GPT-6 Astra
gpt-6-astraINPUT / MTOK$10.00
OUTPUT / MTOK$50.00
Cached input: $1.00 / MTok. Standard short-context list price.
OPENAI API · VERIFIED OCTOBER 31, 2026
OpenAI API
Pricing Calculator
Compare published OpenAI API list prices per million tokens, then estimate a text workload in your browser. This is an independent unofficial calculator; prices can change.
GPT-6.1 Sol
gpt-6.1-solINPUT / MTOK$2.00
OUTPUT / MTOK$10.00
Cached input: $0.10 / MTok. Standard short-context list price.
GPT-6.1 Terra
gpt-6.1-terraINPUT / MTOK$1.00
OUTPUT / MTOK$5.00
Cached input: $0.05 / MTok. Standard short-context list price.
GPT-6 Luna
gpt-6-lunaINPUT / MTOK$0.10
OUTPUT / MTOK$0.50
Cached input: $0.01 / MTok. Standard short-context list price.
GPT-5.6 Sol
gpt-5.6-solINPUT / MTOK$4.00
OUTPUT / MTOK$20.00
Cached input: $0.40 / MTok. Listed under Cyber models.
01 / COST ESTIMATOR
Estimate an OpenAI API workload.
Choose a model and enter monthly token volume. The estimate uses the displayed standard list rates and runs entirely in your browser.
Estimated monthly token cost$200.00$10.00 input + $50.00 output per MTok · cached input not included
02 / HOW TO READ THE RATE CARD
Model the whole request, not just one number.
Last updated / verified: 2026-10-31. OpenAI documents prices per one million tokens. This page shows the standard short-context list prices visible on the official pricing page on October 31, 2026.
Cache separately
Repeated prompt tokens may qualify for cached-input pricing. The calculator intentionally excludes cache savings so the result stays conservative.
Check route and mode
Flex/Batch, Fast, Ultrafast, long-context, regional processing and cloud-platform routes can have different prices. Verify the exact option before launch.
Include tools
Web search, containers, file search and other built-in tools can add usage-based charges beyond model tokens.
Source: OpenAI API Pricing documentation. Responses API and Chat Completions API are not priced separately according to that documentation.
03 / FAQ
OpenAI API pricing questions
How is OpenAI API cost calculated?
Divide input and output tokens by one million, multiply each by its corresponding list price, then add cached-input, tool, regional or other usage charges. The calculator here estimates token cost only.
Are Responses API and Chat Completions priced separately?
OpenAI's pricing documentation says Responses API, Chat Completions API, Realtime API, Batch API and Assistants API are not priced separately. Tokens are billed at the chosen model's rates.
Does the calculator include prompt caching?
No. Cached-input rates are shown on the cards where the official page lists them, but the estimate uses uncached input. This keeps the default estimate simple and conservative.
Where are GPT-4.1 and other models?
Model availability and pricing can change. If a model is not listed on the current official pricing page or its exact rate cannot be verified, this page does not invent a number. Verify on OpenAI.
Are these prices guaranteed to stay current?
No. This is an independent unofficial calculator. Prices can change, so check the official OpenAI page before budgeting or deploying.
Compare OpenAI with other LLM APIs.
Use the all-model guide or open the Claude-specific pricing page.