📖 API Documentation

OpenAI-compatible interface · One-line integration · Streaming support

🔑 Authentication

All API requests require an API key. Include it in the Authorization header:

Authorization: Bearer tk-your-api-key

Get your API key from the Dashboard after registration. Keys have the prefix tk- and are shown only once upon creation.

⚠️ Keep your API key secret! Do not share it or commit it to version control. Use environment variables.

📋 Available Models

Model ID Type Context Input /M tok Output /M tok

16 models available across 6 model families

DeepSeek V4 · V3.2 · Qwen3.5 · Kimi K2 · GLM-5 · MiniMax M2 · Llama 3.3

View All Models curl https://www.flintapi.ai/v1/models

GET /v1/models — List all available models 

curl https://www.flintapi.ai/v1/models

💬 Chat Completions

POST /v1/chat/completions

Send a conversation and get a model-generated response. Supports multi-turn dialogue and system prompts.

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://www.flintapi.ai/v1",
    api_key="tk-your-api-key"
)

response = client.chat.completions.create(
    model="deepseek-v4-flash",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Explain quantum computing in simple terms."}
    ],
    max_tokens=500,
    temperature=0.7
)

print(response.choices[0].message.content)

cURL

curl https://www.flintapi.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer tk-your-api-key" \
  -d '{
    "model": "deepseek-v4-pro",
    "messages": [
      {"role": "system", "content": "You are an expert programmer."},
      {"role": "user", "content": "Write a Python function to find prime numbers up to N."}
    ],
    "max_tokens": 300,
    "temperature": 0.3,
    "stream": false
  }'

Response Format

{
  "id": "chatcmpl-xxx",
  "object": "chat.completion",
  "created": 1717891234,
  "model": "deepseek-v4-flash",
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "Quantum computing uses qubits..."
    },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 25,
    "completion_tokens": 150,
    "total_tokens": 175
  }
}

Streaming (SSE)

# Python streaming example
stream = client.chat.completions.create(
    model="deepseek-v4-flash",
    messages=[{"role": "user", "content": "Tell me a story about AI"}],
    stream=True
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

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

⚙️ Parameters

Parameter Type Default Description
model string Required Model ID: deepseek-v4-flash or deepseek-v4-pro
messages array Required Conversation messages with role and content
max_tokens int 1024 Maximum tokens to generate
temperature float 0.7 Sampling temperature (0=deterministic, 2=random)
top_p float 1.0 Nucleus sampling threshold (0–1)
stream bool false Enable SSE streaming response
stop array null Stop sequences to halt generation
presence_penalty float 0 Topic novelty bias (-2.0 to 2.0)

🚦 Rate Limits

To ensure fair resource allocation across all users, FlintAPI enforces the following rate limits:

Tier Requests / Minute Tokens / Minute Concurrent Requests
Standard 60 100,000 5
Enterprise Custom Custom Custom

When rate limited, the API returns HTTP 429. Headers include Retry-After (seconds). Need higher limits? Contact support@flintapi.ai.

⚠️ Error Codes

401

Missing or Invalid API Key

No Authorization header provided, or the key is invalid.

402

Insufficient Balance

Your account balance cannot cover the estimated cost of this request.

403

Access Denied

Your API key or account has been disabled. Contact support.

429

Rate Limit Exceeded

Too many requests. Check the Retry-After header and slow down.

500

Internal Server Error

Something went wrong on our end. Please try again later.

503

Service Unavailable

The inference backend is temporarily unavailable. Retry shortly.

🔌 SDK Examples

JavaScript / Node.js

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://www.flintapi.ai/v1",
  apiKey: "tk-your-api-key"
});

const response = await client.chat
  .completions.create({
    model: "deepseek-v4-flash",
    messages: [
      {role: "user", content: "Hello!"}
    ]
  });

console.log(response.choices[0]
  .message.content);

Go

import "github.com/sashabaranov/go-openai"

config := openai.DefaultConfig("tk-key")
config.BaseURL = "https://www.flintapi.ai/v1"
client := openai.NewClientWithConfig(config)

resp, err := client.CreateChatCompletion(
  ctx,
  openai.ChatCompletionRequest{
    Model: "deepseek-v4-pro",
    Messages: []openai.ChatCompletionMessage{
      {Role: "user", Content: "Hello"},
    },
  },
)