Every frontier model, on one key.

An OpenAI-compatible endpoint in front of Claude, GPT, Gemini, Grok and MiniMax. Go is $5 a month for 3,000 credits — a genuinely unfair deal.

Get 3,000 credits Browse 31 models

terminal

export OPENAI_BASE_URL="https://ai.eaon.dev/v1"
export OPENAI_API_KEY="eaon_sk_..."

# GPT-6 Astra, Opus 5, and 29 more answer here

models: 31; models
providers: 12; providers
credits/mo for $5: 3,000; credits/mo for $5
max context: 1M; max context

Models from

OpenAIAnthropicGooglexAIDeepSeekMetaNVIDIAQwenMoonshot AIXiaomiTencentMiniMax

Where most people start

All 31 models

Buying model access should be boring

One bill instead of five
Anthropic, OpenAI, Google and xAI each want their own account, their own key and their own invoice. Here it is one line on one card.
The deal is the product
Go is $5 a month for 3,000 credits — about $33–$86 of value at official-API rates. Plus is $25 for 15,000. Same models, metered the same way — just a fraction of the bill.
One flat fee, no rate limits
A single subscription instead of a card on file per token. Every call spends real tokens against that credit. Nothing here throttles how fast you can call it.
Nothing to migrate to
The endpoint is OpenAI-shaped. Change a base URL and a key in whatever you already use, and the models change underneath you.

What a plan actually buys

Pick a plan to see roughly how far its usage grant goes on each model, or filter by tier. Every call is metered from real tokens — no private multipliers.

Plus: 15,000 credits a month for $25. That’s 3,750 each week (monthly ÷ 4) — unused weeks do not roll over. A credit is not a call: one credit is $0.01 of real model usage, and a typical call costs a fraction of one. Every call is metered from the tokens it actually used, so cheap models go much further. “Calls” below assumes a 2,000-in / 800-out turn.

Model	Context	Tier	Credits / call	Calls / week	On Plus
Nemotron 3.5 Lightningeaon/nemotron-3.5-lightning	1,000k	flash	0	unlimited	Included
Qwen 3.7 Flasheaon/qwen3.7-flash	1,000k	flash	0.025	152k	Included
MiniMax M2.5eaon/minimax-m2.5	200k	flash	0.026	145k	Included
MiniMax M2.5 HighSpeedeaon/minimax-m2.5-highspeed	200k	flash	0.026	145k	Included
MiniMax M2.7eaon/minimax-m2.7	200k	flash	0.026	145k	Included
MiniMax M2.7 HighSpeedeaon/minimax-m2.7-highspeed	200k	flash	0.026	145k	Included
MiniMax M3eaon/minimax-m3	200k	flash	0.026	145k	Included
Gemini 3.1 Flash Liteeaon/gemini-3.1-flash-lite	1,000k	flash	0.032	118k	Included
DeepSeek V4 Flasheaon/deepseek-v4-flash	1,000k	flash	0.032	116k	Included
Muse Spark 1.3eaon/muse-spark-1.3	1,000k	flash	0.054	69k	Included
Hunyuan 3eaon/hunyuan-3	262.144k	flash	0.064	58k	Included
Gemini 3 Flasheaon/gemini-3-flash	1,000k	flash	0.065	58k	Included
MiMo v2.5eaon/mimo-v2.5	1,000k	flash	0.076	50k	Included
Gemini 2.5 Flash Liteeaon/gemini-2.5-flash-lite	1,000k	flash	0.078	48k	Included
Gemini 3.7 Flasheaon/gemini-3.7-flash	1,000k	flash	0.088	43k	Included
Gemini 3.8 Flasheaon/gemini-3.8-flash	1,000k	flash	0.088	43k	Included
Qwen 3.8 Flasheaon/qwen3.8-flash	1,000k	flash	0.101	37k	Included
GPT-4o minieaon/gpt-4o-mini	128k	flash	0.117	32k	Included
Grok 4.5eaon/grok-4.5	256k	standard	0.125	30k	Included
Grok 4.6eaon/grok-4.6	256k	standard	0.125	30k	Included
GPT-5.6 Terraeaon/gpt-5.6-terra	400k	standard	0.136	28k	Included
Claude Sonnet 5eaon/sonnet-5	1,000k	standard	0.17	22k	Included
MiMo v2.5 Proeaon/mimo-v2.5-pro	1,000k	standard	0.313	12k	Included
GPT-5.5eaon/gpt-5.5	400k	standard	0.34	11k	Included
Gemini 3.1 Pro Previeweaon/gemini-3.1-pro-preview	1,000k	standard	0.35	11k	Included
GPT-5.6 Soleaon/gpt-5.6-sol	400k	frontier	0.51	7.4k	Included
Claude Opus 5eaon/opus-5	1,000k	frontier	0.646	5.8k	Included
GPT-6 Astraeaon/gpt-6-astra	400k	frontier	0.9	4.2k	Included
Hunyuan 4 Previeweaon/hunyuan-4-preview	1,000k	frontier	1.1	3.4k	Included
Claude Fable 5eaon/fable-5	200k	frontier	1.28	2.9k	Included
Kimi K2.6eaon/kimi-k2.6	262.144k	frontier	1.53	2.5k	Included

How it works

Three steps, and none of them involve talking to anyone.

01
Create a key
Sign up and issue one from the dashboard. It is shown once, and it works against every model your plan covers.
02
Point your client at it
Set the base URL to the Eaon endpoint and the key to your new one. No SDK to install and no proxy to run locally.
03
Pick a model per call
Send an Eaon model id in the request body. Swap it whenever you like — each call is metered from the tokens it actually used.

Drop it into what you already use

Two environment variables. No SDK to install, no wrapper library, no proxy running on your machine.

~/.zshrc

export ANTHROPIC_BASE_URL="https://ai.eaon.dev/v1"
export ANTHROPIC_AUTH_TOKEN="eaon_sk_..."
export ANTHROPIC_MODEL="eaon/sonnet-5"

claude

Four things you can check yourself

We cannot show you a key twice
Only a sha256 of each key is stored. The plaintext appears once, when you create it, and after that we do not have it either. Lose one and you revoke it and issue another.
An outage on their side does not spend your month
Budget is reserved before the upstream call and handed back if it fails.
Cancelling happens on the page you subscribed from
Billing runs through Stripe end to end. No email to write, no retention flow to sit through.

Three plans, and you can change your mind

Start free, move up when you hit the ceiling, cancel from the same page you subscribed on.

Free

$0/month

Enough to wire it up and see it work.

300 credits a month
≈$3.75–$8.50 of official-API value
Resets monthly (not weekly)
Flash models
1 API key
No rate limits

Go1× Go

$5/month

3,000 credits a month for $5.

3,000 credits a month
750 credits each week (monthly ÷ 4)
≈$33–$86 of official-API value
Unused week does not roll over
Every model, GPT-6 Astra included
5 API keys
No rate limits

Monthly credit is billed in 7-day windows: you get 1/4 each week. Meter resets every week from your plan start date.

Plus5× Go

$25/month

5× Go — 15,000 credits a month.

15,000 credits a month
3,750 credits each week (monthly ÷ 4)
≈$165–$430 of official-API value
Unused week does not roll over
Every model, GPT-6 Astra included
10 API keys
No rate limits

Monthly credit is billed in 7-day windows: you get 1/4 each week. Meter resets every week from your plan start date.

Pro10× Go

$50/month

10× Go — 30,000 credits a month.

30,000 credits a month
7,500 credits each week (monthly ÷ 4)
≈$330–$860 of official-API value
Unused week does not roll over
Every model, GPT-6 Astra included
10 API keys
No rate limits

Monthly credit is billed in 7-day windows: you get 1/4 each week. Meter resets every week from your plan start date.

Max20× Go

$100/month

20× Go — 60,000 credits a month.

60,000 credits a month
15,000 credits each week (monthly ÷ 4)
≈$660–$1,720 of official-API value
Unused week does not roll over
Every model, GPT-6 Astra included
20 API keys
No rate limits

Monthly credit is billed in 7-day windows: you get 1/4 each week. Meter resets every week from your plan start date.

Questions that come up

What am I actually billed for?

The real cost of the call: prompt tokens, reply tokens, and cached tokens at a lower rate, priced per model. A short question and a long conversation on the same model cost different amounts, honestly, rather than both being rounded up to one flat charge.

Does unused budget roll over?

No. It resets every 7 days from when your plan started (every 30 on Free). We priced the plans expecting most windows to leave some on the table, which is what lets the heavy ones stay affordable.

Are there rate limits?

No. Send requests as fast as you want — nothing here throttles a resolved key. The only limit that applies is your account's own budget, and a spike just spends it faster.

Will my existing tools work without changes?

If they speak the OpenAI chat completions protocol, yes. Point the base URL at Eaon, swap the key, and pick a model id from the catalogue. Claude Code, Cursor, Codex CLI and the official SDKs all work this way.

What happens when I run out?

A request whose worst case would exceed what's left gets HTTP 402 immediately, before it ever reaches a model — so you're never charged for a call that didn't run. Nothing silently downgrades to a cheaper model behind your back either.

Do you train on my requests?

No. Prompts pass through to the upstream provider and are not stored. What we keep is the metering row: model, real cost, token counts, latency and status.

Can I cancel whenever?

Yes, from the billing portal. The plan stays live until the end of the period you already paid for, then drops to Free.

New models, when we add them

Rate changes too. Nothing else, and never more than once a month.

Every frontier model, on one key.

Where most people start

Buying model access should be boring

One bill instead of five

The deal is the product

One flat fee, no rate limits

Nothing to migrate to

What a plan actually buys

How it works

Create a key

Point your client at it

Pick a model per call

Drop it into what you already use

Four things you can check yourself

We cannot show you a key twice

An outage on their side does not spend your month

Cancelling happens on the page you subscribed from

Three plans, and you can change your mind

Free

Go1× Go

Plus5× Go

Pro10× Go

Max20× Go

Questions that come up

New models, when we add them