LLM To API

YOUR AI ACCOUNTS. YOUR API.

Your AI accounts.An API for your tools and code.

Connect an AI account, create an API key, then add the URL, key and model to your tool or code. Manage the configuration and every request in one place.

Connecting a real account requires an active paid plan and a supported AI account. Provider subscriptions or usage are billed separately.

Your API connection detailsExample · not a real key
Base URL
https://gateway.llmtoapi.com/v1
API Key
sk-••••••••••••••••••••••••
Model
Choose from your connected account
Protocol
Responses / Chat / Messages
Models and protocols depend on the sourceSee the setup steps

Bring your AI accounts into your work.

Create separate keys for your apps. Choose a supported protocol and use the tools you already know.

Tools with custom API settings

Enter the Base URL, key and model. Use the API setup panel to check the required protocol and configuration.

Your own code

Copy a cURL or SDK example for your protocol and build from the first request.

Automated workflows

Give each workflow a key, control models and expiry, and trace issues in request logs.

From your account to your first request.

An active plan is required to connect. Check authorization, keys and request results in your dashboard.

01

Connect your AI account

Use an available subscription connection or API key and check its models.

02

Create your AI API

Choose a source. Models are selected by default; adjust the name and expiry as needed.

03

Connect your tools or code

Copy the configuration, send a request and check its result in request logs.

Find the right connection for your account.

Subscription and API accounts are different products. Current platform availability is shown below; models and allowance depend on your provider account.

ProductAuthorizationProtocolsAvailability
Codex subscriptionAccount authorizationChat Completions / ResponsesAvailable with a supported plan
Anthropic APIAPI KeyMessagesAvailable with a supported plan
GLM APIAPI KeyChat CompletionsAvailable with a supported plan
Kimi APIAPI KeyChat CompletionsAvailable with a supported plan
Kimi Code subscriptionAccount authorizationMessagesAvailable with a supported plan
OpenAI APIAPI KeyChat Completions / ResponsesAvailable with a supported plan

Input and tool-calling capabilities vary by model. Read about protocols and capabilities

Make the first call from your code.

This example uses Chat Completions. The API setup panel provides configuration for your selected model and protocol.

Read the integration guide

Start with a request

API example
curl https://gateway.llmtoapi.com/v1/chat/completions \
  -H "Authorization: Bearer $LLMTOAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"MODEL_FROM_YOUR_CONNECTION","messages":[{"role":"user","content":"Hello"}]}'

BEFORE YOU CONNECT

Understand the connection before you pay.

You bring the AI account. We host the connection, manage separate keys and help you inspect requests. Registration is free; connecting a real account requires an active paid plan.

Why authorize an account?
The platform needs credentials to send requests to your provider on behalf of your apps. Subscription sign-in happens on the provider’s official page; API connections use the provider key you supply. Your apps use separate platform-generated keys.
What is stored?
We store account and plan information, connection settings, encrypted authorization credentials and recoverable API keys, plus request status, model, usage, timing and errors. Request body storage is controlled in account settings; when enabled, it is encrypted and subject to retention limits.
How do I stop access?
Pause a connection to stop new requests while retaining credentials. Delete it to clear credentials held by the platform and schedule related data cleanup. To revoke provider-side access, also revoke the connection with the provider where supported, or revoke or rotate your provider API key.
Platform fees and provider limits
Platform fees cover the hosted gateway, connections, app keys and request history, within your plan’s connection, concurrency and retention limits. They exclude provider subscriptions and API usage, do not increase or reset provider allowances, and do not bypass rate limits. Check that your account, model and intended use are supported first.
Read the access and data guide →

PLANS & ACCESS

Clear plans. Clear usage boundaries.

The platform hosts connections, manages APIs and keeps request history. Your AI accounts provide model access and allowance.

Starter

Connect your own AI accounts with one URL and API key.

USD 9.9/ month
  • 2 provider accounts
  • 2 total concurrent requests
  • 5 API keys
  • 30 days of request history
Review plan and access
Pro

Manage more accounts and concurrency across multiple apps.

USD 19.9/ month
  • 5 provider accounts
  • 5 total concurrent requests
  • 5 API keys
  • 30 days of request history
Review plan and access

After registering and verifying your email, choose a plan in Billing. An active plan is required to connect; provider fees are separate.

FAQ

Before your first request.

From connecting your first account to managing several apps, find the answers here.

Product and connections

What does LLM To API help me do?

Turn your own AI accounts into APIs for your tools and code. Connect an account in My access, create an AI API, then choose Use API to get the Base URL, key, model and request examples. Manage separate keys for your apps and inspect request results and usage in the dashboard.

Can I use my Codex subscription through an AI API?

Yes. With LLM To API, you can use your Codex subscription through an AI API. Connect your own Codex account, get a Base URL and API key, and use them in compatible AI clients, your own apps and automated workflows.

Supports Chat Completions and Responses using your existing subscription allowance.

Are Grok, Claude, Kimi Code and GLM Coding Plan supported?

These integrations are in preview, with real subscription authorization and requests still awaiting verification. They can be used in My access when the platform enables the integration and your plan includes it. Seeing a provider name does not grant access.

Grok, Claude and Kimi Code use their respective account authorization flows. GLM Coding Plan uses a Coding Plan API key for the selected region. Ordinary Anthropic, Kimi and GLM APIs are separate products from subscription access; their credentials are not interchangeable.

What can I build with the API?

Use it for AI chat, coding assistance, text processing and AI features in your apps. Configure a client that accepts a custom API endpoint, or send requests from your own code and pass the results into a workflow. Available capabilities depend on the connected model and protocol.

Which models can I use?

Model availability depends on your provider account, connection checks and the models selected for your AI API. After connecting an account, check the models available to that connection and use the model names shown in your configuration. Provider catalog counts do not mean your account has access to every listed model.

Getting started

What do I need to get started?

You need an email address, your own AI account and a client or app that accepts a custom API endpoint. Enter the email verification code after registering to sign in automatically. Activate a plan in Billing, then connect an account in My access. Once connected, choose Create my AI API, then Use API to copy the configuration. Connecting an account does not automatically create a key.

Connecting an account requires an active platform plan. The home and billing pages show current checkout availability and plan prices.

Can I use it without writing code?

Yes. If your client has settings for a Base URL, API key and model name, enter the values from your API configuration. You only need to write code when integrating AI features into your own program.

Can I keep using my current client or SDK?

Yes, if it supports a custom API endpoint and a protocol available on your connection. Replace its Base URL and API key with your API values and select an available model. Clients that only use a fixed provider endpoint cannot connect directly.

Which API formats are supported?

The platform provides formats including Chat Completions, Responses and Anthropic Messages. Codex subscription connections support a Chat Completions compatible endpoint and Responses. Follow your API configuration examples when selecting a protocol and model; supported features vary by connection.

Do I need to run my own server or leave my computer on?

The hosted API endpoint does not require you to deploy a gateway or keep a personal computer running to forward requests. Your client or app needs an internet connection when making requests, and your provider authorization and platform plan must remain active.

Pricing and usage

How do I pay, and what if access is not activated afterward?

Choose a plan in Billing, complete payment through PayPal and return to the site. Access is activated after payment is verified; opening checkout or approving a subscription alone does not confirm payment. If verification is pending, check the order in Billing before purchasing again. Contact support with the order ID and payment time if needed, never your payment password.

Does the platform fee include an AI subscription or extra model usage?

No. The platform fee covers API access, hosting and management. You supply your own provider account. Subscription connections use that account’s available benefits; ordinary API-key connections follow the provider’s API billing. Budget for the platform plan and your provider subscription separately.

Does API access increase my allowance? What happens when it runs out?

API access does not increase or reset your provider allowance. Requests still use the original account’s available usage and remain subject to its model access and rate limits. If the allowance runs out, wait for it to renew or use another supported connection with available usage. Repeated retries do not restore an allowance.

Can I connect multiple accounts and use several apps?

Connect your own AI accounts and create a separate AI API for each app. Select the connected account when creating an API; the Source column identifies services such as Codex. Your plan controls available integrations, connections, keys and concurrency, while provider account limits also apply.

Account management and troubleshooting

Can I create a separate API key for each app?

Yes. Choose an account when creating an AI API. All available models on that connection are selected by default, and you can narrow the selection. The generated name is editable. Leave expiry blank for no expiry, or choose 30 days, 3 months, 1 year or a date. Keys start with sk- and can be copied, revealed, paused or deleted. Each key can call only its selected models.

Where do I get configuration and test the API? Is streaming supported?

Choose Use API in Getting started or My access. In the same window, select a model and protocol, view cURL, Python SDK, environment and compatible client settings, or switch to Test API to send a message and see streaming results. Tests make real requests to your provider account and consume its allowance.

Your external tool must support the selected model’s protocol. Copy the full model ID and do not append /v1 twice. After a successful platform test, send a request from your own tool and confirm the result in Request logs.

How are credentials handled? Does every client need my provider credentials?

The platform uses your provider authorization or API credentials to connect upstream and encrypts stored credentials. Clients use the API keys generated by the platform, so you do not need to enter provider credentials into every client. Keep both types private and leave them out of support tickets, screenshots and public code.

Can I inspect usage, request history and request bodies?

Your account shows usage, request status, models, latency and errors. Request-body capture is controlled in account settings. When enabled, new request bodies are stored according to your plan and retention settings and can be deleted from your account. Bodies that were never captured cannot be recovered.

Model usage reflects the data returned by the provider. Requests without complete usage data are marked as unknown.

What should I check if a request fails?

First check that the Base URL, API key, model name and protocol match your API configuration. Then check your plan, key expiry and connection status. If provider authorization has expired, follow the connection’s instructions to reauthorize or update credentials. For rate limits or exhausted allowances, reduce request frequency or wait for usage to become available.

If the issue continues, open a support ticket with the request ID, time and error message so the request can be traced.

What if a key leaks or I want to stop an app from making requests?

Pause the key in My access to block new requests. If it is no longer needed, choose Delete and type DELETE to confirm. The AI API record and key are permanently removed; historical requests and usage remain subject to retention settings. Create a new key and update clients that still need access. If only account authorization has expired, update the original connection without recreating every key.