Quick Start

Get started with the Dragonfly API in 3 steps.

Create an account

Get your API key

Go to Dashboard → API Keys → Create Key.

Make your first request

Use any OpenAI-compatible SDK. Just change the base URL.

curl https://api.dragonfly.dev/v1/chat/completions \
  -H "Authorization: Bearer sk-df-xxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-chat",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Authentication

All API requests require a Bearer token in the Authorization header.

Authorization: Bearer sk-df-xxxxxxxxxxxxxxxxxxxx

Get your API key from the Dashboard. Keep it secret — treat it like a password.

Chat Completions

Create a chat completion. OpenAI-compatible.

POST/v1/chat/completions

Request Parameters

Parameter	Type	Required	Description
model	string	Yes	Model ID (e.g. deepseek/deepseek-chat)
messages	array	Yes	Array of message objects with role and content
temperature	number	No	Sampling temperature (0-2). Default: 1
top_p	number	No	Nucleus sampling. Default: 1
max_tokens	integer	No	Maximum tokens to generate
stream	boolean	No	Stream response via SSE. Default: false
stop	string\|array	No	Stop sequences
frequency_penalty	number	No	Frequency penalty (-2 to 2). Default: 0
presence_penalty	number	No	Presence penalty (-2 to 2). Default: 0
tools	array	No	Function calling tools (OpenAI format)
tool_choice	string\|object	No	Tool selection mode

Request Example

curl https://api.dragonfly.dev/v1/chat/completions \
  -H "Authorization: Bearer sk-df-xxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-chat",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "What is 2+2?"}
    ],
    "temperature": 0.7,
    "max_tokens": 1024
  }'

Response

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1709000000,
  "model": "deepseek/deepseek-chat",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "2 + 2 = 4"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 25,
    "completion_tokens": 8,
    "total_tokens": 33
  }
}

Claude Messages API

Dragonfly supports the Anthropic Messages API format natively. Use any Anthropic SDK pointed at Dragonfly.

Endpoint

POST /v1/messages

import anthropic

client = anthropic.Anthropic(
    base_url="https://dragonfly-api.com",
    api_key="sk-df-your-key-here"
)

message = client.messages.create(
    model="deepseek/deepseek-chat",
    max_tokens=1024,
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)
print(message.content[0].text)

Parameter	Type	Required	Description
model	string	Yes	Model ID (e.g., deepseek/deepseek-chat)
max_tokens	integer	Yes	Maximum tokens to generate
messages	array	Yes	Array of message objects with role and content
system	string	No	System prompt
stream	boolean	No	Enable SSE streaming
temperature	number	No	Sampling temperature (0-1)
stop_sequences	array	No	Custom stop sequences

💡 Multi-Format Support

Dragonfly supports both OpenAI (/v1/chat/completions) and Anthropic (/v1/messages) API formats. Use whichever SDK you prefer — same models, same pricing.

List Models

List all available models.

GET/v1/models

curl https://api.dragonfly.dev/v1/models

Response

{
  "object": "list",
  "data": [
    {
      "id": "deepseek/deepseek-chat",
      "object": "model",
      "owned_by": "deepseek",
      "pricing": { "input": 0.0005, "output": 0.0015 }
    }
  ]
}

Audio Transcriptions (ASR)

Transcribe audio to text.

POST/v1/audio/transcriptions

Parameter	Type	Required	Description
file	file	Yes	Audio file (mp3, wav, m4a, webm)
model	string	No	Model ID. Default: whisper-1
language	string	No	ISO language code (e.g. en, zh)

curl https://api.dragonfly.dev/v1/audio/transcriptions \
  -H "Authorization: Bearer sk-df-xxx" \
  -F file=@audio.mp3 \
  -F model=whisper-1

Response

{
  "text": "Hello, how are you today?"
}

Audio Speech (TTS)

Generate speech from text.

POST/v1/audio/speech

Parameter	Type	Required	Description
model	string	Yes	TTS model ID
input	string	Yes	Text to speak
voice	string	No	Voice ID. Default: alloy
speed	number	No	Speed (0.25-4.0). Default: 1.0

curl https://api.dragonfly.dev/v1/audio/speech \
  -H "Authorization: Bearer sk-df-xxx" \
  -H "Content-Type: application/json" \
  -d '{"model": "tts-1", "input": "Hello world", "voice": "alloy"}' \
  --output speech.mp3

Crypto Payment

Create a USDT payment to add credits.

POST/v1/billing/crypto/create-payment

Parameter	Type	Required	Description
amount_cents	integer	Yes	Amount in cents (e.g. 1000 = $10.00)

curl https://api.dragonfly.dev/v1/billing/crypto/create-payment \
  -H "Authorization: Bearer sk-df-xxx" \
  -H "Content-Type: application/json" \
  -d '{"amount_cents": 1000}'

Response

{
  "payment_id": "pay_abc123",
  "amount_usdt": "10.00",
  "address": "TXxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
  "network": "TRC-20",
  "expires_at": "2026-02-17T22:00:00Z"
}

Models & Pricing

Prices per million tokens.

DeepSeek

Model ID	Input	Output	Context	Capabilities
deepseek/deepseek-chat	$0.50	$1.50	128K	Chat, Code
deepseek/deepseek-reasoner	$2.00	$8.00	128K	Reasoning
deepseek/janus-pro-7b	—	—	—	Image Gen

Qwen

Model ID	Input	Output	Context	Capabilities
qwen/qwen3-235b-a22b	$1.00	$4.00	128K	Chat, Code
qwen/qwen3-30b-a3b	$0.50	$2.00	128K	Chat
qwen/wan2.1-t2v	—	—	—	Video Gen

Moonshot

Model ID	Input	Output	Context	Capabilities
moonshot/kimi-k2	$1.00	$4.00	128K	Chat, Agents

Zhipu

Model ID	Input	Output	Context	Capabilities
zhipu/glm-5-0131	$1.00	$4.00	128K	Multimodal

Doubao

Model ID	Input	Output	Context	Capabilities
doubao/doubao-1.5-pro-256k	$0.30	$0.90	256K	Chat

Rate Limits

Plan	Requests/min	Tokens/min
Free	10	40,000
Starter	60	200,000
Pro	300	1,000,000
Enterprise	Unlimited	Unlimited

Rate limit headers are included in every response: X-RateLimit-Remaining, X-RateLimit-Reset.

Error Codes

Code	Type	Description
400	bad_request	Invalid request parameters
401	unauthorized	Missing or invalid API key
403	forbidden	Insufficient balance or permissions
429	rate_limit_exceeded	Too many requests. Retry after X-RateLimit-Reset.
500	internal_error	Server error. Retry with exponential backoff.
502	upstream_error	Upstream provider error

Error Response Format

Response

{
  "error": {
    "message": "Insufficient balance",
    "type": "forbidden",
    "code": 403
  }
}