# Amux AI vs Requesty: no service fee, more native protocols

> Amux AI and Requesty both offer a unified LLM API. The differences: Amux AI bills inference at provider list price with no markup, charges no top-up fee and offers low-cost channels far below official pricing plus discounted official channels; it natively supports the Gemini protocol plus Alibaba Cloud Model Studio, Volcengine Seedance, MiniMax and xAI image and video protocols; bodies of successful text calls are not stored; and enterprise-grade organization management, with team budgets that need no enterprise plan. Requesty adds a 5% service fee and offers EU data residency, visual routing policies, an MCP gateway and BYOK.

Last verified 2026-10-19 · https://amux.ai/vs/requesty

- **0%** Platform service fee: Requesty adds a 5% service fee on top of model prices
- **90%** Max saving vs. official price: From low-cost channels, based on live catalog prices; stable official channels are discounted too
- **4** Native text protocols: Including Gemini generateContent, which Requesty does not list
- **Not stored** Bodies of successful text calls: Requesty logs requests by default and keeps them for 30 days

## Amux AI vs Requesty, feature by feature

| Feature | Amux AI | Requesty |
|---|---|---|
| Platform fees | 0% — no inference markup, no top-up fee; low-cost channels go far below official pricing, and official channels are discounted too | 5% service fee — described on the pricing page per model price ($10 → $10.50) and in the billing docs per top-up ($100 costs $105) |
| Free usage | Pay as you go — you pay only for what you use | Free plan: 200 requests per day on free models only |
| Text protocols | Native OpenAI Chat, OpenAI Responses, Anthropic Messages and Gemini (generateContent), with most models callable across protocols | OpenAI Chat, Responses and Anthropic Messages; no native Gemini protocol listed in the docs |
| Image and video | Image: OpenAI Images and Alibaba Cloud Model Studio. Video: native Model Studio, Volcengine Seedance, MiniMax and xAI request formats plus a unified task API — existing client code only needs a new base URL and key | Images through the OpenAI Images API; no video generation in the docs |
| Embeddings and audio | Embeddings, speech and rerank endpoints (Coming soon) | Embeddings, text-to-speech and speech-to-text; no rerank |
| Model coverage | 70+ text, image and video models, with more added regularly; 52 models can switch between providers | Advertises 600+ models |
| Routing and failover | Five routing strategies, configurable per API key; automatic failover on connection errors, timeouts, rate limits and server errors, with failed attempts not billed | Ordered fallbacks, weighted load balancing and latency routing; failed attempts not billed |
| Teams and budgets | Enterprise-grade organization management: organizations, workspaces and roles (including a finance role); spend limits per workspace, member and key on every organization — no enterprise plan required | Monthly limits per key; groups and team budgets, full RBAC and audit logs on Enterprise only |
| Logging and privacy | Request and response bodies of successful text calls are not stored; customer content is never used for training | Logs kept by default, encrypted, for 30 days, and can be turned off per key; no training on paid plans |
| Usage and export | Itemized charges for every call; monthly statements exported to Excel by key, model and workspace | CSV export from cost tracking; cost returned with each response |
| Single sign-on | SAML single sign-on (Coming soon) | SAML / OIDC SSO on the Enterprise plan |

## Choose Amux AI if

- You want no platform service fee and leading models such as Claude, GPT and Gemini far below official pricing through low-cost channels, or at a discount through stable official channels
- You use the native Gemini protocol or need video generation, and want to call models in the native Alibaba Cloud, Volcengine, MiniMax or xAI request formats
- Your team needs budgets per workspace, member and key, with a finance role managing top-ups and invoices, without an enterprise plan
- You want bodies of successful text calls left unstored

## Choose Requesty if

- You need EU data residency, or want to configure fallback and load-balancing policies visually in the console
- You need an MCP gateway or guardrails such as PII masking
- You need embeddings or speech endpoints today (on the Amux AI roadmap)
- You want to bring your own provider keys (BYOK)

## Switch from Requesty to Amux AI

Both work with the OpenAI and Anthropic SDKs and use the same manufacturer/model ID format. Switching only changes the endpoint and key — your application code stays as it is.

1. Sign up for Amux AI and create an API key in the console.
2. Replace the base URL with the Amux AI endpoint and the API key with your new key.
3. Keep your existing model IDs; for the few models whose version format differs, copy the ID from the model page.

- OpenAI SDK base URL: `https://gateway.amux.ai/v1`
- Anthropic SDK / Claude Code base URL: `https://gateway.amux.ai`

```python
import os
from openai import OpenAI

client = OpenAI(base_url="https://gateway.amux.ai/v1", api_key=os.environ["AMUX_API_KEY"])
response = client.chat.completions.create(
    model="openai/gpt-6.1-sol",
    messages=[{"role": "user", "content": "Hello"}],
)
```

- For requests that use a Requesty policy (policy/…), set a routing strategy on the Amux AI API key instead, or append ":provider" to the model ID to pin a provider.
- Claude Code and the Anthropic SDK use the endpoint without /v1; the Gemini SDK can call generateContent directly.

## Frequently asked questions

### What is the main difference between Amux AI and Requesty?

Amux AI has no inference markup and no top-up fee, offers low-cost channels far below official pricing plus discounted official channels, and natively supports the Gemini protocol plus vendor image and video protocols; bodies of successful text calls are not stored, and enterprise-grade organization management, with team budgets that need no enterprise plan. Requesty adds a 5% service fee and offers EU data residency, visual routing policies, an MCP gateway, embeddings and audio endpoints, and BYOK.

### How can Amux AI price models below the official rate?

Amux AI connects each model to several providers in two kinds of channels: low-cost channels priced far below official pricing for cost-sensitive workloads, and official channels from model makers and major clouds that are stable and also discounted. Live per-provider prices are published on each model page; you can restrict an API key or workspace to official channels only, or set price-first routing.

### What does a $100 top-up actually cost on each?

A $100 top-up on Amux AI gives you $100 in credit with no fee. Requesty’s billing docs state that a 5% service fee is added to top-ups, so a $100 top-up costs $105 (as of 2026-10-19 — see the Requesty docs for current terms).

### What code changes are needed to switch from Requesty to Amux AI?

Usually two: point the base URL at the Amux AI endpoint and replace the API key with an Amux AI key. Model IDs use the same manufacturer/model format; check the Amux AI model page for the exact name of each model. Requests that use routing policies should use a strategy set on the API key instead.

### Does Amux AI store my prompts and responses?

Request and response bodies of successful text calls are not stored, and customer content is never used for training; prompts for image and video tasks are kept with the task for 30 days. Failed calls keep a limited sample for troubleshooting for up to 15 days, which you can turn off with a request header.

### Can Claude Code, Cursor and similar tools switch from Requesty to Amux AI?

Yes. Amux AI natively implements the Anthropic Messages and OpenAI protocols, and setup guides cover Claude Code, Codex, Gemini CLI, Cursor, Cline, Cherry Studio and more — replace the endpoint and key as described.

### Can I use Requesty and Amux AI together?

Yes. Both work with the OpenAI SDK, so you can split traffic by model or use case — for example, send mainstream models through Amux AI for lower prices and keep workloads that need EU data residency on Requesty.

_Requesty and other product names mentioned on this page are trademarks of their respective owners. Information about third-party products is compiled from their official public sources for evaluation purposes only and may change; refer to each vendor's website for current details. To report an inaccuracy, contact support@amux.ai._