iTechGuides is reader-supported. When you buy through links on our site, we may earn an affiliate commission. As an Amazon Associate I earn from qualifying purchases. Learn more
GPT-4 is no longer selectable in ChatGPT. OpenAI retired it from the ChatGPT product on April 30, 2025, but still documents GPT-4 as an older model available through the OpenAI API. To use it today, check the GPT-4 API model documentation, use an API account on a supported paid usage tier, and send requests through a documented API endpoint. A ChatGPT subscription by itself does not guarantee GPT-4 API access.
What “access to GPT-4” meant at launch
OpenAI announced GPT-4 on March 14, 2023. Its launch guidance described text-input access through ChatGPT Plus and the API waitlist. OpenAI wrote: “We are releasing GPT‑4’s text input capability via ChatGPT and the API (with a waitlist).” That was launch-era guidance, not a current ChatGPT selection path. See the original GPT-4 announcement.
Can you choose GPT-4 in ChatGPT now?
No. OpenAI’s ChatGPT release notes state that GPT-4 was retired from ChatGPT effective April 30, 2025. The model therefore should not appear in the current ChatGPT model picker. OpenAI has continued to retire other legacy ChatGPT models, and availability can vary by plan, region and date.
The Tool Desk
Outbyte Driver Updater FREEScan for outdated or missing drivers - takes under a minuteDriver Scan →Outbyte PC Repair FREERepair Windows errors before they cause bigger problemsFix Now →If your goal is simply to use ChatGPT, choose from the models currently shown in your account. Do not assume that a current model has identical context limits, endpoints or capabilities to GPT-4.
#1 Best Overall
How to access GPT-4 through the API
- Open the official model page. Start with OpenAI’s GPT-4 API documentation. It identifies GPT-4 as an older high-intelligence model and lists its supported API surfaces and limits.
- Use an API account with a supported usage tier. The model page marks the Free API tier as unsupported and lists rate limits for paid tiers. Your account’s eligibility, limits and verification requirements are authoritative because OpenAI can change them.
- Create API credentials in your OpenAI developer account. Keep the key secret, store it in an environment variable or server-side secret manager, and never embed it in public browser code or a mobile app.
- Send a request through a documented endpoint. The GPT-4 page identifies Chat Completions and other supported endpoints. Use the exact model identifier and request format shown in the current documentation rather than copying an old ChatGPT tutorial.
- Monitor usage and limits. API requests are billed separately from ChatGPT subscriptions. Check your usage dashboard, rate-limit headers and the live pricing and model pages before putting an integration into production.
ChatGPT versus the GPT-4 API
| Question | ChatGPT product | GPT-4 through the API |
|---|---|---|
| Is GPT-4 available? | Retired from ChatGPT on April 30, 2025. | Still documented as an older API model; access depends on account eligibility. |
| Who is it for? | People using OpenAI’s hosted conversational interface. | Developers making direct requests or building applications. |
| What controls access? | Your current plan, region and the models OpenAI exposes in ChatGPT. | API usage tier, rate limits, model support and account status. |
| How is it billed? | Any applicable ChatGPT plan or product billing. | Separate token-based API billing; it is not included automatically with a ChatGPT subscription. |
| Context window listed for GPT-4 | Not applicable as a current ChatGPT selection. | 8,192 tokens on the GPT-4 API model page. |
GPT-4 API price and limits
At the time of the model-page check on September 28, 2026, OpenAI listed GPT-4 at $30 per 1 million input tokens and $60 per 1 million output tokens. These are API rates, not a ChatGPT subscription price, and OpenAI may change them. The same page lists an 8,192-token context window and tier-specific rate limits. Confirm the live figures before budgeting or launching an application.
What the token prices mean
- Input tokens are the text you send, including prompts and conversation history.
- Output tokens are the text GPT-4 generates.
- Your total bill depends on actual token usage and the endpoint or features you use.
Common access mistakes
- Looking for GPT-4 in ChatGPT: retirement means it will not appear in the picker.
- Assuming ChatGPT Plus unlocks the API: ChatGPT and API billing and eligibility are separate.
- Using the Free API tier: OpenAI’s GPT-4 page marks that tier unsupported.
- Relying on an old tutorial: launch instructions, model identifiers, pricing and limits can become outdated.
- Assuming feature parity: check the model page’s endpoint and capability list instead of assuming GPT-4 supports features available in newer models.
Which route should you choose?
Choose ChatGPT when
You want a ready-made conversational interface and do not need to embed model calls in your own software. GPT-4 itself is not an available ChatGPT choice, so use the models currently offered in your account.
Choose the API when
You need programmatic requests, automation or an application integration and specifically require the GPT-4 model documented by OpenAI. Confirm your paid usage tier, current limits, supported endpoint and live price first.
Windows Errors? Fix Them Before They Spread
Repair common Windows errors and clear accumulated junk for a smoother, more stable PC - no reinstall needed.Free scan · no reinstallCrashes, No Sound, or Screen Glitches?
Random freezes, missing sound and display glitches usually trace back to one bad driver. Find and replace yours safely.Free scan · under a minuteQuick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
