Claude API proxy with pay-per-token pricing. Compatible with Anthropic API format.
The Messages API is compatible with the official Anthropic API format. It supports streaming, vision, tool use, and extended thinking features.
/api/v1/messagesPrices are per 1M tokens
| Model | Input | Output | Description |
|---|---|---|---|
| claude-opus-4-8 | $3.6765/1M | $18.3824/1M | Most capable Opus, long-horizon work |
| claude-opus-4-7 | $3.6765/1M | $18.3824/1M | 1M context, adaptive thinking |
| claude-opus-4-7-thinking | $3.6765/1M | $18.3824/1M | Opus 4.7 + Thinking |
| claude-haiku-4-5-20251001 | $0.3530/1M | $1.7648/1M | Fast, affordable |
| claude-haiku-4-5-20251001-thinking | $0.3530/1M | $1.7648/1M | Haiku + Thinking |
| claude-sonnet-4-20250514 | $1.0589/1M | $5.2942/1M | Balanced |
| claude-sonnet-4-20250514-thinking | $1.0589/1M | $5.2942/1M | Sonnet + Thinking |
| claude-sonnet-4-5-20250929 | $1.0589/1M | $5.2942/1M | Sonnet 4.5 |
| claude-sonnet-4-5-20250929-thinking | $1.0589/1M | $5.2942/1M | Sonnet 4.5 + Thinking |
| claude-sonnet-4-6 | $2.6471/1M | $13.2353/1M | Latest Sonnet |
| claude-sonnet-4-6-thinking | $2.6471/1M | $13.2353/1M | Latest Sonnet + Thinking |
| claude-opus-4-6 | $4.4118/1M | $22.0589/1M | Latest Opus |
| claude-opus-4-6-thinking | $4.4118/1M | $22.0589/1M | Latest Opus + Thinking |
| claude-opus-4-20250514 | $5.2942/1M | $26.4706/1M | Opus 4 |
| claude-opus-4-20250514-thinking | $5.2942/1M | $26.4706/1M | Opus 4 + Thinking |
| claude-opus-4-5-20251101 | $1.7648/1M | $8.8236/1M | Opus 4.5 |
| claude-opus-4-5-20251101-thinking | $1.7648/1M | $8.8236/1M | Opus 4.5 + Thinking |
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!"}
]
}'{
"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
}
}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?"}
]
}'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."}
]
}'Credits are calculated based on actual token usage:
Cost = (input_tokens * input_price + output_tokens * output_price) / 1,000,000 Credits = Cost(CNY) // credits are in ¥