An open-source LLM gateway/proxy layer that unifies many providers into an OpenAI-style interface; ideal for teams that want to self-host a relay and control their own keys and logs.
An open-source LLM gateway/proxy layer that unifies many providers into an OpenAI-style interface; ideal for teams that want to self-host a relay and control their own keys and logs.
Best for: For dev teams with ops capacity who want control over API keys, logs, routing, and permissions.
Availability and latency
Current status
Self-hosted
Latency reference
Depends on your deployment
/models check
Self-hosted configuration
Last verified
2026-09-15
Status notes
An open-source proxy layer; real latency and availability depend on your deployment and upstream providers.
Open-source and self-hosted; cost comes from servers and the underlying model providers.
Price tags
High stability, Self-hosted
Free quota
No unified free quota; depends on the providers you connect.
Payment methods
Self-hosted
How to call the API
Usually you create an API key in the platform console, then replace the SDK's baseURL, model name, and auth details per the docs. Test streaming, function calling, error codes, and rate limits before launch.
import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.AI_GATEWAY_API_KEY,
baseURL: "see the platform docs"
});
const response = await client.chat.completions.create({
model: "gpt-4.1-mini",
messages: [{ role: "user", content: "Test one call through an AI gateway." }]
});
Pros
Supported models: OpenAI, Claude, Gemini, DeepSeek, Grok, Qwen, Moonshot, Doubao and more.
Capabilities: OpenAI-compatible, Streaming, Function calling, Embeddings, Log query.
A third-party paid GPT API relay for developers in China, with an OpenAI-compatible endpoint at https://api.codexhot.com/v1. Its public guide lists GPT GO, PLUS, and PRO groups with models the platform reports as tested; group names do not establish official authorization or performance guarantees.
Models
OpenAI
Payment
Price
The public guide displays default GO / PLUS / PRO multipliers of 0.02 / 0.07 / 0.1 against the platform's own model base billing, not fixed prices per request. Charges depend on model, group, input/output, caching, and request-time rules. Vouchers start at CNY 5; the submitter says they are purchased through the external wzyp.cn shop and redeemed on the website. Payment methods depend on that shop; AI Beyond could not verify its checkout page.
Flow7's prepaid multi-model API gateway provides Responses, Chat Completions, and Anthropic Messages compatibility, request spend limits, locked price versions, and completed-response charge receipts. Public model-family labels do not establish verified upstream supplier or model-weight provenance.
Models
OpenAI, Claude, Gemini, DeepSeek, Grok, Moonshot
Payment
Credit card
Price
Pay-as-you-go from a prepaid USD wallet. First funding starts at $20; later reloads start at $50, with applicable tax potentially added. The maximum estimated cost is reserved before dispatch, then settled with usage, the locked price version, final charge, and a receipt. Current model and policy-selector prices come from the public catalog.
A multi-model routing platform for developers; switch models by changing the base_url with the OpenAI SDK, ideal for teams comparing the quality and price of many models at once.
Models
OpenAI, Claude, Gemini, DeepSeek, Grok, Qwen and more
Payment
Credit card, Stripe, Free trial
Price
Billed per model and provider; some models offer free routing or free quota.
This entry is marked as supporting the OpenAI-compatible format, but the exact base_url, model names, and parameters still follow the official docs.
Is LiteLLM Proxy ready for production?
Run a small-traffic load test, rate-limit test, and error-code test first, and confirm the billing rules; keep a backup provider for important workloads.
Risk
Risk notice
This site only organizes information about AI API relay services; it makes no guarantee about third-party platforms' stability, price, data security, or availability. Judge the risk yourself before use, and avoid uploading sensitive data, personal privacy, trade secrets, or core API keys to unknown platforms.
