{T}
TokenMath.net
Official Provider HubSan Francisco, CA, USA

OpenAI API Pricing & Token Economics

OpenAI provides the GPT and o-series model families through its Chat Completions and Assistants APIs. Their pricing architecture features automatic 75% prompt caching on 1,024+ prefix tokens, 50% discounts on asynchronous Batch API processing, and dedicated reasoning token accounting for extended chain-of-thought deliberation.

Prompt Caching Policy

Automatic prefix caching on >= 1,024 tokens (50% to 75% discount off standard input).

Batch / Asynchronous Rules

50% off standard input and output rates via 24-hour asynchronous Batch API.

Special Billing Conditions

Reasoning tokens generated during internal chain-of-thought are billed at standard output rates.

Active OpenAI Models(8 models verified)

All 30 Models →
ModelContextInput / 1MCached / 1MOutput / 1MBatch DiscountActions
GPT-6 Astra
gpt-6-astra
1.05M$10.00$1.00$50.0050% offSpecs →
GPT-5.6 Sol
gpt-5.6-sol
1.05M$4.00$0.40$20.0050% offSpecs →
GPT-5.6 Terra
gpt-5.6-terra
1.05M$2.00$0.20$12.0050% offSpecs →
GPT-5.6 Luna
gpt-5.6-luna
1.05M$0.20$0.02$1.2050% offSpecs →
OpenAI o3
o3-2026-04-15
200k$2.00$0.50$8.0050% offSpecs →
OpenAI o3-pro
o3-pro-2026-06-01
256k$20.00$10.00$80.0050% offSpecs →
OpenAI o4-mini
o4-mini-2026-07-15
200k$1.10$0.275$4.4050% offSpecs →
OpenAI o1
o1-2024-12-17
200k$15.00$7.50$60.0050% offSpecs →

Calculate your monthly OpenAI bill

Simulate prompt caching hit rates, batch discounts, and output token costs with zero server logging.

Open Cost Calculator →