OpenAI API pricing
OpenAI sells API access to the GPT model family plus embeddings, image, audio, and video models. Prices are per 1M tokens across three service tiers, with steep cached-input discounts.
Official price list: platform.openai.com
Current lineup
GPT-5.6
OpenAI's current flagship API model (the full-size tier, listed as gpt-5.6-sol).
$5.00 in / $30.00 out per 1M
GPT-5.6 Terra
The mid-size tier of the GPT-5.6 family.
$2.00 in / $12.00 out per 1M
GPT-5.6 Luna
The small, low-cost tier of the GPT-5.6 family.
$0.20 in / $1.20 out per 1M
GPT-5.5
OpenAI flagship model, superseded by GPT-5.6.
$5.00 in / $30.00 out per 1M
GPT-5.4
OpenAI flagship model of the GPT-5.4 generation (March 2026).
$2.50 in / $15.00 out per 1M
GPT-5.4 mini
Mid-size model of the GPT-5.4 generation.
$0.75 in / $4.50 out per 1M
GPT-5.4 nano
Smallest, cheapest model of the GPT-5.4 generation.
$0.20 in / $1.25 out per 1M
GPT-5.3 Codex
OpenAI's Codex line for agentic coding, as priced on the API.
GPT-5.2
OpenAI flagship model of December 2025.
$1.75 in / $14.00 out per 1M
GPT-5.1
OpenAI flagship model of November 2025.
$1.25 in / $10.00 out per 1M
GPT-5
The original GPT-5 (August 2025), still widely integrated.
$1.25 in / $10.00 out per 1M
GPT-5 mini
Mid-size model of the original GPT-5 generation.
$0.25 in / $2.00 out per 1M
GPT-5 nano
Smallest model of the original GPT-5 generation.
$0.05 in / $0.40 out per 1M
GPT-4.1
OpenAI's 2025 long-context workhorse, still in wide production use.
$2.00 in / $8.00 out per 1M
GPT-4.1 mini
Mid-size model of the GPT-4.1 generation.
$0.40 in / $1.60 out per 1M
GPT-4o
OpenAI's 2024 flagship — legacy, but still among the most-integrated models.
$2.50 in / $10.00 out per 1M
GPT-4o mini
The 2024 budget default; huge installed base.
$0.15 in / $0.60 out per 1M
OpenAI o3
OpenAI's 2025 reasoning model line.
$2.00 in / $8.00 out per 1M
OpenAI o4-mini
Compact reasoning model of the o-series.
$1.10 in / $4.40 out per 1M
How OpenAI billing works
Three service tiers: Standard, Batch/Flex at 50% off, and Fast (renamed from Priority processing in July 2026) at roughly 2x Standard — the Fast multiplier varies by model (1.7–2.5x), so read the per-model table rather than assuming 2x. Batch runs asynchronously within 24 hours.
Cached input is ~90% off on current models (older gpt-4o-era models discount 50%). The GPT-5.6 family additionally bills cache WRITES at 1.25x the input rate — earlier families wrote to the cache for free.
Long-context surcharge: on GPT-5.4-and-later flagships, a request whose input exceeds the ~272K-token threshold bills the ENTIRE request at roughly 2x input / 1.5x output rates — the surcharge applies to all tokens, not the excess.
Dated snapshots of the same family can carry different prices (gpt-4o-2024-05-13 is double gpt-4o), and API responses echo the dated snapshot — price on the response-reported model, not the alias you requested.
Every OpenAI model we price
The full catalog — including dated snapshots and variants — exactly as Marginal prices incoming usage events.
| Cached input / 1M | ||||
|---|---|---|---|---|
| chatgpt-4o-latest | $5.00 | $15.00 | 125K | — |
| ft:gpt-3.5-turbo | $3.00 | $6.00 | 16K | — |
| ft:gpt-3.5-turbo-0125 | $3.00 | $6.00 | 16K | — |
| ft:gpt-3.5-turbo-0613 | $3.00 | $6.00 | 4K | — |
| ft:gpt-3.5-turbo-1106 | $3.00 | $6.00 | 16K | — |
| ft:gpt-4-0613 | $30.00 | $60.00 | 8K | — |
| ft:gpt-4.1-2025-04-14 | $3.00 | $12.00 | 1M | $0.75 |
| ft:gpt-4.1-mini-2025-04-14 | $0.80 | $3.20 | 1M | $0.20 |
| ft:gpt-4.1-nano-2025-04-14 | $0.20 | $0.80 | 1M | $0.05 |
| ft:gpt-4o-2024-08-06 | $3.75 | $15.00 | 125K | $1.875 |
| ft:gpt-4o-2024-11-20 | $3.75 | $15.00 | 125K | — |
| ft:gpt-4o-mini-2024-07-18 | $0.30 | $1.20 | 125K | $0.15 |
| ft:o4-mini-2025-04-16 | $4.00 | $16.00 | 200K | $1.00 |
| gpt-3.5-turbo | $0.50 | $1.50 | 16K | — |
| gpt-3.5-turbo-0125 | $0.50 | $1.50 | 16K | — |
| gpt-3.5-turbo-1106 | $1.00 | $2.00 | 16K | — |
| gpt-3.5-turbo-16k | $3.00 | $4.00 | 16K | — |
| gpt-4 | $30.00 | $60.00 | 8K | — |
| gpt-4-0125-preview | $10.00 | $30.00 | 125K | — |
| gpt-4-0314 | $30.00 | $60.00 | 8K | — |
| gpt-4-0613 | $30.00 | $60.00 | 8K | — |
| gpt-4-1106-preview | $10.00 | $30.00 | 125K | — |
| gpt-4-turbo | $10.00 | $30.00 | 125K | — |
| gpt-4-turbo-2024-04-09 | $10.00 | $30.00 | 125K | — |
| gpt-4-turbo-preview | $10.00 | $30.00 | 125K | — |
| gpt-4.1 | $2.00 | $8.00 | 1M | $0.50 |
| gpt-4.1-2025-04-14 | $2.00 | $8.00 | 1M | $0.50 |
| gpt-4.1-mini | $0.40 | $1.60 | 1M | $0.10 |
| gpt-4.1-mini-2025-04-14 | $0.40 | $1.60 | 1M | $0.10 |
| gpt-4.1-nano | $0.10 | $0.40 | 1M | $0.025 |
| gpt-4.1-nano-2025-04-14 | $0.10 | $0.40 | 1M | $0.025 |
| gpt-4o | $2.50 | $10.00 | 125K | $1.25 |
| gpt-4o-2024-05-13 | $5.00 | $15.00 | 125K | — |
| gpt-4o-2024-08-06 | $2.50 | $10.00 | 125K | $1.25 |
| gpt-4o-2024-11-20 | $2.50 | $10.00 | 125K | $1.25 |
| gpt-4o-audio-preview | $2.50 | $10.00 | 125K | — |
| gpt-4o-audio-preview-2024-12-17 | $2.50 | $10.00 | 125K | — |
| gpt-4o-audio-preview-2025-06-03 | $2.50 | $10.00 | 125K | — |
| gpt-4o-mini | $0.15 | $0.60 | 125K | $0.075 |
| gpt-4o-mini-2024-07-18 | $0.15 | $0.60 | 125K | $0.075 |
| gpt-4o-mini-audio-preview | $0.15 | $0.60 | 125K | — |
| gpt-4o-mini-audio-preview-2024-12-17 | $0.15 | $0.60 | 125K | — |
| gpt-4o-mini-search-preview | $0.15 | $0.60 | 125K | $0.075 |
| gpt-4o-mini-search-preview-2025-03-11 | $0.15 | $0.60 | 125K | $0.075 |
| gpt-4o-search-preview | $2.50 | $10.00 | 125K | $1.25 |
| gpt-4o-search-preview-2025-03-11 | $2.50 | $10.00 | 125K | $1.25 |
| gpt-5 | $1.25 | $10.00 | 272K | $0.125 |
| gpt-5-2025-08-07 | $1.25 | $10.00 | 272K | $0.125 |
| gpt-5-chat | $1.25 | $10.00 | 125K | $0.125 |
| gpt-5-chat-latest | $1.25 | $10.00 | 125K | $0.125 |
| gpt-5-mini | $0.25 | $2.00 | 272K | $0.025 |
| gpt-5-mini-2025-08-07 | $0.25 | $2.00 | 272K | $0.025 |
| gpt-5-nano | $0.05 | $0.40 | 272K | $0.005 |
| gpt-5-nano-2025-08-07 | $0.05 | $0.40 | 272K | $0.005 |
| gpt-5-search-api | $1.25 | $10.00 | 272K | $0.125 |
| gpt-5-search-api-2025-10-14 | $1.25 | $10.00 | 272K | $0.125 |
| gpt-5.1 | $1.25 | $10.00 | 272K | $0.125 |
| gpt-5.1-2025-11-13 | $1.25 | $10.00 | 272K | $0.125 |
| gpt-5.1-chat-latest | $1.25 | $10.00 | 125K | $0.125 |
| gpt-5.2 | $1.75 | $14.00 | 272K | $0.175 |
| gpt-5.2-2025-12-11 | $1.75 | $14.00 | 272K | $0.175 |
| gpt-5.2-chat-latest | $1.75 | $14.00 | 125K | $0.175 |
| gpt-5.3-chat-latest | $1.75 | $14.00 | 125K | $0.175 |
| gpt-5.4 | $2.50 | $15.00 | 1M | $0.25 |
| gpt-5.4-2026-03-05 | $2.50 | $15.00 | 1M | $0.25 |
| gpt-5.4-mini | $0.75 | $4.50 | 272K | $0.075 |
| gpt-5.4-mini-2026-03-17 | $0.75 | $4.50 | 272K | $0.075 |
| gpt-5.4-nano | $0.20 | $1.25 | 272K | $0.02 |
| gpt-5.4-nano-2026-03-17 | $0.20 | $1.25 | 272K | $0.02 |
| gpt-5.5 | $5.00 | $30.00 | 1M | $0.50 |
| gpt-5.5-2026-04-23 | $5.00 | $30.00 | 1M | $0.50 |
| gpt-5.6 | $5.00 | $30.00 | 1M | $0.50 |
| gpt-5.6-luna | $0.20 | $1.20 | 1M | $0.02 |
| gpt-5.6-sol | $5.00 | $30.00 | 1M | $0.50 |
| gpt-5.6-terra | $2.00 | $12.00 | 1M | $0.20 |
| gpt-audio | $2.50 | $10.00 | 125K | — |
| gpt-audio-1.5 | $2.50 | $10.00 | 125K | — |
| gpt-audio-2025-08-28 | $2.50 | $10.00 | 125K | — |
| gpt-audio-mini | $0.60 | $2.40 | 125K | — |
| gpt-audio-mini-2025-10-06 | $0.60 | $2.40 | 125K | — |
| gpt-audio-mini-2025-12-15 | $0.60 | $2.40 | 125K | — |
| o1 | $15.00 | $60.00 | 200K | $7.50 |
| o1-2024-12-17 | $15.00 | $60.00 | 200K | $7.50 |
| o3 | $2.00 | $8.00 | 200K | $0.50 |
| o3-2025-04-16 | $2.00 | $8.00 | 200K | $0.50 |
| o3-mini | $1.10 | $4.40 | 200K | $0.55 |
| o3-mini-2025-01-31 | $1.10 | $4.40 | 200K | $0.55 |
| o4-mini | $1.10 | $4.40 | 200K | $0.275 |
| o4-mini-2025-04-16 | $1.10 | $4.40 | 200K | $0.275 |
Prices last synced Aug 20, 2026 from the LiteLLM community price catalog — the same catalog Marginal prices real usage events against, refreshed daily. Spot an error? Tell us.
Other providers
Using OpenAI in production?
Marginal prices every call your app makes against this catalog and slices spend by customer, feature, or any field you define. One track() call to integrate.