OpenAI lists standard GPT-5.5 API rates of $5 per 1 million input tokens, $0.50 per 1 million cached input tokens, and $30 per 1 million output tokens. The documented model ID is gpt-5.5; prices are in U.S. dollars per million tokens. OpenAI GPT-5.5 model documentation
GPT-5.5 API price per million tokens
| Token category | Price (USD per 1 million tokens) |
|---|---|
| Input | $5.00 |
| Cached input | $0.50 |
| Output | $30.00 |
OpenAI documents a 1,050,000-token context window and a maximum output of 128,000 tokens. The model page lists the Responses and Chat Completions API endpoints. OpenAI GPT-5.5 model documentation
Estimate your GPT-5.5 API cost
For cost calculations, divide input into uncached input and cached input so the same tokens are not charged twice. Total input tokens equal uncached input tokens plus cached input tokens. If you start with total input and know the cached subset, subtract that subset to get uncached input.
Estimated cost = (uncached input tokens ÷ 1,000,000 × $5) + (cached input tokens ÷ 1,000,000 × $0.50) + (output tokens ÷ 1,000,000 × $30)
For a request with 10,000 uncached input tokens and 2,000 output tokens, with no cached input:
- Input: 10,000 ÷ 1,000,000 × $5 = $0.05
- Output: 2,000 ÷ 1,000,000 × $30 = $0.06
- Estimated total: $0.11
For a mixed-cache example, suppose a request has 10,000 total input tokens, of which 4,000 are cached, plus 2,000 output tokens. That leaves 6,000 uncached input tokens:
- Uncached input: 6,000 ÷ 1,000,000 × $5 = $0.03
- Cached input: 4,000 ÷ 1,000,000 × $0.50 = $0.002
- Output: 2,000 ÷ 1,000,000 × $30 = $0.06
- Estimated total: $0.092
These examples use standard token rates and exclude pricing adjustments. For a monthly estimate, calculate cost from your expected token counts and request volume; measured usage is preferable to estimates.
Pricing conditions that can change the estimate
- Long prompts: OpenAI says prompts with more than 272,000 input tokens are priced at 2× the input rate and 1.5× the output rate for the full session. The documented rule applies to standard, Batch, and Flex pricing. OpenAI GPT-5.5 model documentation
- Regional processing: OpenAI’s model documentation reports a 10% uplift for GPT-5.5 regional-processing (data residency) endpoints. Include it if you use an eligible endpoint. OpenAI GPT-5.5 model documentation
- Batch, Flex, and Priority: The documented material available here does not establish GPT-5.5’s base Batch or Flex rates, their eligibility or availability conditions, or Priority rates. The long-context rule above applies to standard, Batch, and Flex, but this estimate uses standard rates only. Do not assume an additional discount or surcharge for another tier without checking the applicable terms in OpenAI API pricing.
API billing is separate from ChatGPT subscriptions
GPT-5.5 API usage is billed by token category. A ChatGPT subscription is a separate product and billing arrangement; its monthly fee is not a fixed amount of API tokens and should not be substituted into an API cost estimate.
Is GPT-5.5 available for production API use?
Yes. OpenAI announced that GPT-5.5 and GPT-5.5 Pro were available in the API on April 24, 2026. The GPT-5.5 model documentation lists the model ID gpt-5.5, the Responses and Chat Completions endpoints, text and image input, and text output. Check the model documentation for the endpoint and capability details relevant to your integration. OpenAI announcement · GPT-5.5 model documentation