OpenAI Models

145 modelsGeneral models free to startUp to 1.05M context

Usage

Last 29 days · 2026-08-17 to 2026-09-14

Tokens

12.6B

Requests

60.1K

Models in use

16 of 145

Tokens per day, stacked by model

0981M2B08-1708-2408-3109-0709-142026-08-17 — 2,140 tokens gpt-5.6-sol: 1,300 5 more models: 8402026-08-18 — 3,085 tokens gpt-5.5: 1,845 gpt-5.6-sol: 960 5 more models: 2802026-08-19 — 75 tokens 5 more models: 752026-08-20 — 80 tokens gpt-4.1: 802026-08-21 — 1,060 tokens gpt-image-2: 1,0602026-08-22 — 0 tokens2026-08-23 — 0 tokens2026-08-24 — 0 tokens2026-08-25 — 0 tokens2026-08-26 — 3,880 tokens 5 more models: 3,350 gpt-5.6-sol: 5302026-08-27 — 2,910 tokens 5 more models: 2,365 gpt-5.6-sol: 445 gpt-5.5: 1002026-08-28 — 0 tokens2026-08-29 — 0 tokens2026-08-30 — 195 tokens 5 more models: 1952026-08-31 — 0 tokens2026-09-01 — 280,329,055 tokens gpt-5.5: 272,708,530 gpt-4.1: 6,039,950 gpt-4o: 958,675 gpt-image-2: 552,830 gpt-4.1-nano: 61,155 gpt-4.1-mini: 7,9152026-09-02 — 398,413,755 tokens gpt-5.5: 388,326,710 gpt-4.1: 6,443,095 gpt-4o: 2,231,515 gpt-image-2: 1,264,975 gpt-4.1-mini: 142,895 gpt-4.1-nano: 4,5652026-09-03 — 538,053,075 tokens gpt-5.5: 527,283,095 gpt-4.1: 6,630,115 gpt-image-2: 1,602,925 gpt-4o: 1,448,200 gpt-4.1-nano: 736,665 gpt-4.1-mini: 352,0752026-09-04 — 582,427,440 tokens gpt-5.5: 572,157,935 gpt-4.1: 8,049,480 gpt-4o: 1,178,360 gpt-image-2: 725,205 gpt-4.1-mini: 296,415 gpt-4.1-nano: 20,0452026-09-05 — 805,534,635 tokens gpt-5.5: 795,504,395 gpt-4.1: 6,533,720 gpt-image-2: 1,736,915 gpt-4.1-mini: 951,200 gpt-4o: 782,670 gpt-4.1-nano: 25,7352026-09-06 — 748,991,140 tokens gpt-5.5: 734,797,315 gpt-4.1: 11,149,000 gpt-image-2: 2,340,055 gpt-4o: 251,935 gpt-4.1-mini: 237,470 gpt-4.1-nano: 215,3652026-09-07 — 977,813,290 tokens gpt-5.5: 963,391,520 gpt-4.1: 9,396,180 gpt-image-2: 2,248,145 gpt-4o: 1,308,705 gpt-4.1-mini: 849,525 gpt-4.1-nano: 617,420 5 more models: 1,230 gpt-5.6-sol: 5652026-09-08 — 1,021,818,130 tokens gpt-5.5: 997,528,020 gpt-4.1: 9,071,195 gpt-4.1-mini: 8,154,555 gpt-image-2: 4,858,700 gpt-4o: 2,145,970 gpt-5.6-sol: 35,330 gpt-4.1-nano: 21,865 5 more models: 2,4952026-09-09 — 1,029,013,175 tokens gpt-5.5: 1,013,789,345 gpt-4.1: 9,770,240 gpt-image-2: 3,016,385 gpt-4.1-mini: 1,663,895 gpt-4o: 771,695 gpt-5.6-sol: 905 gpt-4.1-nano: 7102026-09-10 — 1,155,809,310 tokens gpt-5.5: 1,140,121,435 gpt-4.1: 12,325,430 gpt-image-2: 2,044,740 gpt-4o: 976,080 gpt-4.1-nano: 302,765 gpt-4.1-mini: 33,900 gpt-6-astra: 4,240 5 more models: 7202026-09-11 — 902,252,225 tokens gpt-5.5: 888,019,090 gpt-4.1: 10,124,450 gpt-image-2: 1,543,885 gpt-4o: 989,265 gpt-4.1-nano: 948,265 gpt-4.1-mini: 621,310 gpt-6-astra: 5,860 5 more models: 1002026-09-12 — 977,955,315 tokens gpt-5.5: 965,256,055 gpt-4.1: 9,274,800 gpt-image-2: 1,766,060 gpt-4.1-mini: 814,900 gpt-4o: 779,830 gpt-6-astra: 62,080 gpt-4.1-nano: 1,5902026-09-13 — 1,962,758,215 tokens gpt-5.5: 1,946,108,320 gpt-4.1: 11,371,270 gpt-4o: 2,931,755 gpt-image-2: 1,625,560 gpt-4.1-mini: 665,590 gpt-4.1-nano: 55,7202026-09-14 — 1,249,946,250 tokens gpt-5.5: 1,232,892,475 gpt-4.1: 9,847,915 gpt-image-2: 4,580,480 gpt-4.1-nano: 1,806,105 gpt-4o: 735,585 gpt-4.1-mini: 83,690
  • gpt-5.5
  • gpt-4.1
  • gpt-image-2
  • gpt-4o
  • gpt-4.1-mini
  • gpt-4.1-nano
  • gpt-6-astra
  • gpt-5.6-sol
  • 5 more models

Which models that traffic went to

  1. GPT 5.598.5%12.4B
  2. GPT 4.11.0%126M
  3. GPT Image 20.2%29.9M
  4. GPT 4o0.1%17.5M
  5. GPT 4.1 Mini0.1%14.9M
  6. GPT 4.1 Nano<0.1%4.8M
  7. GPT 6 Astra<0.1%72.2K
  8. GPT 5.6 Sol<0.1%40K
  9. 5 more models<0.1%11.7K

Share of 12.6B tokens. 3 models with traffic report no token counts and cannot be ranked here, including gpt-live-transcribe and gpt-oss-20b-free — they are in the request view.

The two views disagree on purpose: a model can take a large share of the calls and a small share of the tokens — many short requests — or the reverse. Which one matters depends on whether your cost is driven by call volume or by prompt length. Measured on AIHubMix over the last 29 days, counting the 145 model IDs listed on this page; traffic routed through upstream-specific IDs that are not in the public catalog is not included.

All 145 OpenAI Models

Open in model list
OpenAI models on AIHubMix with input and output modalities, context length, maximum output, price per million tokens including cache read and cache write rates, and measured throughput and latency.
Modalities
gpt-5.6-lunaTakes text, vision, returns text.1.05M128K$1$6/M$0.1/M$1.25/M88 tok/s2.20 s
gpt-5.5Takes text, vision, PDF, returns text.1.05M128K$2$12/M——45 tok/s6.35 s
gpt-5.4Takes text, vision, PDF. Output modality not published.1.05M128K$2.5$15/M$0.25/M———
gpt-5.6-terraTakes text, vision, returns text.1.05M128K$2.5$15/M$0.25/M$3.125/M56 tok/s3.55 s
gpt-6-astraTakes text, vision, returns text.1.05M128K$2.5$15/M$0.25/M$3.125/M——
gpt-5.6-solTakes text, vision, returns text.1.05M128K$5$30/M$0.5/M$6.25/M44 tok/s5.24 s
gpt-4.1-freeTakes text, vision, PDF, returns text.1.05M33KFreeFree/MFree/M—43 tok/s1.13 s
gpt-4.1-nanoTakes text, vision, PDF, returns text.1.05M33K$0.1$0.4/M$0.025/M—83 tok/s0.82 s
gpt-4.1-miniTakes text, vision, PDF, returns text.1.05M33K$0.4$1.6/M$0.1/M—58 tok/s0.74 s
gpt-4.1Takes text, vision, PDF, returns text.1.05M33K$2$8/M$0.5/M—71 tok/s1.13 s
gpt-5-nanoTakes text, vision, returns text.400K128K$0.05$0.4/M$0.005/M—106 tok/s3.58 s
gpt-5-miniTakes text, vision, returns text.400K128K$0.25$2/M$0.025/M—57 tok/s5.95 s
gpt-5.1-codex-miniTakes text, vision. Output modality not published.400K128K$0.25$2/M$0.025/M———
gpt-5Takes text, vision, returns text.400K128K$1.25$10/M$0.125/M—68 tok/s5.27 s
gpt-5-codexTakes text, vision, returns text.400K128K$1.25$10/M$0.125/M—27 tok/s7.54 s
gpt-5.1Takes text, vision, PDF, returns text.400K128K$1.25$10/M$0.125/M———
gpt-5.1-codexTakes text, vision. Output modality not published.400K128K$1.25$10/M$0.125/M———
gpt-5.1-codex-maxTakes text, vision, returns text.400K128K$1.25$10/M$0.125/M———
gpt-5.2Takes text, vision, PDF, returns text.400K128K$1.75$14/M$0.175/M———
gpt-5.2-codexTakes text, vision, PDF, returns text.400K128K$1.75$14/M$0.175/M—38 tok/s5.62 s
gpt-5.2-highTakes text, vision, PDF, returns text.400K128K$1.75$14/M$0.175/M———
gpt-5.3-codexTakes text, vision, PDF. Output modality not published.400K128K$1.75$14/M$0.175/M———
gpt-5-proTakes text, vision, returns text.400K272K$15$120/M——9 tok/s313.10 s
gpt-5.2-proTakes text, vision, returns text.400K128K$21$168/M$2.1/M———
hy3-previewTakes text. Output modality not published.256K128K$0.17$0.5666/M$0.051/M———
o3-miniTakes text, vision, returns text.200K—$1.1$4.4/M$0.55/M—474 tok/s10.90 s
o4-miniTakes text, vision, PDF, returns text.200K100K$1.1$4.4/M$0.275/M—44 tok/s5.80 s
codex-mini-latestTakes text, vision, returns text.200K—$1.5$6/M$0.375/M———
o3Takes text, vision, PDF, returns text.200K100K$2$8/M$0.5/M—40 tok/s6.46 s
o3-proTakes text, vision, returns text.200K100K$20$80/M$20/M—13 tok/s88.94 s
o1-proTakes text, returns text.200K—$170$680/M$170/M———
gpt-oss-20bTakes text, returns text.131K—$0.11$0.55/M——2619 tok/s0.12 s
gpt-oss-120bTakes text, returns text.131K—$0.18$0.9/M——1101 tok/s0.45 s
gpt-oss-20b-freeTakes text, returns text.131K—FreeFree/M————
gpt-4o-miniTakes text, vision, returns text.128K—$0.15$0.6/M$0.075/M—97 tok/s0.62 s
gpt-4o-mini-audio-previewTakes text, audio, returns text.128K16K$0.15$0.6/M————
gpt-4o-mini-search-previewTakes text, vision, returns text.128K—$0.15$0.6/M$0.075/M—189 tok/s1.57 s
gpt-5-chat-latestTakes text, vision, returns text.128K16K$1.25$10/M$0.125/M—77 tok/s0.85 s
gpt-5.1-chat-latestTakes text, vision. Output modality not published.128K16K$1.25$10/M$0.125/M———
gpt-5.3-chat-latestTakes text, vision, returns text.128K16K$1.75$14/M$0.175/M———
gpt-4oTakes text, vision, PDF, returns text.128K16K$2.5$10/M$1.25/M—52 tok/s0.64 s
gpt-4o-2024-11-20Takes text, vision, returns text.128K—$2.5$10/M$1.25/M—61 tok/s0.60 s
gpt-4o-audio-previewTakes text, audio, returns text.128K16K$2.5$10/M——10 tok/s2.49 s
gpt-4o-search-previewTakes text, vision, returns text.128K—$2.5$10/M$1.25/M—121 tok/s2.33 s
gpt-audio-1.5Takes text, audio. Output modality not published.128K16K$2.5$10/M————
o1Takes text, returns text.0K—$15$60/M$7.5/M———
dall-e-2Takes text, vision, returns vision.——FreeFree/M————
dall-e-3Takes text, vision, returns vision.——FreeFree/M————
gpt-4o-imageTakes text, vision, returns vision.——FreeFree/M————
gpt-4o-image-vipTakes text, vision, returns vision.——FreeFree/M————
gpt-4o-mini-ttsTakes audio, returns audio.——FreeFree/M———0.95 s
gpt-image-1Takes text, vision, returns vision.——FreeFree/M————
gpt-image-1-miniTakes text, vision, returns vision.——FreeFree/M————
gpt-live-transcribe——FreeFree/M————
sora-2Takes , returns video.——FreeFree/M————
sora-2-proTakes , returns video.——Free$720/M————
web-sora-2Takes , returns video.——FreeFree/M————
web-sora-2-proTakes , returns video.——FreeFree/M————
whisper-1Takes audio, returns text.——FreeFree/M————
whisper-1-proTakes audio, returns text.——FreeFree/M————
whisper-large-v3Takes audio, returns text.——FreeFree/M————
whisper-large-v3-turboTakes audio, returns text.——FreeFree/M————
text-embedding-3-smallTakes text. Output modality not published.——$0.02$0.02/M————
text-embedding-ada-002Takes text. Output modality not published.——$0.1$0.1/M————
text-embedding-v1Takes text. Output modality not published.——$0.1$0.1/M————
text-embedding-3-largeTakes text. Output modality not published.——$0.13$0.13/M————
gpt-4o-mini-2024-07-18Takes text, vision, returns text.——$0.15$0.6/M$0.075/M———
gpt-4o-mini-global——$0.15$0.6/M$0.075/M———
omni-moderation-latest——$0.2$0.2/M————
text-moderation-007——$0.2$0.2/M————
text-moderation-latest——$0.2$0.2/M————
text-moderation-stable——$0.2$0.2/M————
aihubmix-routerTakes text, vision, returns text.——$0.4$1.6/M$0.1/M———
aistudio_gpt-4.1-mini——$0.4$1.6/M$0.1/M———
text-ada-001——$0.4$0.4/M————
gpt-3.5-turbo——$0.5$1.5/M————
gpt-3.5-turbo-0125——$0.5$1.5/M————
text-babbage-001——$0.5$0.5/M————
gpt-3.5-turbo-1106——$1$2/M————
o3-mini-global——$1.1$4.4/M$0.55/M———
gpt-3.5-turbo-0301——$1.5$1.5/M————
gpt-3.5-turbo-0613——$1.5$2/M————
gpt-3.5-turbo-instruct——$1.5$2/M————
davinci-002——$2$2/M————
gpt-image-2Takes text, vision. Output modality not published.——$2$2/M————
kling-v1——$2$2/M————
kling-v1-5——$2$2/M————
kling-v1-6——$2$2/M————
kling-v2-1——$2$2/M————
kling-v2-1-master——$2$2/M————
kling-v2-5-turbo——$2$2/M————
kling-v2-6——$2$2/M————
kling-v2-master——$2$2/M————
kling-v3——$2$2/M————
kling-v3-omniTakes text, vision, video. Output modality not published.——$2$2/M————
kling-video-o1Takes text, vision, video. Output modality not published.——$2$2/M————
o3-global——$2$8/M$0.5/M———
sora-2-hd——$2$2/M————
text-curie-001——$2$2/M————
web-gpt-image-1.5——$2$2/M————
web-gpt-image-1.5-pro——$2$2/M————
gpt-4o-2024-08-06——$2.5$10/M$1.25/M———
gpt-4o-2024-08-06-global——$2.5$10/M$1.25/M———
gpt-4o-transcribe-diarize——$2.5$10/M————
gpt-4o-zhTakes text, vision, returns text.——$2.5$10/M————
computer-use-preview——$3$12/M————
gpt-3.5-turbo-16k——$3$4/M————
gpt-3.5-turbo-16k-0613——$3$4/M————
o1-mini——$3$12/M$1.5/M———
o1-mini-2024-09-12——$3$12/M$1.5/M———
chatgpt-4o-latestTakes text, vision, returns text.——$5$15/M————
gpt-4o-2024-05-13——$5$15/M$5/M—199 tok/s0.45 s
gpt-image-test——$5$40/M————
distil-whisper-large-v3-enTakes audio, returns text.——$5.556$5.556/M————
text-embedding-3-large-proTakes text. Output modality not published.——$7$7/M————
gpt-4-0125-preview——$10$30/M————
gpt-4-1106-preview——$10$30/M————
gpt-4-turbo——$10$30/M————
gpt-4-turbo-2024-04-09——$10$30/M————
gpt-4-turbo-preview——$10$30/M————
gpt-4-vision-preview——$10$30/M————
o1-2024-12-17Takes text, vision, returns text.——$15$60/M$7.5/M———
o1-previewTakes text, vision, returns text.——$15$60/M$7.5/M———
o1-preview-2024-09-12——$15$60/M$7.5/M———
tts-1Takes audio, returns audio.——$15$15/M————
tts-1-1106Takes audio, returns audio.——$15$15/M————
davinci——$20$20/M————
o3-pro-global——$20$80/M————
text-davinci-002——$20$20/M————
text-davinci-003——$20$20/M————
text-davinci-edit-001——$20$20/M————
text-search-ada-doc-001——$20$20/M————
wan2.2-i2v-plus——$20$20/M————
wan2.2-t2v-plusTakes , returns video.——$20$20/M————
wan2.5-i2v-preview——$20$20/M————
wan2.5-t2v-previewTakes , returns video.——$20$20/M————
gpt-4——$30$60/M————
gpt-4-0314——$30$60/M————
gpt-4-0613——$30$60/M————
tts-1-hdTakes audio, returns audio.——$30$30/M————
tts-1-hd-1106Takes audio, returns audio.——$30$30/M————
gpt-4.1-proTakes text, vision, returns text.——$40$160/M$10/M—96 tok/s0.53 s
gpt-4-32k——$60$120/M————
gpt-4-32k-0314——$60$120/M————
gpt-4-32k-0613——$60$120/M————

Prices are USD per million tokens; cache read and cache write are the rates for prompt-cache hits and for writing a prompt into the cache. Throughput and latency are measured on AIHubMix — the same figures the model detail page shows — not vendor claims. A dash means the catalog does not publish that field for that model, which is not the same as the model not supporting it.

Common Comparisons

aihubmix-router vs chatgpt-4o-latestaihubmix-router vs codex-mini-latestaihubmix-router vs gpt-4.1aihubmix-router vs deepseek-v4-flashahm-Phi-3-5-vision-instruct vs aihubmix-router

OpenAI on AIHubMix

Which OpenAI model should I start with?

gpt-4.1-free is free on input — the cheapest entry here that declares tool calling, and it carries a 1.05M context. Move up to o1-pro when answer quality matters more than cost, or to gpt-5.6-luna for long-form reasoning.

Which of these models reason before answering?

25 of the 145 models here declare a reasoning phase — they work through the problem before producing an answer, which helps on multi-step problems at the cost of extra output tokens. Use the Reasoning filter above the table to see them. The catalog does not record anything further about how they differ, so this page does not sort them into families.

Why are there several entries for the same model?

Because each row is a route you can call, not a model release. Some IDs name an upstream (azure-, alicloud-, cc-), and some differ only in capitalisation, kept so older integrations keep working.

The catalog does not carry a field saying which of those a given row is, so this page does not sort them into buckets it would have to invent. Every row shows that route’s own price, context and speed — compare those directly, and open a model to see the upstreams that serve it.

How is cached input billed?

The Cache read column is the rate for input tokens served from the prompt cache — for example gpt-5 bills cache hits at 10% of the input rate and gpt-5-chat-latest bills cache hits at 10% of the input rate. Cache write is the surcharge for putting a prompt into the cache in the first place, and only a few upstreams bill it separately. A dash in either column means the catalog carries no cache rate for that model, so plan on paying the full input rate.

Do I need a separate OpenAI account?

No. One AIHubMix key covers every model on this page, and switching between them is a change to the model string — billing, rate limits, and logs stay in one place.

Other Model Authors

See all model authors →
Qwen
118 modelsGoogle
97 modelsLlama
42 modelsChatGLM
40 modelsDeepSeek
33 models

Start calling OpenAI in one line

One key, one endpoint, 750 models across 29 model authors.

Get API keyRead the docs

© 2023 - 2026 AIHubMix, LLC

Product

Developer

Connect

Terms & Policies