API reference

Top Tools AI API

One OpenAI-compatible endpoint for every model on Top Tools AI. Keep your existing SDK, change the base URL and API key, and pick a model by name.

Base URL

https://top-tools-ai.com/api/v1

Auth

Bearer API key

Format

JSON · streaming (SSE)

01 · Start here

Quickstart

Make your first request in three steps.

1Create an API key in your dashboard.
2Point your OpenAI client at https://top-tools-ai.com/api/v1.
3Set model to a model you have access to, such as Top-Tools-Ai.

curl https://top-tools-ai.com/api/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Top-Tools-Ai",
    "messages": [
      { "role": "user", "content": "What is the capital of France?" }
    ]
  }'

Python

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://top-tools-ai.com/api/v1",
)

response = client.chat.completions.create(
    model="Top-Tools-Ai",
    messages=[{"role": "user", "content": "What is the capital of France?"}],
)

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

TypeScript

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "YOUR_API_KEY",
  baseURL: "https://top-tools-ai.com/api/v1",
});

const response = await client.chat.completions.create({
  model: "Top-Tools-Ai",
  messages: [{ role: "user", content: "What is the capital of France?" }],
});

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

fetch

const response = await fetch("https://top-tools-ai.com/api/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "Top-Tools-Ai",
    messages: [{ role: "user", content: "What is the capital of France?" }],
  }),
});

const data = await response.json();
console.log(data.choices[0].message.content);

Authentication

Send your API key as a Bearer token in the Authorization header of every request.

http

Authorization: Bearer sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx

Keep your key secret. Never expose it in client-side code or public repositories.

Models

Each model is unlocked on its own, and you can hold access to several at once. Your API key works with every model you currently have access to. Click an ID to copy it.

Top-Tools-Ai

Top Tools AI · 512K context

Image GenVisionTool CallsDeep Thinking

Free daily

10M free tokens/day · unlimited with a paid plan

Step 5 Preview

StepFun · 1M context

VisionTool CallsDeep Thinking

Subscription

Unlimited with a paid plan

Qwen-3.8-Max

Qwen · 1M context

VisionTool CallsDeep Thinking

Subscription

Unlimited with a paid plan

GLM-5.2

Z.AI · 1M context

Tool CallsDeep Thinking

Subscription

Unlimited with a paid plan

GLM-5.3

Z.AI · 1M context

Tool CallsDeep Thinking

Subscription

Unlimited with a paid plan

GLM-5.3-Flash

Z.AI · 1M context

VisionTool CallsDeep Thinking

Subscription

Unlimited with a paid plan

MiMo-V2.5

Xiaomi · 1M context

VisionTool CallsDeep Thinking

Subscription

Unlimited with a paid plan

MiMo-V2.5-Pro

Xiaomi · 1M context

VisionTool CallsDeep Thinking

Subscription

Unlimited with a paid plan

MiMo-V2.6-Pro

Xiaomi · 1M context

VisionTool CallsDeep Thinking

Subscription

Unlimited with a paid plan

MiMo-V2.6-Flash

Xiaomi · 1M context

VisionTool CallsDeep Thinking

Subscription

Unlimited with a paid plan

DeepSeek-V4-Pro

DeepSeek · 1M context

Tool CallsDeep Thinking

Subscription

Unlimited with a paid plan

DeepSeek-V4-Flash

DeepSeek · 1M context

Tool CallsDeep Thinking

Subscription

Unlimited with a paid plan

DeepSeek-V4.1-Flash

DeepSeek · 1M context

VisionTool CallsDeep Thinking

Subscription

Unlimited with a paid plan

DeepSeek V4.1 Flash-1017

DeepSeek · 1M context

VisionTool CallsDeep Thinking

Subscription

Unlimited with a paid plan

MiniMax-M3

MiniMax · 1M context

VisionTool CallsDeep Thinking

Subscription

Unlimited with a paid plan

MiniMax-M3.1-Flash

MiniMax · 1M context

VisionTool CallsDeep Thinking

Subscription

Unlimited with a paid plan

MiniMax-M2.7

MiniMax · 204K context

Tool CallsDeep Thinking

Subscription

Unlimited with a paid plan

Kimi-K2.7-Code

Moonshot · 256K context

VisionTool CallsDeep Thinking

Subscription

Unlimited with a paid plan

Kimi-K2.6

Moonshot · 256K context

VisionTool CallsDeep Thinking

Subscription

Unlimited with a paid plan

gpt-5.6-sol

OpenAI · 1M context

Tool CallsDeep Thinking

Pay as you go

$1.00 / 1M input · $8.00 / 1M output

claude-opus-5

Anthropic · 1M context

Tool CallsDeep Thinking

Pay as you go

$3.00 / 1M input · $13.00 / 1M output

DeepSeek-V4-Flash-Vision-Exp

DeepSeek · 1M context

VisionTool CallsDeep Thinking

Pay as you go

$0.17 / 1M input · $0.28 / 1M output

Welcome balance

New accounts get a one-time 10 million-token balance for non-PAYG models except Top-Tools-Ai. Top-Tools-Ai has its own separate 10 million-token daily allowance.

Paid plans

Plans unlock a model for 3, 30, or 90 days with no usage caps. See plan pricing. PAYG models need a separate paid balance.

Chat completions

POST /chat/completions follows the OpenAI chat format. Requesting a model you don't have access to returns a 403.

Response

json

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "model": "Top-Tools-Ai",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "The capital of France is Paris."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 24,
    "completion_tokens": 9,
    "total_tokens": 33
  }
}

Streaming

Set "stream": true to receive server-sent events, exactly like the OpenAI API.

bash

curl https://top-tools-ai.com/api/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "MiMo-V2.6-Pro",
    "stream": true,
    "messages": [{ "role": "user", "content": "Write a haiku about APIs." }]
  }'

Tool calls

Pass OpenAI-style tools. Run the call yourself and send the result back as a tool message. Models marked Tool Calls above support this.

request body

{
  "model": "GLM-5.3-Flash",
  "messages": [{ "role": "user", "content": "What's the weather in Paris?" }],
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "get_weather",
        "description": "Get the current weather for a city",
        "parameters": {
          "type": "object",
          "properties": { "city": { "type": "string" } },
          "required": ["city"]
        }
      }
    }
  ]
}

Vision

Send images as image_url content parts, using a URL or a base64 data URL. Models marked Vision accept them.

request body

{
  "model": "Qwen-3.8-Max",
  "messages": [
    {
      "role": "user",
      "content": [
        { "type": "text", "text": "Describe this image." },
        { "type": "image_url", "image_url": { "url": "data:image/png;base64,..." } }
      ]
    }
  ]
}

Image generation

POST /images/generations returns a URL to the generated image.

bash

curl https://top-tools-ai.com/api/v1/images/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A futuristic city at night, neon lights, photorealistic",
    "n": 1,
    "size": "1024x1024"
  }'

response

{
  "created": 1720000000,
  "data": [
    { "url": "https://..." }
  ]
}

Limits

requests / minute

Shared across all of your API keys. May be temporarily reduced to 30 during extremely high demand.

simultaneous requests

Per user, across chat completions and image generation. The 6th returns 429.

500

admin concurrency

Admin accounts may run up to 500 active requests. The 501st returns 429.

API Limits Plus costs $9.99/month and adds 10 concurrent requests and 30 RPM, normally bringing your account to 15 simultaneous requests and 75 requests per minute. You can start the upgrade from the dashboard.

When you hit a concurrency limit, retry after one of your active requests finishes.

Errors

Errors return a JSON body with an error object.

json

{
  "error": {
    "message": "Too many concurrent requests",
    "type": "rate_limit_error",
    "code": "concurrency_limit_exceeded"
  }
}

401—Invalid or missing API key.

403—Model access denied. You don't have an active subscription for the requested model.

429rpm_limit_exceededMore than 45 requests per minute across your API keys.

429concurrency_limit_exceededMore than 5 simultaneous requests for your account (500 for admins).

502provider_unavailableThe model provider could not complete the request.

502provider_empty_responseThe response ended without visible text after the bounded retry.

500—Internal gateway error.

Ready to build?

Create an API key in the dashboard and send your first request.

Go to dashboard