaturenumber
Sampling temperature (0-1). Default: 1
thinkingobject
Enable extended thinking for *-thinking models

Basic Request

curl -X POST https://apimodels.app/api/v1/messages \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4-5-20250929",
    "max_tokens": 1024,
    "messages": [
      {"role": "user", "content": "Hello, Claude!"}
    ]
  }'

Response

{
  "id": "msg_01XFDUDYJgAACzvnptvVoYEL",
  "type": "message",
  "role": "assistant",
  "content": [
    {
      "type": "text",
      "text": "Hello! How can I help you today?"
    }
  ],
  "model": "claude-sonnet-4-5-20250929",
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 12,
    "output_tokens": 10
  }
}

Extended Thinking

For *-thinking models, you can enable extended thinking for complex reasoning tasks.

curl -X POST https://apimodels.app/api/v1/messages \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4-5-20250929-thinking",
    "max_tokens": 16000,
    "thinking": {
      "type": "enabled",
      "budget_tokens": 10000
    },
    "messages": [
      {"role": "user", "content": "Solve this step by step: What is 15% of 340?"}
    ]
  }'

Streaming

Set stream: true to receive Server-Sent Events (SSE).

curl -X POST https://apimodels.app/api/v1/messages \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4-5-20250929",
    "max_tokens": 1024,
    "stream": true,
    "messages": [
      {"role": "user", "content": "Write a short poem about coding."}
    ]
  }'

Billing

Credits are calculated based on actual token usage:

Cost = (input_tokens * input_price + output_tokens * output_price) / 1,000,000
Credits = Cost(CNY) * 10  // ¥1 = 10 credits

Error Codes

400Invalid request parameters
401Invalid or missing API key
402Insufficient credits
404Model not found
429Rate limit exceeded
500Internal server error
View ModelsGet API Key