
APIAny API connects every production model
APIAny, the Universal All-in-One Self-Governing AI API Platform
APIAny.Dev is a unified OpenAI-compatible API gateway for leading LLM, image, video, and audio models. Compare APIAny API pricing, read APIAny API docs, and start building production apps, agents, and workflows.
By APIAny EditorialPublished Updated
Selected creations
Real image and video examples made through our models. Preview freely; using a preset never starts generation.












Models & pricing
Which APIAny API models can you call?
APIAny is a live catalog of production chat, image, and video models billed in prepaid credits, with prices shown on each card.
Z-Image
Per request
≈ $0.0015
3 credits / req
GPT Image 2.5
Per request
≈ $0.03
60 credits / req
Nano Banana
Per request
≈ $0.0075
15 credits / req
Nano Banana Pro
Per request
≈ $0.04
80 credits / req
Seedance 2.0
Per request
≈ $0.587
1,174 credits / req
Seedance 1.5
Per request
≈ $0.075
150 credits / req
Veo 3.1
Per request
≈ $0.11
220 credits / req
Gemini Omni
Per request
≈ $0.12
240 credits / req
NSFW Image Detection
Per request
≈ $0.0005
1 credits / req
GPT 5.5
1,000 / 4,000 credits / 1M
DeepSeek V4
140 / 280 credits / 1M
GLM 5.3 Flash
280 / 980 credits / 1M
Claude Opus 4.8
3,000 / 15,000 credits / 1M
Gemini 3.5 Flash
150 / 600 credits / 1M
How do you use APIAny from any Agent with one prompt?
Copy a single APIAny API prompt to Codex, Claude, Cursor, or any agent so it understands every APIAny API model and endpoint, then ask your questions.
Please read APIAny.Dev's documentation index below and answer my questions based on it: https://docs.apiany.ai/llms.txt About APIAny.Dev: a unified OpenAI-compatible API for the models publicly listed on APIAny.Dev: chat (GPT 5.5, GPT 5.4, Claude Opus 4.8, Gemini 3.5 Flash, DeepSeek V4, GLM-5.2), image (Nano Banana, Nano Banana 2, Nano Banana Pro, GPT Image 2), video (Seedance 2.0, Veo 3.1, Gemini Omni, Kling), and audio workflows such as Suno. Pay only for successful requests. My question: How do I generate a short Veo 3.1 video in Python?
How do you complete a 3-minute APIAny API integration?
A 3-minute APIAny integration is a base-URL and API-key change that lets you call chat, image, video, and audio models through one gateway.
Sign Up & Create Key
Register an APIAny account and generate your APIAny API key in the dashboard - no credit card required.
Update Configuration
Set your APIAny API base URL to https://apiany.ai. OpenAI SDK users only need to modify one line of code.
Start Calling Models
Access GPT, Claude, Gemini, image, video, and audio models through APIAny API.
curl --request POST \
--url https://apiany.ai/v1/chat/completions \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
"model": "gpt-5.5",
"messages": [
{
"role": "system",
"content": "You are a professional AI assistant."
},
{
"role": "user",
"content": "Tell me about the history of artificial intelligence."
}
]
}'from openai import OpenAI
client = OpenAI(
api_key="sk-...",
base_url="https://apiany.ai/v1",
)
completion = client.chat.completions.create(
model="gpt-5.5",
messages=[
{"role": "system", "content": "You are a professional AI assistant."},
{"role": "user", "content": "Tell me about the history of artificial intelligence."},
],
)
print(completion.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.APIANY_API_KEY,
baseURL: "https://apiany.ai/v1",
});
const completion = await client.chat.completions.create({
model: "gpt-5.5",
messages: [
{ role: "system", content: "You are a professional AI assistant." },
{ role: "user", content: "Tell me about the history of artificial intelligence." },
],
});
console.log(completion.choices[0]?.message?.content);package main
import (
"bytes"
"fmt"
"io"
"net/http"
)
func main() {
body := []byte(`{
"model": "gpt-5.5",
"messages": [
{"role": "system", "content": "You are a professional AI assistant."},
{"role": "user", "content": "Tell me about the history of artificial intelligence."}
]
}`)
req, _ := http.NewRequest("POST", "https://apiany.ai/v1/chat/completions", bytes.NewReader(body))
req.Header.Set("Authorization", "Bearer sk-...")
req.Header.Set("Content-Type", "application/json")
res, err := http.DefaultClient.Do(req)
if err != nil {
panic(err)
}
defer res.Body.Close()
data, _ := io.ReadAll(res.Body)
fmt.Println(string(data))
}import java.net.URI;
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;
public class APIAnyDemo {
public static void main(String[] args) throws Exception {
String body = """
{
"model": "gpt-5.5",
"messages": [
{"role": "system", "content": "You are a professional AI assistant."},
{"role": "user", "content": "Tell me about the history of artificial intelligence."}
]
}
""";
HttpRequest request = HttpRequest.newBuilder()
.uri(URI.create("https://apiany.ai/v1/chat/completions"))
.header("Authorization", "Bearer sk-...")
.header("Content-Type", "application/json")
.POST(HttpRequest.BodyPublishers.ofString(body))
.build();
HttpResponse<String> response = HttpClient.newHttpClient()
.send(request, HttpResponse.BodyHandlers.ofString());
System.out.println(response.body());
}
}<?php
$payload = [
"model" => "gpt-5.5",
"messages" => [
["role" => "system", "content" => "You are a professional AI assistant."],
["role" => "user", "content" => "Tell me about the history of artificial intelligence."],
],
];
$ch = curl_init("https://apiany.ai/v1/chat/completions");
curl_setopt_array($ch, [
CURLOPT_RETURNTRANSFER => true,
CURLOPT_POST => true,
CURLOPT_HTTPHEADER => [
"Authorization: Bearer sk-...",
"Content-Type: application/json",
],
CURLOPT_POSTFIELDS => json_encode($payload),
]);
$response = curl_exec($ch);
curl_close($ch);
echo $response;
?>Why APIAny.Dev
Why do teams choose APIAny API before they integrate?
APIAny is one OpenAI-compatible API key, catalog, and bill for chat, image, video, and audio models.
Clear APIAny API model access
Browse APIAny model capabilities, pricing, and API docs before you integrate, then call every model through APIAny's OpenAI-compatible API gateway.
Flexible APIAny API routing choices
Route GPT, Claude, Gemini, image, video, audio, and specialist models through the APIAny API platform.
APIAny API built for production use
APIAny API auth, credits, task tracking, and unified billing keep production teams moving without stitching services together.
Explore models by type
What model classes does APIAny API cover?
APIAny groups public models into chat, image, video, and audio classes so you can pick a capability, then a specific model id.
Compare AI model families
How do you choose an APIAny model family?
An APIAny model family is a set of related versions that share one integration surface, so you can compare cost and quality without changing endpoints.
OpenAI
GPT API Family
Flagship reasoning, coding, and low-latency GPT-compatible models through one endpoint.
ByteDance
Seedance API Family
Text-to-video, image-to-video, reference media, and Seedance image generation in one family.
Gemini API Family
Google multimodal models for vision, search-grounded tasks, and large-context reasoning.
OpenAI
GPT Image API Family
High-quality generation and editing for product images, ads, concept art, and creative pipelines.
Built for production
Why is APIAny a production API platform, not a demo proxy?
APIAny is a production API platform with auth, credits, routing, and usage records — not a demo proxy.
Never Fail a Request
APIAny API retries and high availability keep your requests succeeding even when a provider has issues.
One Dashboard, Total Control
Manage your APIAny API keys, credits, usage, and billing from one dashboard.
Smart Model Routing
APIAny API routing helps you get reliable performance at the best available price, without changing client code.
Transparent Model Pricing
APIAny API shows input, output, request, image, and video costs clearly before your users generate anything.
Integration in 4 steps
How do you go from an APIAny account to the first production call?
The APIAny path to production is sign-up, an API key, an OpenAI-compatible request, and credit-tracked usage in one dashboard.
01
Sign Up
Create an APIAny API account and land in the dashboard with credits, billing, and usage already wired.
02
Create APIAny API Key
Issue APIAny API scoped keys for apps, agents, workers, or internal tools without touching provider secrets.
03
Choose Integration Method
Call APIAny API chat, image, and video endpoints or use APIAny API tasks for async media jobs.
04
Start Calling
Ship APIAny API production requests with credits, costs, callbacks, and task history tracked automatically.
Sources
Which official APIs does APIAny document against?
APIAny documents its OpenAI-compatible gateway against provider APIs. The quotations below come from those official references.
The Chat Completions API endpoint will generate a model response from a list of messages comprising a conversation.
The Gemini API provides access to Google's most capable generative AI models.
The Images API provides several endpoints that let you generate images from text prompts or create edits of existing images.
FAQ
What should you know before you integrate APIAny?
These answers cover what APIAny is, which models you can call, how OpenAI-compatible endpoints work, and how prepaid credits are billed.
What is APIAny.Dev?
APIAny.Dev is a unified AI model platform. With APIAny, you access leading LLM, image, video, and audio models through one OpenAI-compatible API gateway, and pay with prepaid credits.
Which models are available?
The catalog spans GPT, Claude, Gemini, DeepSeek, GLM, Seedance, Kling, MiniMax, Nano Banana, Suno, and more across text, image, video, and audio. Browse the full list on the Models page.
Are the endpoints OpenAI-compatible?
Yes. APIAny chat completions, image, and video generation use an OpenAI-compatible request shape, and media endpoints return task ids for polling, so existing clients can migrate by changing the base URL and key.
How does pricing and credits work?
It is pay-as-you-go with prepaid credits. $1 = 1,000 credits, and larger recharges include bonus credits. Each model shows its credit cost up front, and credits are deducted per request.
How can I pay?
Payments are currently processed through Stripe. Recharges are one-time credit purchases, and there are no subscriptions.
Do credits expire?
No. Credits never expire. Once recharged, they stay in your balance until you use them.
Can I create API keys?
Yes. Create scoped APIAny keys from your dashboard. Requests are validated against active keys, scopes, rate limits, and your credit balance.
What happens when a media job takes time?
Image and video generation run as async tasks. You get a task id immediately, then poll status or receive a callback. Credits are charged on success and refunded if a job fails.
