gpt5apikey.com/GPT 5 API: Pay per token
GPT 5 API: Pay per token
Stop paying for capacity you don’t use. Our gpt 5 api charges strictly for the tokens you process, giving you transparent, predictable costs for uncensored text generation.
No subscription. Prepaid credit never expires.
- $0.25
- per 1M input tokens
- $1.00
- Output tokens / 1M
- 100,000
- token context
- $0.50
- trial credit
- 300
- requests per minute
Cost calculator
Worked examples
Local RAG pipeline summarization
A script processes 50,000 input tokens (context + query) and generates 2,000 output tokens (summary). Input cost: 50,000 / 1,000,000 × $0.25 = $0.0125. Output cost: 2,000 / 1,000,000 × $1.00 = $0.0020. Total: $0.0145.
Creative fiction drafting
A writer uses the model to generate a 3,000-word chapter. Input prompt is 1,000 tokens. Output is 4,000 tokens. Input cost: 1,000 / 1,000,000 × $0.25 = $0.00025. Output cost: 4,000 / 1,000,000 × $1.00 = $0.0040. Total: $0.00425.
High-volume classification
An automated system classifies 10,000 documents. Each request uses 500 input tokens and returns 50 output tokens. Cost per request: (500 / 1,000,000 × $0.25) + (50 / 1,000,000 × $1.00) = $0.000125 + $0.00005 = $0.000175.
Token-Based Pricing Model
The gpt 5 api uses a straightforward pay-as-you-go structure. You pay only for the input and output tokens your requests consume, measured in millions of tokens. The input rate is $0.25 per 1M tokens, and the output rate is $1.00 per 1M tokens. This model eliminates hidden fees for API calls or connection overhead, making it easy to calculate exact costs for your workload.
Unlike enterprise plans that charge for idle capacity, this approach ensures you never pay for unused resources. Whether you are running a small script or a high-throughput pipeline, your costs scale linearly with your actual usage.
Prepaid Credits That Never Expire
We require prepaid credits to manage resource allocation without imposing monthly subscriptions. Once you add funds, the credit is yours indefinitely. There is no expiration date, so you can top up when prices are favorable or during quiet periods without worrying about losing your balance.
This prepaid model also provides strict budget control. Your API usage cannot exceed the amount you have loaded, preventing unexpected bills at the end of the month. It is ideal for developers who want to forecast their LLM spending with precision.
Top-Up Bonuses and Trial Access
New accounts receive $0.50 in trial credit, valid for 7 days, requiring no credit card. For ongoing use, we offer bonuses on larger top-ups: +5% extra credit for deposits of $50 or more, and +10% for deposits of $100 or more. You can pay via crypto (USDT or USDC), starting from a minimum of $10.
These bonuses effectively reduce your per-token cost. By loading credits in bulk, you get more processing power for the same base price, making high-volume projects even more cost-effective.
Specs that affect cost
Same price for every feature — function calling and JSON mode cost nothing extra.
| Item | Value |
|---|---|
| Completion length | 16,000 tokens max; 2,048 if max_tokens is not set |
| JSON mode | response_format: {"type": "json_object"} |
| Context window | 100,000 tokens (prompt + completion together) |
| Tools / tool calls | Supported: tools + tool_choice, tool_calls in the reply (streamed too), tool results as role: tool messages |
| Rate limit | 300 requests per minute per key |
| Parallel requests | up to 8 in parallel per key |
| Top-up | USDT (TRC20) or USDC (Base), any whole amount from $10 to $500 |
| Bonus credit | +5% from $50, +10% from $100 |
| Subscription | paid credit never expires, no subscription |
| Token prices | input $0.25 / 1M tokens, output $1.00 / 1M tokens |
| Free trial | $0.50 of credit valid 7 days, no card needed |
Questions and answers
How do I calculate the cost of a specific request?
Use the formula: (input_tokens / 1,000,000 × $0.25) + (output_tokens / 1,000,000 × $1.00). For example, 1M input and 1M output tokens cost $1.25 total. You can track your exact usage via the <code>/v1/chat/completions</code> response headers.
Does my prepaid credit expire?
No. Your prepaid balance never expires. You can add funds at any time, and the credit remains available until you use it. This makes the <strong>gpt 5 api</strong> suitable for long-term projects with irregular usage patterns.
Is there a monthly fee for using the API?
No. There are no monthly subscription fees or base costs. You only pay for the tokens you consume. If you do not make any requests, your cost is zero.
What happens if I hit the request limit?
If you exceed 300 requests per minute, the API will return a 429 error. You can regenerate your API key to get a fresh identifier, but note that each account is limited to one active key at a time. Regenerating the key revokes the previous one.
Your key is one form away
Create an account, copy the key, change the base URL. That is the whole setup.
