Pricing / OpenAI

OpenAI API pricing

145 model entries. OpenAI entries in the bundled pricing snapshot. Source rate fields are shown as encoded in the snapshot dated 2026-03-25; model modality is not encoded.

Lowest encoded input rate

$0.05/1M

gpt-5-nano

Highest encoded input rate

$150/1M

o1-pro-2025-03-19

Models with cache pricing

79 of 145

Interpret the /1M columns as token rates only for models independently verified as token-billed. Non-text billing units are not represented in this snapshot schema.

ModelInput $/1MOutput $/1MCache $/1M
gpt-5-nano$0.05$0.4$0.005
gpt-5-nano-2025-08-07$0.05$0.4$0.005
gpt-4.1-nano$0.1$0.4$0.025
gpt-4.1-nano-2025-04-14$0.1$0.4$0.025
gpt-4o-mini$0.15$0.6$0.075
gpt-4o-mini-2024-07-18$0.15$0.6$0.075
gpt-4o-mini-audio-preview$0.15$0.6-
gpt-4o-mini-audio-preview-2024-12-17$0.15$0.6-
gpt-4o-mini-search-preview$0.15$0.6$0.075
gpt-4o-mini-search-preview-2025-03-11$0.15$0.6$0.075
gpt-5.4-nano$0.2$1.25$0.02
ft:gpt-4.1-nano-2025-04-14$0.2$0.8$0.05
gpt-5-mini$0.25$2$0.025
gpt-5.1-codex-mini$0.25$2$0.025
gpt-5-mini-2025-08-07$0.25$2$0.025
ft:gpt-4o-mini$0.3$1.2-
gpt-4o-mini-2024-07-18.ft-$0.3$1.2-
ft:gpt-4o-mini-2024-07-18$0.3$1.2$0.15
gpt-4.1-mini$0.4$1.6$0.1
ada$0.4$0.4-
gpt-4.1-mini-2025-04-14$0.4$1.6$0.1
babbage$0.5$0.5-
gpt-3.5-turbo$0.5$1.5-
gpt-3.5-turbo-0125$0.5$1.5-
gpt-4o-mini-realtime-preview$0.6$2.4$0.3
gpt-realtime-mini$0.6$2.4$0.06
gpt-audio-mini$0.6$2.4-
gpt-audio-mini-2025-10-06$0.6$2.4-
gpt-audio-mini-2025-12-15$0.6$2.4-
gpt-4o-mini-realtime-preview-2024-12-17$0.6$2.4$0.3
gpt-realtime-mini-2025-10-06$0.6$2.4$0.06
gpt-realtime-mini-2025-12-15$0.6$2.4$0.06
gpt-5.4-mini$0.75$4.5$0.075
ft:gpt-4.1-mini-2025-04-14$0.8$3.2$0.2
gpt-3.5-turbo-1106$1$2-
o4-mini$1.1$4.4$0.275
o3-mini$1.1$4.4$0.55
o3-mini-2025-01-31$1.1$4.4$0.55
o4-mini-2025-04-16$1.1$4.4$0.275
gpt-4o-mini-transcribe$1.25$5-
gpt-5$1.25$10$0.125
gpt-5.1$1.25$10$0.125
gpt-5.1-2025-11-13$1.25$10$0.125
gpt-5.1-chat-latest$1.25$10$0.125
gpt-5-2025-08-07$1.25$10$0.125
gpt-5-chat$1.25$10$0.125
gpt-5-chat-latest$1.25$10$0.125
gpt-5-codex$1.25$10$0.125
gpt-5.1-codex$1.25$10$0.125
gpt-5.1-codex-max$1.25$10$0.125
gpt-4o-mini-transcribe-2025-03-20$1.25$5-
gpt-4o-mini-transcribe-2025-12-15$1.25$5-
gpt-5-search-api$1.25$10$0.125
gpt-5-search-api-2025-10-14$1.25$10$0.125
codex-mini$1.5$6$0.375
gpt-3.5-0301$1.5$2-
gpt-3.5-turbo-0613$1.5$2-
gpt-3.5-turbo-instruct$1.5$2-
codex-mini-latest$1.5$6$0.375
gpt-5.2$1.75$14$0.175
gpt-5.3-codex$1.75$14$0.175
gpt-5.2-2025-12-11$1.75$14$0.175
gpt-5.2-chat-latest$1.75$14$0.175
gpt-5.3-chat-latest$1.75$14$0.175
gpt-5.2-codex$1.75$14$0.175
gpt-4.1$2$8$0.5
o3$2$8$0.5
curie$2$2-
o4-mini-deep-research$2$8$0.5
gpt-4.1-2025-04-14$2$8$0.5
o3-2025-04-16$2$8$0.5
o4-mini-deep-research-2025-06-26$2$8$0.5
gpt-4o$2.5$10$1.25
gpt-4o-search-preview$2.5$10-
gpt-4o-transcribe$2.5$10-
gpt-5-image-mini$2.5$2$0.25
gpt-5.4$2.5$15$0.25
gpt-4o-transcribe-diarize$2.5$10-
gpt-4o-2024-08-06$2.5$10$1.25
gpt-4o-2024-11-20$2.5$10$1.25
gpt-4o-audio-preview$2.5$10-
gpt-4o-audio-preview-2024-12-17$2.5$10-
gpt-4o-audio-preview-2025-06-03$2.5$10-
gpt-audio$2.5$10-
gpt-audio-1.5$2.5$10-
gpt-audio-2025-08-28$2.5$10-
gpt-4o-mini-tts$2.5$10-
gpt-4o-search-preview-2025-03-11$2.5$10$1.25
gpt-5.4-2026-03-05$2.5$15$0.25
gpt-4o-mini-tts-2025-03-20$2.5$10-
gpt-4o-mini-tts-2025-12-15$2.5$10-
computer-use$3$12-
ft:gpt-3.5-turbo-$3$6-
gpt-3.5-turbo-16k$3$4-
o1-mini$3$12$1.5
ft:gpt-3.5-turbo$3$6-
ft:gpt-3.5-turbo-0125$3$6-
ft:gpt-3.5-turbo-0613$3$6-
ft:gpt-3.5-turbo-1106$3$6-
ft:gpt-4.1-2025-04-14$3$12$0.75
ft:gpt-4o$3.75$15-
ft:gpt-4o-2024-08-06$3.75$15$1.875
ft:gpt-4o-2024-11-20$3.75$15-
gpt-realtime$4$16$0.4
ft:o4-mini-2025-04-16$4$16$1
gpt-realtime-1.5$4$16$0.4
gpt-realtime-2025-08-28$4$16$0.4
chatgpt-4o-latest$5$15-
gpt-4o-realtime-preview$5$20$2.5
gpt-4o-2024-05-13$5$15-
gpt-4o-realtime-preview-2024-12-17$5$20$2.5
gpt-4o-realtime-preview-2025-06-03$5$20$2.5
gpt-image-1.5$5$10$1.25
gpt-image-1.5-2025-12-16$5$10$1.25
gpt-4o:extended$6$18-
gpt-4-turbo$10$30-
gpt-4-vision-preview$10$30-
gpt-5-image$10$10$1.25
o3-deep-research$10$40$2.5
gpt-4-0125-preview$10$30-
gpt-4-1106-preview$10$30-
gpt-4-turbo-2024-04-09$10$30-
gpt-4-turbo-preview$10$30-
o3-deep-research-2025-06-26$10$40$2.5
gpt-5-pro$15$120-
o1$15$60$7.5
gpt-5-pro-2025-10-06$15$120-
o1-2024-12-17$15$60$7.5
davinci$20$20-
o3-pro$20$80-
text-davinci-002$20$20-
text-davinci-003$20$20-
o3-pro-2025-06-10$20$80-
gpt-5.2-pro$21$168-
gpt-5.2-pro-2025-12-11$21$168-
gpt-4$30$60-
gpt-5.4-pro$30$180-
ft:gpt-4-0613$30$60-
gpt-4-0314$30$60-
gpt-4-0613$30$60-
gpt-5.4-pro-2026-03-05$30$180$3
gpt-4-32k$60$120-
gpt-4.5-preview$75$150$37.5
o1-pro$150$600-
o1-pro-2025-03-19$150$600-

Use the OpenAI snapshot as a reference, then measure the request

Local tracking can estimate supported responses from provider usage fields. The authenticated gateway path adds request identity, persisted cost evidence, session attribution, and pre-dispatch budget checks.