Messages

POST https://ai.sivcloud.com/v1/messages uses the Anthropic Messages format. Claude Code and the Anthropic SDK use it.

curl https://ai.sivcloud.com/v1/messages \
  -H "x-api-key: $SIVCLOUD_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4.1-flash",
    "max_tokens": 256,
    "messages": [{"role": "user", "content": "Hello"}]
  }'

The Authorization: Bearer header is also accepted.

Response

{
  "type": "message",
  "role": "assistant",
  "model": "deepseek-v4.1-flash",
  "content": [{"type": "text", "text": "Hello!"}],
  "stop_reason": "end_turn",
  "usage": {"input_tokens": 20, "output_tokens": 3, "cache_read_input_tokens": 0}
}

cache_read_input_tokens is the input read from cache, and cache_creation_input_tokens is what was written to cache. See Cache.

Count tokens

POST https://ai.sivcloud.com/v1/messages/count_tokens counts the input tokens of a Messages request without creating a message. The body is the same as /v1/messages; system, messages and tools are all counted.

curl https://ai.sivcloud.com/v1/messages/count_tokens \
  -H "x-api-key: $SIVCLOUD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "deepseek-v4.1-flash", "messages": [{"role": "user", "content": "Hello"}]}'

{"input_tokens": 9}

The number is a local estimate and can differ slightly from usage in the response. The call is free: it does not touch your balance or allowance and does not appear in the usage log. An API key is still required.

Good to know

• max_tokens is required, as in the Anthropic API. The cost reserve is computed from it.
• Not every model opens this endpoint. The Models page in the console marks the endpoints of each model.
• Streaming uses "stream": true. See Streaming.
• Claude Code setup is on the Claude Code page.