AIFast LLM API Developer Center
One Base URL, unified access to 500+ models
Covers mainstream text, image, video and retrieval models at home and abroad. From the first request to production troubleshooting, access is completed with replicable and verifiable steps.
# Query currently available models
curl https://www.aifast.link/v1/models \
-H "Authorization: Bearer $AIFAST_API_KEY"OpenAI CompatibleClick the complete question to enter the topic center
From judgment methods, configuration steps to troubleshooting and acceptance, avoid repeated searches between scattered tutorials.
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.
Enter the theme center 02 · OPENAI COMPATIBLEOpenAI-compatible API integration and troubleshootingWhen 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.
Enter the theme center 03 · DEVELOPER TOOLSAI development tool custom API access centerCursor, 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.
Enter the theme centerStart with your current task
There is no need to read from the beginning, just choose the step that needs to be solved most now.
Create an API Key, query the model list, and send the first request.
View quick start 02Codex, Claude Code and CursorConfigure and accept respectively according to Responses, Anthropic Messages and OpenAI Compatible protocols.
Enter the Development Tools Center 03Positioning call errorCheck 401, 429, 502, model name and address errors one by one.
Enter the troubleshooting manualPress the model platform to start accessing
Select the target model platform, first query the current model ID, and then complete the minimum request and production acceptance.
Check the configuration differences between Claude model ID, protocol boundary, streaming output and Claude Code.
Migrate Python and Node.js SDK, handle Base URL, Key conflicts and /v1/v1.
Complete OpenAI Compatible calls and verify multi-modal and streaming capabilities step by step.
Use one repeatable verification workflow for DeepSeek, Qwen, Kimi, Doubao, and Zhipu GLM integrations.
Confirm three fields before accessing
Most first-time access problems can be located from the address, authentication, and model identification.
OpenAI Compatible address is usually filled in https://www.aifast.link/v1, and check if the client will append again /v1.
Use Authorization: Bearer Authentication, and save the key in the server environment variable or key system.
from the console or /v1/models Copy the actual model ID; do not replace it with a Chinese title, manufacturer name, or model series name.
Concerned about capability degradation, model impersonation, or route substitution?
First check the protocol, model declaration, token, dynamic questions, SSE and tool calls before deciding whether to connect. The report provides itemized evidence and does not package black box screening as manufacturer certification.
Open the free detection toolLLM intelligence detection and model quality testing: downgrading from model declaration, token, dynamic questions, SSE, tool calling and business baseline troubleshooting capabilities, and distinguishing routing changes from occasional fluctuations.
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.
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.
Interpret compatibility scores and pass, inconclusive, fail, and observation signals, with a fair method for comparing and retesting multiple API gateways.
OpenAI Compatible API compatibility troubleshooting: Differentiating Chat, Responses, Anthropic Messages, Base URLs, SSE, tool calls, and multimodal capabilities.
Use tools first to get verifiable results
No need to download and install. Check the existing API, correct the base URL, or estimate the token cost based on real usage.
Check model declarations, tokens, dynamic questions, SSE and tool calls.
Start testing Configuration troubleshootingBase URL checkerLocate duplicate /v1, full endpoint and client path splicing issues.
check address cost estimateToken cost calculatorCalculate costs for input, output, batch jobs, and failed retries.
Estimate cost Continuous checksOpenAI-compatible API CheckRun protocol, SSE and tool-call checks in GitHub Actions.
View open-source project Reliability evidenceAPI Stability TrackerCalculate success rate, P50/P95 latency and error distribution from JSONL samples.
View statistics tool Developer entry pointAIFast Developer HubFind migration, troubleshooting, client configuration and verifiable evidence in one place.
Open GitHubClaude API access in China: OpenAI-compatible setup and checks
Query a live Claude model ID, run a minimal call, verify streaming, and troubleshoot 401, 404, 429, and protocol compatibility.
Quick StartOpenAI API Access from China: Base URL, SDK, 401, and 429
Configure the OpenAI SDK Base URL, query live model IDs, and troubleshoot /v1/v1, 401, 429, and API compatibility issues.
Quick StartGemini API access in China: OpenAI-compatible calls and checks
Query real Gemini model IDs, complete text calls, and verify multimodality, streaming output, and stability on a case-by-case basis.
TroubleshootingOpenAI Compatible Base URL Online Checker
Check OpenAI-compatible API URLs, repeated /v1, complete endpoints, HTTPS, and final request paths to locate /v1/v1 and 404 errors.
Models and CostLLM API Token Cost Calculator
Estimate total API cost from current model prices, input and output tokens, task volume, and the failed-retry rate.
Quick StartOpenAI-Compatible API tutorial: integration and request verification
Configure the Base URL with curl, Python and Node.js, verify the model list and first request, and troubleshoot 401, model not found and /v1/v1 errors.
Quick StartAIFast 3-minute quick start
Register, create an API key, query live model IDs, and send your first request in the fewest steps.
Quick StartLLM API streaming and SSE integration guide
Validate streaming responses with curl, Python and Node.js and troubleshoot proxy buffering, interruptions and missing usage.
Quick StartLLM API Pre-production Checklist
Verify keys, protocols, timeout and retry behavior, logging, cost monitoring, staged rollout, and rollback readiness.
Quick StartWhat is LLM API gateway? Access methods and risk checks
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.
Quick StartHow to choose an OpenAI-compatible API service: a 12-point checklist for teams in China
Compare cloud platforms, global aggregators, self-hosted gateways, and unified services for networks in China using 12 OpenAI-compatible API criteria: protocol support, models, reliability, token accounting, rate limits, security, billing, and migration cost.
Quick StartChinese LLM API setup: DeepSeek, Qwen, Kimi, Doubao and Zhipu
Domestic LLM API access tutorial: unified verification of the real model ID, OpenAI Compatible, tool calling and network search capabilities of DeepSeek, Tongyi Qianwen, Kimi, Doubao and Zhipu GLM.
Platform ReferenceAIFast platform facts, official entry points, and verification limits
Review official domains, the Base URL, public endpoints, current platform statements, and the historical Veridrop report while separating live facts, dynamic information, and historical evidence.
Platform ReferenceEnterprise LLM API Unified Procurement, Billing and Invoicing Checklist
Plan model coverage, concurrency, project isolation, billing checks, invoicing, incident handling, migration, and acceptance requirements.
Platform ReferenceIs an LLM API degrading model capability? A reproducible test checklist
LLM intelligence detection and model quality testing: downgrading from model declaration, token, dynamic questions, SSE, tool calling and business baseline troubleshooting capabilities, and distinguishing routing changes from occasional fluctuations.
Platform ReferenceHow to investigate model impersonation and route substitution in an LLM API
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.
Platform ReferenceCan a matching API model field prove the underlying model is authentic?
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.
Platform ReferenceHow to read an LLM API gateway check report
Interpret compatibility scores and pass, inconclusive, fail, and observation signals, with a fair method for comparing and retesting multiple API gateways.
Platform ReferenceLLM API comparison test template: results can be reproduced and costs can be verified
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.
Platform ReferenceLLM API Compatibility Matrix
OpenAI Compatible API compatibility troubleshooting: Differentiating Chat, Responses, Anthropic Messages, Base URLs, SSE, tool calls, and multimodal capabilities.
Tool IntegrationCursor Custom API Setup and Troubleshooting
Configure a custom API key, Base URL, and exact model ID; inspect the request path; and troubleshoot API Key Valid, 401, and model not found errors.
Tool IntegrationCursor2API Setup: Fix 401, Truncation, and Migrate APIs
Distinguish Cursor2API from official custom APIs, troubleshoot 401, output truncation, tool-call, and model-change issues, then migrate to a standard API with a repeatable checklist.
Tool IntegrationClaude Code custom API configuration tutorial
Configure ANTHROPIC_BASE_URL, authentication variables, and model mapping to distinguish Anthropic Messages from the OpenAI Compatible protocol.
TroubleshootingClaude Code gateway API acceptance and troubleshooting
Use a 20-minute checklist to verify Anthropic Messages paths, streaming, tool calls, context, caching, and common 403, 429, and 502 errors.
Tool IntegrationCodex 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.
TroubleshootingCodex gateway API acceptance and troubleshooting
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.
Tool IntegrationOpenClaw API configuration, model verification and common errors
Add a standalone custom provider, configure the API adapter, Base URL and real model ID, and verify streaming output and tool calls.
Tool IntegrationConfigure AIFast in Hermes Agent
Configure Base URL, API Key and real model ID using hermes model and custom endpoint.
Tool IntegrationConfigure 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.
Tool IntegrationEmbedding, Rerank API and Dify knowledge base access
Distinguish chat, embedding, and reranking models, configure a Dify knowledge base, and validate retrieval quality with real questions.
Tool IntegrationConfigure AIFast in OpenWebUI
Add an OpenAI Compatible connection, load a list of models, and troubleshoot address, container network, and streaming output issues.
Tool IntegrationChatbox and Cherry Studio integration guide
Add an OpenAI-compatible provider and configure its API endpoint, API key, and live model ID.
Troubleshooting401, 429, 502 API error troubleshooting
Use HTTP status codes to identify API key, quota, rate-limit, gateway, and upstream model problems.
Troubleshooting401 invalid_api_key and API Key invalid troubleshooting
Troubleshoot 401 errors by checking request headers, environment variables, the Base URL, the key provider, and configuration overrides. Avoid ineffective retries and key exposure.
TroubleshootingFix OpenAI API 429: Rate Limits, Quota, and Retries
Separate request-rate, token-rate, concurrency, quota, and duplicate-retry causes, then recover with Retry-After, exponential backoff, and request queues.
Troubleshooting502 Bad Gateway, stream disconnected and SSE disconnection troubleshooting
Locate 502s, upstream errors, and streaming interruptions with short requests, non-streaming comparisons, SSE events, and layered timeouts.
TroubleshootingAPI model not found, /v1/v1 and 404 troubleshooting
Identify model ID, 404, and duplicate-version path errors using /v1/models, account permissions, and the full request URL.
TroubleshootingAPI Key Security Usage Checklist
Keep API keys out of repositories, frontend code, screenshots, and logs to reduce leakage risk.
Models and CostHow to choose text, image, video, and retrieval models
Select models based on input and output types, latency, cost, and task verifiability.
Models and CostImage generation API integration: requests, results, and quality checks
Verify image endpoints and output formats, download results safely, compare quality with fixed prompts, and track retries and total cost.
Models and CostVideo generation API: asynchronous tasks, polling and result acceptance
Build an idempotent task state machine with bounded polling, download results safely, and track quality, failures, and total cost.
Models and CostLLM API cost estimation and usage control
Estimate end-to-end task costs from token usage, failed retries, long contexts, and tool loops, then set budget safeguards.
Choose the fastest path to your first successful API call
Start with a live gateway check, copy the OpenAI-compatible base URL, or review international funding before moving a project into production.