Refactoring a 2,000-line Python module
Input: 1,500,000 tokens ($0.375). Output: 500,000 tokens ($0.50). Total cost: $0.875. This workload benefits from the 100k context window without hitting per-request overheads.
Codex API: Token pricing
Pricing is straightforward: you pay per million tokens processed by the uncensored coding LLM. There are no subscriptions, no per-seat fees, and your usage can never exceed your prepaid balance.
No subscription. Prepaid credit never expires.
- $0.25per 1M input tokens
- $1.00Output tokens / 1M
- 100,000token context
- $0.50trial credit
- 300requests per minute
Cost calculator
Worked examples
Bulk linting of a 50-file codebase
Input: 2,000,000 tokens ($0.50). Output: 100,000 tokens ($0.10). Total cost: $0.60. The single-model endpoint ensures consistent behavior across all files in the batch.
Generating unit tests for a complex class
Input: 500,000 tokens ($0.125). Output: 1,500,000 tokens ($1.50). Total cost: $1.625. High output volume is common when the model generates verbose test suites.
Token Pricing
Our codex api charges based on the volume of text processed. Input tokens are billed at $0.25 per 1M tokens, while output tokens are billed at $1.00 per 1M tokens. This structure reflects the higher computational cost of generating text compared to processing it. The pricing is transparent and applies to every request, whether you are using streaming or standard JSON responses. Since we serve a single, dedicated uncensored model, you do not pay for idle capacity or router fees often found in aggregated APIs. This makes our ai coding api highly predictable for high-throughput agents that process large codebases.Prepaid Credit & Bonuses
We operate on a prepaid credit system. You load funds, and usage is deducted in real-time. Your balance can never go negative, ensuring you never receive an unexpected invoice. We offer bonuses to reward larger loads: a 5% bonus is added when you top up $50 or more, and a 10% bonus applies to loads of $100 or more. This increases the effective value of your credit. Credits never expire, so you can load funds when prices are favorable and use them over an extended period. This model eliminates the risk of subscription waste if your coding agent scales down unexpectedly.
Payment Methods
You can add credit to your account using crypto (USDT or USDC). Both methods are processed securely and instantly. There are no hidden transaction fees for standard top-ups. The minimum top-up amount is $10, making it easy to start small. When you purchase credit, it is immediately available in your account. This flexibility allows developers to manage their codex api key budget according to their project cycles. Whether you are running a weekend project or a continuous integration pipeline, you can adjust your spending by topping up as needed.No Hidden Fees
Our pricing includes everything. There are no extra charges for tool calling, streaming, or high request volumes within your rate limits. The only limit is the 300 requests per minute cap per key. You do not pay for failed requests or network errors; you only pay for tokens processed. This simplicity extends to our support and infrastructure. You are not paying for SLA guarantees or enterprise compliance add-ons you might not need. The cost is strictly for the compute power used to generate text. This makes our service ideal for developers who want to know exactly what each line of code generation costs.
Limits and what is included
No tiers: every key gets the full feature set and the same limits.
| Parameter | Details |
|---|---|
| Function calling | Yes — tools, tool_choice; replies carry tool_calls, also when streaming; send results back as role: tool |
| Completion length | up to 16,000 tokens per request (default 2,048) |
| Context window | 100,000 tokens, input and output combined |
| Structured output | JSON object mode via response_format json_object |
| Concurrency | 8 requests at the same time per key |
| Requests per minute | 300/min per key |
| Volume bonus | +5% on $50+, +10% on $100+ |
| Token prices | input $0.25 / 1M tokens, output $1.00 / 1M tokens |
| Free trial | $0.50 of credit valid 7 days, no card needed |
| Top-up | crypto: USDT on TRON or USDC on Base, $10–$500, any whole sum |
| Credit expiry | no monthly fee; paid credit does not expire |
Questions and answers
Do I lose unused credits if I stop using the API?
No. Your prepaid credit never expires. You can load funds and use them whenever you need them, whether that is tomorrow or next year. This is particularly useful for intermittent coding projects or agents that run sporadically.
Can I have multiple API keys to split my quota?
No. Each account is limited to one API key. This key can be regenerated at any time, which immediately revokes the old one. This simplifies billing and security management by ensuring all usage is tied to a single account balance.
Are there any fees for streaming responses?
No. Streaming responses are billed at the same token rates as standard JSON responses. You only pay for the input and output tokens processed. The method of delivery does not affect the price.
How does the trial credit work?
New accounts receive $0.50 in trial credit valid for 7 days. No credit card is required to start. This allows you to test the <strong>codex api</strong> with a real workload before committing to a paid top-up. The trial credit is one-time per person and does not roll over.
Your key is one form away
Create an account, copy the key, change the base URL. That is the whole setup.
