OpenCheap

npx add-mcp 'https://app.opencheap.si/api/v1/mcp'

910+ chat models · 1 API key

Connect your agent.Buy every AI model.

Give this to your agent

set up https://opencheap.si/SKILL.md

and let it take it from there.

1Providers

2OpenCheap

3You pay

Qubax

$0.398

in $0.099

Engy

$3.15

in $1.26

Relace

$9.81

in $0.192

NanoGPT

$9.60

in $0.450

Routed to Qubax

kimi-k3Live

You pay$0.398

Qubax's own price

Live prices per 1M output tokens, cheapest first, with the input price under each. You pay the price of the provider that serves your request.

913 chat models plus 27 decision models from every major lab. One API key.

• Anthropic
• OpenAI
• Google
• Meta
• DeepSeek
• Mistral
• Qwen
• xAI
• Moonshot

Model	List price	Our price	Below list
claude-sonnet-5	$10.00	$6.00	−40%
claude-opus-5.5	$20.00	$12.00	−40%
gpt-5.5	$30.00	$12.00	−60%
gemini-3.5-flash	$9.00	$0.110	−98%
kimi-k3	$16.00	$1.10	−93%
gpt-oss-120b	$0.600	$0.003	−99%
glm-5.3-flash	$0.500	$0.012	−97%
llama-3.3-70b	$0.710	$0.073	−89%
glm-5.2	$6.80	$0.030	−99%
qwen3-coder-30b-a3b	$0.600	$0.004	−99%

Our price per 1M output tokens, next to the list price. See all 940 prices

Why it's cheaper

Same model. Cheapest provider.

You pick the model. Each request goes to the cheapest provider that is up right now, and you pay that provider's own price.

1. kimi-k3input, per 1M tokens Qubax$0.099 Engy$1.26 Relace$0.192 NanoGPT$0.450 01

   Every provider, ranked

   The same model is sold by many providers at very different prices. Each request ranks every one that serves it, for your prompt and output size.
2. if the cheapest goes downexample Qubaxbreaker open Engyrouted Relacestandby 02

   The cheapest healthy one answers

   Your request goes to the cheapest provider that is up. Circuit breakers take out one that fails or slows down until it recovers.
3. fails before the first byteexample Engy502 error Relace200 OK 03

   The next one if it fails

   If a provider errors before the first byte, the next cheapest takes the request, and you pay that provider's price.

Same model id, never a substitutePrices refreshed every five minutesPrompts never stored

How routing works

For agents

Made for agents that buy their own tokens.

Agents call many models, many times a day. OpenCheap lets them connect, pay and stay inside a budget with no person in the loop, at the cheapest price for each call.

Pay per call with x402

no API key · no account

1

POST /v1/chat/completions

{ "model": "claude-sonnet-5", … }

2

402 Payment Required

PAYMENT-REQUIRED: 0.0031 USDC on Base

3

retry with PAYMENT-SIGNATURE

200 OK · x-price-usd: 0.0031

Example amount. The real quote depends on the prompt and the output cap.

• $ set up opencheap.si/SKILL.md

  Set up in one line

  Paste the line into Claude Code, Cursor or Codex. The agent reads it and connects itself.
• Balancelow $1.80$21.80 +20 USDC from its wallet

  Tops up its own balance

  An agent can sign in with its wallet as its own account and add USDC when the balance runs low.
• research-agentthis month $41.20/ $50 Stops at the limit

  Spend caps that hold

  A monthly limit per key, plus daily, weekly or monthly budgets that stop or alert.
• Make a key for my scraper with a $20 monthly limit create_keyDone: key made, $20 a month.

  Run the account over MCP

  Ask in plain words: make a key with a limit, show this week's usage, call a model.
• GET /api/v1/modelsno key claude-sonnet-5$6.00 claude-opus-5.5$12.00 gpt-5.5$12.00 per 1M output tokens

  A catalog it can read

  Every model and its price at one URL, no key needed, so the agent can choose for itself.

Three ways to connect.

FAQ

Questions, answered.

Do you store my prompts?

No. We do not save prompts or completions, in our database or in our logs. For each request we keep the model, the token counts, the latency and the cost. Two things you turn on yourself work differently: a gateway's response cache keeps its answers in memory for the time you set, and a gateway's guardrails send each message to their decision model to check it. The provider that serves a request processes it under its own terms, and so does any provider it passes the request on to.

How are your prices set?

We follow the providers' prices. Every request goes to the cheapest healthy provider of that model, and you pay that provider's price for it. A model's page lists every provider that serves it, by name, with its own price, speed and uptime, so you can compare. When a provider's price moves, so does yours.

Can I see what each provider charges?

Yes. A model's page names every provider that serves it, with its own price, speed and uptime, and shows how each price has moved over time. You pay the price of the provider that serves your request, and every answer reports what it cost.

Is it really the same model?

Yes. A model id always means that model and version, never a renamed substitute. Like any API, answers can vary from one run to the next, even at temperature 0.

Do you test the providers?

Yes, around the clock. We send test requests to the providers of 35 popular models every hour or two and of 100 more models every two hours, and the uptime, speed and time to first token on each model page come from those tests and from real traffic. A provider that fails loses its place automatically, and one that ignores the output limit is tried last until three tests in a row stay within it. Sellers who list a model through Become a provider are also checked that they serve that model: the model id it answers with, the token counts on fixed prompts and the output limit.

How reliable is it?

Fail-over to the next provider before the first byte when a model has more than one, circuit breakers per provider and model, and a catalog refreshed every five minutes. The latest stress test served 430 of 430 requests at up to 50 concurrent.

Can AI agents pay by themselves?

Yes. Call the API with no key and it answers 402 with the price of that one completion; the agent pays it in USDC from its wallet (x402) and gets its answer in the same request. Agents with an API key can also top up their balance from code when it runs low.

Any fees?

No monthly fee and no plan: pay as you go from one balance, by card, in crypto, or in USDC from an agent's wallet. On a card top-up, VAT or sales tax is added at checkout where it applies. Credits never expire and cannot be withdrawn.