AIFastAIFast Developer Docs
DEVELOPER TOOLS

AI development tool custom API access center

Provides centralized API configuration, migration and acceptance tutorials for Codex, Claude Code, Cursor, Cursor2API, OpenClaw, Hermes Agent, Dify, OpenWebUI, Chatbox and Cherry Studio.

Choose a guide by use case Create Account
ANSWER FIRST

Remember these four things first

Confirm the agreement and evidence first, and then start changing configurations or replacing services.

  1. 01

    First confirm whether the tool actually requires Chat Completions, Responses, or Anthropic Messages.

  2. 02

    Store API keys in dedicated environment variables, not in repositories, screenshots, or frontend code.

  3. 03

    After completing the minimal text request, verify streaming, tool calls, file operations, and session recovery.

  4. 04

    Confirm the final host and path from the request log. You cannot judge that the configuration has taken effect based on the client interface alone.

GUIDED PATH

Find the guide for your issue

View all tutorials
01 · Tool accessCodex API gateway configuration tutorial: Custom Provider and Responses API

Configure a Codex custom provider for the Responses API, set environment variables and model IDs, then verify tool calls with a minimal file-editing task.

View steps 02 · Tool accessClaude Code custom API configuration tutorial

Understand Claude Code's environment variables, compatibility boundaries, and security configuration methods.

View steps 03 · Tool accessCursor custom API configuration and compatibility check

Configure a custom API key, Base URL, and live model ID, then verify the capability boundaries of standard chat and Agent mode.

View steps 04 · Tool accessCursor2API common error reports, risk checks and standard API migration

Differentiate Cursor2API from official custom APIs, troubleshoot output truncation, tool calls and upstream changes, and migrate to standard APIs according to the acceptance form.

View steps 05 · Tool accessConfigure AIFast in OpenClaw

Add a standalone custom provider, configure API adapter, Base URL, model ID and security authentication.

View steps 06 · Tool accessConfigure AIFast in Hermes Agent

Configure Base URL, API Key and real model ID using hermes model and custom endpoint.

View steps 07 · Tool accessConfigure the AIFast API in Dify

Configure the Base URL, API Key, model type and real model ID, and verify the workflow and knowledge base nodes.

View steps 08 · Tool accessConfigure AIFast in OpenWebUI

Add an OpenAI Compatible connection, load a list of models, and troubleshoot address, container network, and streaming output issues.

View steps 09 · Tool accessChatbox and Cherry Studio integration guide

Add an OpenAI-compatible provider and configure its API endpoint, API key, and live model ID.

View steps
COMMON QUESTIONS

FAQ

These answers are also written into structured data on the page for easy search and reference.

Why can’t the same Base URL be filled directly into all AI tools?

Because the protocols, path splicing, and authentication variables used by the tools may be different. Codex, Claude Code and ordinary OpenAI Compatible clients must be configured separately according to their respective protocols.

Connection test successful, why is the tool call still unavailable?

Connection tests usually only cover domain names, certifications, or plain text. Tool calls also depend on request fields, streaming events, result callbacks, and the capability boundaries of the client's current version.

How to confirm that the client has indeed accessed the custom API?

Combine the client status page, desensitized diagnostic information and server request logs to confirm the final request host, path, model ID and status code. Don't just look at the model dropdown box name.

VERIFIED SOURCES

Reference and Check Sources

Page verification date: 2026-07-18
Confirm the model and protocol first, then create a test key

Use the console's live catalog as the source of truth for model IDs, prices, and availability.