Text model

ChatGPT without a VPN — access from anywhere

Q: Which ChatGPT models are available in GPTunneL?

The current list is always visible in the «Every ChatGPT model» block above — it is built straight from the platform catalogue. Usually that means the whole current generation, the Codex branch for code and the earlier generations still in service.

Q: Which model should I use for work?

For most tasks mini is enough — it is fast and noticeably cheaper. If the task is hard (development, long documents, agent workflows), take the standard model of the generation or pro. For a stream of small repetitive requests nano is the cheapest option.

Q: How are the Codex models different?

They are the same family fine-tuned for development: they hold the structure of a project better, edit several files at once more carefully and are more confident with a terminal and a debugger.

Q: Which languages does ChatGPT handle?

The models work comfortably in dozens of languages — they understand the request and answer in the same language, including long texts and documents.

Q: Can I send images and files?

Yes. The models accept images and documents: diagrams, screenshots, tables and scans are read together with the text of your request.

Every OpenAI model in GPTunneL: the GPT-5 family, Codex for code and the o-series. Pay per token, no subscription and no VPN.

Try ChatGPT Available models

What the GPT family is good at

Traits OpenAI keeps from one generation to the next — you can count on them whichever model you pick.

The widest range on the market

From a tiny nano tier for a stream of repetitive requests to pro versions for the hardest tasks. Every budget has a model that fits.

Multimodal by default

Text, images, documents and audio in one window. Attach a screenshot or a scan and work through it in plain text.

A separate branch for code

The Codex models are tuned for development — reading a repository, editing several files at once, debugging and review.

The largest ecosystem

More ready-made solutions and prompts are written for GPT than for anything else, so almost any task already has a proven approach.

Which model to pick

The family has four tiers — for different jobs and budgets.

	NanoVolume and speed	MiniThe default pick	StandardHard tasks	ProMaximum quality
Best for	Classification, tagging, auto-replies, simple extraction	Everyday writing, correspondence, analysis	Development, long documents, agents	Tasks where accuracy matters more than time
Context	400K tokens	400K tokens	up to 1M tokens	up to 1M tokens
Speed	Highest	High	Medium	Low
Price	Lowest	Moderate	Above average	Highest

Figures reflect the current model at each tier. Exact per-model prices are on the Pricing

Every ChatGPT model

Release dates follow OpenAI's official announcements.

July 2026

GPT-5.6 Sol GPT-5.6 Terra GPT-5.6 Luna

Three models of one generation for different modes of work. Sol is the strongest on agent tasks; Terra and Luna are cheaper and faster.

April 2026

GPT-5.5 GPT-5.5 Pro

Context grew to a million tokens, and the Pro version thinks longer about a task and answers more accurately.

March 2026

GPT-5.4 GPT-5.4 Mini GPT-5.4 Nano GPT-5.4 Pro

A generation with the full set of tiers — from nano to pro, so every task can find its own price point.

February 2026

GPT-5.3 Codex

The development branch — repository search, running commands in the terminal and debugging code.

December 2025

GPT-5.2 GPT-5.2 Pro GPT-5.2 Codex

The first update to the fifth generation, released alongside a dedicated model for code.

Full release history

November 2025

GPT-5.1 GPT-5.1 Codex GPT-5.1 Codex mini

The model became noticeably livelier in conversation and follows instructions more carefully.

August 2025

GPT-5 GPT-5 Mini GPT-5 Nano GPT-5 ProGPT-5 Codex

The generation where reasoning stopped being a separate model — the main line learned to think longer about a hard request.

August 2025

GPT OSS 120B GPT OSS 20B GPT OSS 120B RU GPT OSS 20B RU

Open-weight models you can run yourself. GPTunneL also carries variants fine-tuned for specific languages.

April 2025

GPT-4.1 GPT-4.1 Mini GPT-4.1 Nano

Context grew to a million tokens, and mini and nano tiers shipped alongside the larger model.

2025

o3 o3 Mini o4 Mini

A separate branch that built a chain of reasoning before answering. Its capabilities later moved into the main family.

2024

GPT-4o GPT-4o Mini

The first genuinely multimodal model in the family — text, images and sound in one window.

November 2023

GPT-4 Turbo

Context grew to 128 thousand tokens and the price fell several times over — the point at which GPT became a tool for working with documents.

March 2023

GPT-4

The generation that made serious work with the model possible: far fewer mistakes and the first understanding of images.

November 2022

GPT-3.5 Turbo

The model ChatGPT launched on, and the start of the current wave of neural networks.

How billing works

There is no subscription: you top up one balance and spend it on any model on the platform.

Pay per token

You are charged for exactly what the request and the answer used. Not using it costs nothing: no limits, no monthly fee.

One balance for every model

ChatGPT, Claude, Gemini, image and video generation — all out of the same wallet. No separate subscription per service.

Top up the way you prefer

International cards, Apple Pay, Google Pay or crypto. The minimum top-up is $5.

See pricing

How to get started with ChatGPT

One account for every model on the platform.

Emailyou@example.comPassword••••••••

Build a quarterly summary from this table and name the main deviations

Report.xlsx

GPT-5.6 Sol

Quarterly summary

Revenue has grown for four quarters running, but the rate slowed from 18% to 6%.

The main deviation is marketing: spend rose by half with the same number of deals.

Cost of sales is flat, so the margin drop is entirely explained by expenses.

The model switches right inside the input — you can change it mid-conversation.

The answer lands in the chat and the context is kept until the conversation ends.

Try ChatGPT in GPTunneL

Signing up takes a minute, and $5 on the balance is enough to see whether the model fits your task.

Try ChatGPT

Frequently asked questions

/01Do I need a VPN to use ChatGPT through GPTunneL?

No. Requests go through GPTunneL's infrastructure, so OpenAI models open like any ordinary website — no VPN and no proxy.

/02Which ChatGPT models are available in GPTunneL?

/03Which model should I use for work?

/04How are the Codex models different?

/05Which languages does ChatGPT handle?

/06Can I send images and files?

ChatGPT is a service by OpenAI and the best-known neural network in the world: the current wave of interest in artificial intelligence started with its launch at the end of 2022. A whole family of GPT models works under that one name — they answer questions, write and edit text, read documents and program.

The GPT family is the widest on the market. It has tiny models for a stream of repetitive requests, general-purpose middle tiers for everyday work, larger models for hard jobs and a separate Codex branch tuned for development: reading a repository, editing several files at once, debugging. The larger models hold up to a million tokens in context, understand images and documents, search the web and draw pictures in the same conversation.

Every OpenAI model is available in GPTunneL — worldwide, without a VPN, with one balance and billing for the tokens you actually spend.