OpenAI API Pricing Calculator & Cost Guide (Oct 2026)

OpenAI bills the API per token, with separate prices for input, cached input, output, long context, and the Batch API. The table lists selected text models from the official pricing page.

OpenAI API prices per million tokens (USD)

ModelInputCached inputCache writesOutputLong-context inputLong-context outputBatch inputBatch output
gpt-6-astra$10.00$1.00$12.50$50.00$20.00$75.00$5.00$25.00
gpt-6.1-sol$2.00$0.10$2.50$10.00$4.00$15.00$1.00$5.00
gpt-6-sol$2.00$0.20$2.50$10.00$4.00$15.00$1.00$5.00
gpt-6-luna$0.10$0.01$0.125$0.50$0.20$0.75$0.05$0.25
gpt-5.6-sol$4.00$0.40$5.00$20.00$8.00$30.00$2.00$10.00
gpt-5.6-terra$2.00$0.20$2.50$12.00$4.00$18.00$1.00$6.00
gpt-5.6-luna$0.20$0.02$0.25$1.20$0.40$1.80$0.10$0.60
gpt-5.5$5.00$0.50Not listed$30.00$10.00$45.00$2.50$15.00
gpt-5.5-pro$30.00Not listedNot listed$180.00$60.00$270.00$15.00$90.00
gpt-5.4$2.50$0.25Not listed$15.00$5.00$22.50$1.25$7.50
gpt-5.4-mini$0.75$0.075Not listed$4.50Not listedNot listed$0.375$2.25
gpt-5.4-nano$0.20$0.02Not listed$1.25Not listedNot listed$0.10$0.625
gpt-5.4-pro$30.00Not listedNot listed$180.00$60.00$270.00$15.00$90.00
gpt-5.2$1.75$0.175Not listed$14.00Not listedNot listed$0.875$7.00
gpt-5.1$1.25$0.125Not listed$10.00Not listedNot listed$0.625$5.00
gpt-5$1.25$0.125Not listed$10.00Not listedNot listed$0.625$5.00
gpt-5-mini$0.25$0.025Not listed$2.00Not listedNot listed$0.125$1.00
gpt-5-nano$0.05$0.005Not listed$0.40Not listedNot listed$0.025$0.20
gpt-4.1$2.00$0.50Not listed$8.00Not listedNot listed$1.00$4.00
gpt-4.1-mini$0.40$0.10Not listed$1.60Not listedNot listed$0.20$0.80
gpt-4.1-nano$0.10$0.025Not listed$0.40Not listedNot listed$0.05$0.20
gpt-4o$2.50$1.25Not listed$10.00Not listedNot listed$1.25$5.00
gpt-4o-mini$0.15$0.075Not listed$0.60Not listedNot listed$0.075$0.30
o3$2.00$0.50Not listed$8.00Not listedNot listed$1.00$4.00
o4-mini$1.10$0.275Not listed$4.40Not listedNot listed$0.55$2.20
Official OpenAI API pricing(opens in a new tab)

Estimate your OpenAI API cost

Estimated cost$200.00

Uses official list prices for input and output tokens only. Cache, long context, tools, regional uplifts, taxes, and discounts are excluded.

Compare models with cache-aware estimates

How OpenAI API billing works

  • Prices are per one million tokens. Short context means up to 272K input tokens; long context means more than 272K.
  • Batch API prices are listed separately and are lower than standard prices for the same model.
  • Regional processing (data residency) endpoints add a 10% uplift for models released on or after March 5, 2026.
  • GPT-5.6 Sol's promotional pricing is available at least through November 21, 2026.
  • Flex, fast mode, audio, image, and tool pricing are listed on the official page.

Track OpenAI API costs before limits stop requests

Quota Monitor reads OpenAI API costs and official monthly spend limits through an Admin API key. It does not read prepaid credit balances.

Read the OpenAI API monitoring guide

OpenAI API pricing FAQ

How much does the OpenAI API cost per million tokens?
On the official list, the models in this table range from gpt-5-nano at $0.05 input and $0.40 output per million tokens to gpt-5.5-pro and gpt-5.4-pro at $30 input and $180 output (short context).
What do short context and long context mean?
Short context covers requests with up to 272K input tokens; long context covers requests above that and costs more. For example, gpt-6.1-sol input is $2 per million tokens in short context and $4 in long context.
What happens when OpenAI API credits run out?
Requests return HTTP 429 with error.code credit_balance_exhausted until you add credits. Reaching an organization or project spend limit returns organization_spend_limit_exceeded or project_spend_limit_exceeded instead; retrying does not restore access.