API Documentation — FlowerWolf

Base URL： https://flowerwolf.net/v1

Auth Method：Header Authorization: Bearer <YOUR_TOKEN>. Get your token from the user dashboard.

GET /v1/models

List all currently available models. No authentication required.

Param	In	Type	Description
This endpoint does not require any parameters

Request Example

curl https://flowerwolf.net/v1/models

Response Example

{
  "models": [
    {"name": "gpt-4o", "upstream_model": "gpt-4o"},
    {"name": "claude-3-5-sonnet-20240620", "upstream_model": "claude-3-5-sonnet-20240620"},
    {"name": "gemini-1.5-pro", "upstream_model": "gemini-1.5-pro"},
    {"name": "deepseek-chat", "upstream_model": "deepseek-chat"},
    {"name": "qwen-turbo", "upstream_model": "qwen-turbo"}
  ]
}

POST /v1/chat/completions

OpenAI Compatible Chat Completions API. Supports all major models, charges from account balance based on actual usage.

Param	In	Type	Required	Description
model	body	string	Yes	Model name, e.g. `gpt-4o`, `claude-3-5-sonnet-20240620`
messages	body	array	Yes	Message array, same format as OpenAI
max_tokens	body	int	No	Max output tokens (required for some models)
temperature	body	float	No	Sampling temperature, between 0–2
stream	body	bool	No	Enable streaming (SSE)

Request Example

curl https://flowerwolf.net/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_TOKEN" \
  -d '{
    "model": "gpt-4o",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ],
    "max_tokens": 256
  }'

Response Example

{
  "id": "chatcmpl-xxx",
  "model": "gpt-4o",
  "choices": [{
    "message": {
      "role": "assistant",
      "content": "Hello! How can I help you today?"
    },
    "finish_reason": "stop",
    "index": 0
  }],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 18,
    "total_tokens": 28
  }
}

💡 SDK Example (Python):

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_TOKEN",
    base_url="https://flowerwolf.net/v1"
)

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

Error Codes

Status Code	Description
`200`	Request successful
`400`	Bad request, e.g. model does not exist or is not enabled
`401`	Unauthorized — invalid or missing token
`402`	Insufficient balance
`429`	Rate limit exceeded
`502`	Upstream provider error

Reference Pricing (per million tokens)

Model	Provider	Input Price	Output Price
GPT-4o	OpenAI	$5.00	$15.00
Claude 3.5 Sonnet	Anthropic	$3.00	$15.00
Gemini 1.5 Pro	Google	$3.50	$10.50
DeepSeek Chat	DeepSeek	$0.14	$0.28
Qwen Turbo	Alibaba	$0.50	$2.00
Llama 3.1 70B	Meta	$0.99	$2.49

💡 Prices shown are for reference only. Bulk pricing available. Contact Sales →