Cheap GPT API — OpenAI models from $0.30/1M
The whole GPT line through a drop-in OpenAI-compatible endpoint — up to 88% below OpenAI's official price. Change base_url in the SDK you already use and everything keeps working — function calling, JSON schemas, vision, streaming. /v1/responses is supported natively, so Codex CLI runs against us without a shim. Pay in ₽, USDT or by card.
GPT API pricing
USD per 1M tokens, next to OpenAI's official rate. Updated automatically from our live price list.
| Model | Input | Output | OpenAI | Savings |
|---|---|---|---|---|
| GPT 6 Astra | $1.48 | $7.40 | $10 | −85% |
| GPT 5.5 | $0.74 | $4.43 | $5.00 | −85% |
| GPT 5.6 Sol | $0.74 | $4.36 | $5.00 | −85% |
| GPT 6 Sol | $0.56 | $2.88 | $2.00 | −72% |
| GPT 6.1 Sol | $0.56 | $2.88 | $2.00 | −72% |
| GPT 5.6 Terra | $0.30 | $1.77 | $2.50 | −88% |
| GPT Image 2.5 | $1.50 | $9.00 | — | — |
| GPT Image 2.5 Flare | $1.50 | $9.00 | — | — |
| GPT Image 2.5 Sunburst | $1.50 | $9.00 | — | — |
| GPT Image 2 | $0.02 / req | — | — | — |
Why take GPT from here
Your SDK, one line changed
Point base_url at https://cheapai.io/v1 and the official openai package keeps working as-is — streaming, tools, structured outputs, vision. Nothing else in your code moves.
Codex CLI works natively
/v1/responses is implemented, not emulated, so Codex runs with wire_api = "responses" and keeps its context compaction. Config is three lines — the docs have it ready to copy.
No model swapping
response.model always equals what you asked for. We don't quietly route a request for the flagship to a cheaper tier — check the field yourself on any call.
How to connect GPT
Any OpenAI SDK
Works in Cursor, Cline, Kilo Code, LangChain and anything else that lets you set a base URL.
from openai import OpenAI
client = OpenAI(
api_key="sk-...", # from cheapai.io/keys
base_url="https://cheapai.io/v1",
)Codex CLI
User-level ~/.codex/config.toml only — Codex ignores a project-local one. wire_api must be "responses".
model = "gpt-5.6-sol"
model_provider = "cheapai"
[model_providers.cheapai]
name = "CheapAI"
base_url = "https://cheapai.io/v1"
env_key = "CHEAPAI_API_KEY"
wire_api = "responses"Also available without a CDN: https://api.cheapai.io/v1 — use it for long requests where the model stays silent over ~2 minutes, or where the CDN is unreachable.
Full guides for every tool: documentation →
FAQ
How much does the GPT API cost here?
From $0.30 per 1M input tokens. 10 GPT models are live right now and the table above is pulled from the same price list the billing uses, so it is never stale.
Is this the real GPT, or a cheaper model behind the name?
The real thing. response.model always matches the model you requested, so you can verify it on any call without taking our word for it.
Will Codex CLI work?
Yes. /v1/responses is implemented natively, so set wire_api = "responses" in ~/.codex/config.toml with base_url https://cheapai.io/v1. Note that the provider id must not be "openai" — that name is reserved by Codex.
Do I need a VPN?
No. The domain and the API are reachable worldwide, and you can top up in ₽, USDT or by card.
Is there a subscription?
Not required. The default is pay-as-you-go from a balance that doesn't expire; monthly plans exist separately and give up to 40% off, but you never have to take one.