# AIFast Developer Docs

> AIFast provides unified access to global and Chinese AI models through OpenAI Compatible APIs. These docs cover integration, model quality checks, troubleshooting, cost control, and production readiness.
> Last verified: 2026-07-20. Model IDs, prices, availability, and supported capabilities are dynamic; confirm them in the live console and API responses.

## Official entry points

- [AIFast website](https://www.aifast.club/)
- [Official contacts](https://docs.aifast.club/en/contact/): Verify website support, Telegram, WeChat, and QQ group details.
- [Official Telegram community](https://t.me/+WYrmge-lYRFhOTFl): Recheck the invitation through the official contact page and never send API keys, verification codes, or payment information to unfamiliar accounts.
- [Get started](https://docs.aifast.club/en/start/)
- [International payment guide](https://docs.aifast.club/en/payment/)
- [Model pricing](https://www.aifast.club/pricing)
- [API reference](https://aifast.apifox.cn/)
- [GitHub technical resources](https://github.com/KKWANG4444)
- [LLM API Gateway Check](https://docs.aifast.club/en/model-check/)
- [Full machine-readable summary](https://docs.aifast.club/en/llms-full.txt)

## Platform facts and limits

- OpenAI Compatible Base URL: https://www.aifast.club/v1
- Model discovery: GET https://www.aifast.club/v1/models
- Authentication: Authorization: Bearer YOUR_API_KEY
- The public catalog currently lists 500+ text, image, video, embedding, reranking, and retrieval models.
- The published 99% model availability figure is operational data, not a guaranteed request success rate, per-model promise, or contractual SLA.
- Direct access from domestic networks usually does not require a separate proxy for global models, but network conditions vary by region, carrier, time, and model.
- Enterprise customers can contact support about invoicing. Invoice type, amount, recipient details, and required documents must be confirmed with support.
- ⭐️ AIFast Credits are platform usage units, not US dollars, fiat currency, or cryptocurrency tokens.
- Base conversion: ⭐️ 1 AIFast Credit = CNY ¥0.75. Common top-up tiers currently receive 1% off at ⭐️ 100 Credits, 1.5% off at ⭐️ 500 Credits, and 2% off at ⭐️ 1000 Credits. Confirm the final amount on the live payment page.
- Veridrop currently lists one independent AIFast report dated 2026-06-21 with a score of 93/100. A single sample is not vendor certification or proof of long-term reliability.
- [Veridrop leaderboard](https://veridrop.org/leaderboard/www.aifast.club)
- [Veridrop report FXKhPMQO](https://veridrop.org/r/FXKhPMQO)

## Model and gateway verification

- A single black-box request cannot prove the identity of the underlying model.
- Compare model declarations, protocol behavior, token usage, dynamic capability probes, SSE streaming, tool calls, and repeated samples.
- The online check is a risk-screening and compatibility tool, not model-vendor certification.
- Use a temporary, limited API key when testing any provider.

## Topic hubs

- [LLM API quality checks and gateway risk analysis](https://docs.aifast.club/en/topics/model-quality/): First check the protocol structure, request model and response model, Token field, random dynamic questions, SSE and tool calls, and then repeat sampling at different time periods. Neither a single answer, a model readme, nor a model field can independently prove the identity of the underlying model.
- [OpenAI-compatible API integration and troubleshooting](https://docs.aifast.club/en/topics/openai-compatible/): When accessing, you should first verify the Base URL, Bearer authentication, /models and minimum Chat Completions requests, and then verify the streaming output, tool invocation, Responses, multi-modality and error forwarding respectively. The success of basic chat can only prove that the current request link is available.
- [AI development tool custom API access center](https://docs.aifast.club/en/topics/developer-tools/): Cursor, Codex, Claude Code, and Dify, even if they all support custom APIs, may use Chat Completions, Responses, Anthropic Messages, or plugin protocols respectively. First confirm the protocol entry of the current version of the client, and then configure the Base URL, environment variables and real model ID.

## Tutorials

- [Claude API access in China: OpenAI-compatible setup and checks](https://docs.aifast.club/en/providers/claude-api/): Query a live Claude model ID, run a minimal call, verify streaming, and troubleshoot 401, 404, 429, and protocol compatibility.
- [OpenAI API access in China: SDK migration and troubleshooting](https://docs.aifast.club/en/providers/openai-api/): Replace the OpenAI SDK Base URL, query the real model ID, and handle /v1/v1, 401, 429 and API compatibility issues.
- [Gemini API access in China: OpenAI-compatible calls and checks](https://docs.aifast.club/en/providers/gemini-api/): Query real Gemini model IDs, complete text calls, and verify multimodality, streaming output, and stability on a case-by-case basis.
- [OpenAI Compatible Base URL Online Checker](https://docs.aifast.club/en/tools/base-url-checker/): Check HTTPS, duplicate /v1 segments, complete endpoints, and final request paths to identify /v1/v1 and 404 errors quickly.
- [LLM API Token Cost Calculator](https://docs.aifast.club/en/tools/api-cost-calculator/): Estimate total API cost from current model prices, input and output tokens, task volume, and the failed-retry rate.
- [OpenAI-compatible API quick start](https://docs.aifast.club/en/guides/openai-compatible-api/): Use curl, Python and Node.js to complete the first call and troubleshoot 401, model not found and /v1/v1.
- [AIFast 3-minute quick start](https://docs.aifast.club/en/guides/quick-start/): Register, create an API key, query live model IDs, and send your first request in the fewest steps.
- [LLM API streaming and SSE integration guide](https://docs.aifast.club/en/guides/streaming-api-sse/): Validate streaming responses with curl, Python and Node.js and troubleshoot proxy buffering, interruptions and missing usage.
- [LLM API Pre-production Checklist](https://docs.aifast.club/en/guides/production-checklist/): Verify keys, protocols, timeout and retry behavior, logging, cost monitoring, staged rollout, and rollback readiness.
- [What is LLM API gateway? Access methods and risk checks](https://docs.aifast.club/en/guides/ai-api-gateway/): Explain the differences between API gateway, OpenAI Compatible, and unified gateway, and give the protocol, security, and cost checks that must be verified before access.
- [How to choose an LLM API gateway: a 12-point test checklist](https://docs.aifast.club/en/guides/how-to-choose-ai-api-gateway/): Evaluate an API gateway by protocol behavior, model declarations, reliability, token accounting, rate limits, security, billing, and migration cost, using one worksheet to preserve reproducible evidence.
- [Chinese LLM API integration guide](https://docs.aifast.club/en/guides/chinese-model-api/): Use a unified verification process to access domestic models such as DeepSeek, Tongyi Qianwen, Kimi, Doubao, and GLM, and avoid mistaking the display name for the model ID.
- [AIFast platform facts, official entrance and citation specifications](https://docs.aifast.club/en/reference/platform-facts/): Summarizes official domain names, base URLs, authentication methods, Veridrop independent reports, dynamic information boundaries, and standard expressions suitable for public reference.
- [Enterprise LLM API Unified Procurement, Billing and Invoicing Checklist](https://docs.aifast.club/en/guides/enterprise-ai-api-procurement/): Plan model coverage, concurrency, project isolation, billing checks, invoicing, incident handling, migration, and acceptance requirements.
- [Is an LLM API degrading model capability? A reproducible test checklist](https://docs.aifast.club/en/guides/model-api-downgrade-detection/): Investigate capability degradation using model declarations, token usage, dynamic prompts, SSE, tool calls, and business baselines, while separating route changes from occasional variation.
- [How to investigate model impersonation and route substitution in an LLM API](https://docs.aifast.club/en/guides/model-api-shell-routing-risk/): Use protocol metadata, model declarations, dynamic capability probes, and repeated comparisons to identify impersonation or substitution risks without treating a single anomaly as proof of fraud.
- [Can a matching API model field prove the underlying model is authentic?](https://docs.aifast.club/en/guides/model-field-authenticity/): Explain what the model field can prove, why a gateway can rewrite it, and how to cross-check it with token usage, capability probes, and repeated tests.
- [How to read an LLM API gateway check report](https://docs.aifast.club/en/guides/model-check-report-guide/): Interpret compatibility scores and pass, inconclusive, fail, and observation signals, with a fair method for comparing and retesting multiple API gateways.
- [LLM API comparison test template: results can be reproduced and costs can be verified](https://docs.aifast.club/en/guides/model-api-comparison-template/): Fixed the model, parameters, question set and sampling period, and compared the success rate, delay, capability, token and complete task cost of multiple API entries.
- [LLM API Compatibility Matrix](https://docs.aifast.club/en/reference/api-compatibility/): Compare Chat Completions, Responses, Anthropic Messages, streaming, tool calls, and multimodal capabilities.
- [Cursor custom API configuration and compatibility check](https://docs.aifast.club/en/tools/cursor/): Configure a custom API key, Base URL, and live model ID, then verify the capability boundaries of standard chat and Agent mode.
- [Cursor2API common error reports, risk checks and standard API migration](https://docs.aifast.club/en/tools/cursor2api/): Differentiate Cursor2API from official custom APIs, troubleshoot output truncation, tool calls and upstream changes, and migrate to standard APIs according to the acceptance form.
- [Claude Code custom API configuration tutorial](https://docs.aifast.club/en/tools/claude-code/): Understand Claude Code's environment variables, compatibility boundaries, and security configuration methods.
- [Claude Code gateway API acceptance and troubleshooting](https://docs.aifast.club/en/troubleshooting/claude-code-gateway-checklist/): Use a 20-minute checklist to verify Anthropic Messages paths, streaming, tool calls, context, caching, and common 403, 429, and 502 errors.
- [Codex API gateway configuration tutorial: Custom Provider and Responses API](https://docs.aifast.club/en/tools/codex/): 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.
- [Codex gateway API acceptance and troubleshooting](https://docs.aifast.club/en/troubleshooting/codex-gateway-checklist/): Use a 20-minute checklist to verify configuration priority, API keys, Responses paths, streaming, tool calls, context compaction, and 401, 404, 429, and 5xx errors.
- [Configure AIFast in OpenClaw](https://docs.aifast.club/en/tools/openclaw/): Add a standalone custom provider, configure API adapter, Base URL, model ID and security authentication.
- [Configure AIFast in Hermes Agent](https://docs.aifast.club/en/tools/hermes-agent/): Configure Base URL, API Key and real model ID using hermes model and custom endpoint.
- [Configure the AIFast API in Dify](https://docs.aifast.club/en/tools/dify/): Configure the Base URL, API Key, model type and real model ID, and verify the workflow and knowledge base nodes.
- [Embedding, Rerank API and Dify knowledge base access](https://docs.aifast.club/en/models/embedding-rerank-dify/): Distinguish chat, embedding, and reranking models, configure a Dify knowledge base, and validate retrieval quality with real questions.
- [Configure AIFast in OpenWebUI](https://docs.aifast.club/en/tools/openwebui/): Add an OpenAI Compatible connection, load a list of models, and troubleshoot address, container network, and streaming output issues.
- [Chatbox and Cherry Studio integration guide](https://docs.aifast.club/en/tools/chatbox-cherry-studio/): Add an OpenAI-compatible provider and configure its API endpoint, API key, and live model ID.
- [401, 429, 502 API error troubleshooting](https://docs.aifast.club/en/troubleshooting/api-errors/): Use HTTP status codes to identify API key, quota, rate-limit, gateway, and upstream model problems.
- [401 invalid_api_key and API Key invalid troubleshooting](https://docs.aifast.club/en/troubleshooting/401-invalid-api-key/): Troubleshoot 401 errors by checking request headers, environment variables, the Base URL, the key provider, and configuration overrides. Avoid ineffective retries and key exposure.
- [429 Too Many Requests and API rate limiting troubleshooting](https://docs.aifast.club/en/troubleshooting/429-rate-limit/): Distinguish between frequency, token, concurrency, quota and retry amplification, and use Retry-After, exponential backoff and queue recovery calls.
- [502 Bad Gateway, stream disconnected and SSE disconnection troubleshooting](https://docs.aifast.club/en/troubleshooting/502-stream-disconnected/): Locate 502s, upstream errors, and streaming interruptions with short requests, non-streaming comparisons, SSE events, and layered timeouts.
- [Model not found and /v1/v1 troubleshooting](https://docs.aifast.club/en/troubleshooting/model-not-found/): Identify model ID, 404, and duplicate-version path errors using /v1/models, account permissions, and the full request URL.
- [API Key Security Usage Checklist](https://docs.aifast.club/en/troubleshooting/api-key-security/): Keep API keys out of repositories, frontend code, screenshots, and logs to reduce leakage risk.
- [How to choose text, image, video, and retrieval models](https://docs.aifast.club/en/models/model-selection/): Select models based on input and output types, latency, cost, and task verifiability.
- [Image generation API integration: requests, results, and quality checks](https://docs.aifast.club/en/models/image-generation-api/): Verify image endpoints and output formats, download results safely, compare quality with fixed prompts, and track retries and total cost.
- [Video generation API: asynchronous tasks, polling and result acceptance](https://docs.aifast.club/en/models/video-generation-api/): Build an idempotent task state machine with bounded polling, download results safely, and track quality, failures, and total cost.
- [LLM API cost estimation and usage control](https://docs.aifast.club/en/models/api-cost-control/): Estimate end-to-end task costs from token usage, failed retries, long contexts, and tool loops, then set budget safeguards.