AIHubMixAIHubMix

OpenAI Models

132 modelsGeneral models free to startUp to 1.05M context

Usage

Last 30 days · 2026-07-13 to 2026-08-11

Tokens

880B

Requests

78.6M

Models in use

93 of 132

Tokens per day

021.2B42.3B07-1307-2007-2708-0308-102026-07-13 — 28,353,339,310 tokens2026-07-14 — 30,836,700,910 tokens2026-07-15 — 27,688,584,720 tokens2026-07-16 — 26,291,723,400 tokens2026-07-17 — 25,477,456,940 tokens2026-07-18 — 12,745,804,185 tokens2026-07-19 — 13,975,255,635 tokens2026-07-20 — 25,810,946,880 tokens2026-07-21 — 30,152,896,050 tokens2026-07-22 — 30,264,790,265 tokens2026-07-23 — 40,517,039,990 tokens2026-07-24 — 28,732,551,680 tokens2026-07-25 — 20,010,756,565 tokens2026-07-26 — 25,980,763,140 tokens2026-07-27 — 34,505,734,605 tokens2026-07-28 — 29,775,592,555 tokens2026-07-29 — 40,284,628,720 tokens2026-07-30 — 35,926,184,290 tokens2026-07-31 — 38,015,732,575 tokens2026-08-01 — 20,018,253,305 tokens2026-08-02 — 21,015,565,540 tokens2026-08-03 — 37,793,266,535 tokens2026-08-04 — 34,685,812,190 tokens2026-08-05 — 33,371,692,435 tokens2026-08-06 — 42,306,061,005 tokens2026-08-07 — 38,686,165,170 tokens2026-08-08 — 22,805,001,245 tokens2026-08-09 — 17,022,783,570 tokens2026-08-10 — 32,048,569,365 tokens2026-08-11 — 34,668,267,545 tokens

Which models that traffic went to

  1. gpt-5.6-sol23.9%210B
  2. gpt-4o-mini14.2%125B
  3. gpt-5.6-luna12.6%110B
  4. gpt-5.511.5%101B
  5. gpt-5.6-terra7.2%63B
  6. gpt-5.46.8%59.7B
  7. gpt-5.4-mini5.2%45.5B
  8. omni-moderation-latest5.1%45B
  9. 71 more models13.7%120B

Share of 880B tokens. 14 models with traffic report no token counts and cannot be ranked here, including auto and dall-e-3 — 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 30 days, counting the 132 model IDs listed on this page; traffic routed through upstream-specific IDs that are not in the public catalog is not included.

All 132 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-5.5-freeTakes text, vision, returns text.1.05M128KFreeFree/MFree/M—42 tok/s3.58 s
gpt-5.6-lunaTakes text, vision, returns text.1.05M128K$0.20$1.20/M$0.02/M$0.25/M104 tok/s4.07 s
gpt-5.6-terraTakes text, vision, returns text.1.05M128K$2.00$12.00/M$0.20/M$2.50/M56 tok/s4.50 s
gpt-5.4Takes text, vision, returns text.1.05M128K$2.50$15.00/M$0.25/M—48 tok/s1.65 s
gpt-5.5Takes text, vision, returns text.1.05M128K$5.00$30.00/M$0.50/M—39 tok/s4.00 s
gpt-5.6-solTakes text, vision, returns text.1.05M128K$5.00$30.00/M$0.50/M$6.25/M40 tok/s5.90 s
gpt-5.4-proTakes text, vision, returns text.1.05M128K$30.00$180.00/M——43 tok/s3.61 s
gpt-5.5-proTakes text, vision, returns text.1.05M128K$30.00$180.00/M——14 tok/s19.20 s
gpt-4.1-freeTakes text, vision, returns text.1.05M33KFreeFree/MFree/M—72 tok/s0.53 s
gpt-4.1-mini-freeTakes text, vision, returns text.1.05M33KFreeFree/MFree/M—59 tok/s0.36 s
gpt-4.1-nano-freeTakes text, vision, returns text.1.05M33KFreeFree/MFree/M—110 tok/s0.33 s
gpt-4o-freeTakes text, vision, returns text.1.05M33KFreeFree/MFree/M—72 tok/s0.53 s
gpt-4.1-nanoTakes text, vision, returns text.1.05M33K$0.10$0.40/M$0.03/M—73 tok/s0.82 s
gpt-4.1-miniTakes text, vision, returns text.1.05M33K$0.40$1.60/M$0.10/M—58 tok/s0.74 s
gpt-4.1Takes text, vision, returns text.1.05M33K$2.00$8.00/M$0.50/M—67 tok/s1.13 s
autoTakes text, vision, audio, video, returns text.1M—FreeFree/M————
gpt-5-nanoTakes text, vision, returns text.400K128K$0.05$0.40/M$0.005/M—83 tok/s5.06 s
gpt-5.4-nanoTakes text, vision, returns text.400K128K$0.20$1.25/M$0.02/M—103 tok/s0.68 s
gpt-5-miniTakes text, vision, returns text.400K128K$0.25$2.00/M$0.03/M—75 tok/s3.28 s
gpt-5.1-codex-miniTakes text, vision, returns text.400K128K$0.25$2.00/M$0.03/M—168 tok/s0.70 s
gpt-5.4-miniTakes text, vision, returns text.400K128K$0.75$4.50/M$0.07/M—105 tok/s1.19 s
gpt-5Takes text, vision, returns text.400K128K$1.25$10.00/M$0.13/M—65 tok/s7.76 s
gpt-5-chat-latestTakes text, vision, returns text.400K128K$1.25$10.00/M$0.13/M—77 tok/s0.85 s
gpt-5-codexTakes text, vision, returns text.400K128K$1.25$10.00/M$0.13/M—27 tok/s7.54 s
gpt-5.1Takes text, vision, returns text.400K128K$1.25$10.00/M$0.13/M—92 tok/s1.07 s
gpt-5.1-codexTakes text, vision, returns text.400K128K$1.25$10.00/M$0.13/M—82 tok/s0.62 s
gpt-5.1-codex-maxTakes text, vision, returns text.400K128K$1.25$10.00/M$0.13/M———
gpt-5.2Takes text, vision, returns text.400K128K$1.75$14.00/M$0.17/M—96 tok/s2.53 s
gpt-5.2-codexTakes text, vision, returns text.400K128K$1.75$14.00/M$0.17/M—82 tok/s0.66 s
gpt-5.2-highTakes text, vision, returns text.400K128K$1.75$14.00/M$0.17/M———
gpt-5.2-lowTakes text, vision, returns text.400K128K$1.75$14.00/M$0.17/M———
gpt-5.3-codexTakes text, vision, returns text.400K128K$1.75$14.00/M$0.17/M—65 tok/s3.40 s
gpt-5.4-highTakes text, vision, returns text.400K128K$2.50$15.00/M$0.25/M———
gpt-5.4-lowTakes text, vision, returns text.400K128K$2.50$15.00/M$0.25/M———
gpt-chat-latestTakes text, vision, returns text.400K128K$5.00$30.00/M$0.50/M—49 tok/s2.06 s
gpt-5-proTakes text, vision, returns text.400K128K$15.00$120.00/M——9 tok/s313.10 s
gpt-5.2-proTakes text, vision, returns text.400K128K$21.00$168.00/M$2.10/M—7 tok/s19.54 s
o3-miniTakes text, vision, returns text.200K100K$1.10$4.40/M$0.55/M—474 tok/s10.90 s
o4-miniTakes text, vision, returns text.200K100K$1.10$4.40/M$0.28/M—79 tok/s5.80 s
codex-mini-latestTakes text, vision, returns text.200K—$1.50$6.00/M$0.38/M———
o3Takes text, vision, returns text.200K100K$2.00$8.00/M$0.50/M—87 tok/s6.46 s
o3-proTakes text, vision, returns text.200K100K$20.00$80.00/M$20.00/M—13 tok/s88.94 s
o1-proTakes text, returns text.200K—$170.00$680.00/M$170.00/M—19 tok/s96.00 s
gpt-oss-20b-freeTakes text, returns text.131K—FreeFree/M————
gpt-oss-120bTakes text, returns text.131K33K$0.18$0.90/M——1101 tok/s0.20 s
gpt-oss-20bTakes text, returns text.128K—$0.11$0.55/M——2619 tok/s0.12 s
gpt-4o-miniTakes text, vision, returns text.128K16K$0.15$0.60/M$0.07/M—39 tok/s0.62 s
gpt-4o-mini-search-previewTakes text, vision, returns text.128K16K$0.15$0.60/M$0.07/M—189 tok/s0.91 s
gpt-5.1-chat-latestTakes text, vision, returns text.128K16K$1.25$10.00/M$0.13/M—107 tok/s0.95 s
gpt-5.2-chat-latestTakes text, vision, returns text.128K16K$1.75$14.00/M$0.17/M—84 tok/s0.91 s
gpt-5.3-chat-latestTakes text, vision, returns text.128K16K$1.75$14.00/M$0.17/M—85 tok/s0.82 s
gpt-4oTakes text, vision, returns text.128K16K$2.50$10.00/M$1.25/M—52 tok/s0.64 s
gpt-4o-2024-11-20Takes text, vision, returns text.128K16K$2.50$10.00/M$1.25/M—61 tok/s0.60 s
gpt-4o-audio-previewTakes text, audio, returns text.128K16K$2.50$10.00/M——10 tok/s2.49 s
gpt-4o-search-previewTakes text, vision, returns text.128K16K$2.50$10.00/M$1.25/M—121 tok/s2.33 s
gpt-audio-1.5Takes text, audio, returns text, audio.128K16K$2.50$10.00/M————
gpt-4o-2024-05-13128K4K$5.00$15.00/M$5.00/M—199 tok/s0.45 s
gpt-4o-transcribe-diarizeTakes text, audio, returns text.16K2K$2.50$10.00/M————
o1Takes text, returns text.0K—$15.00$60.00/M$7.50/M—39 tok/s9.40 s
dall-e-2Takes text, vision, returns vision.——FreeFree/M————
dall-e-3Takes text, vision, returns vision.——FreeFree/M————
gpt-image-1Takes text, vision, returns vision.——FreeFree/M————
gpt-image-1-miniTakes text, vision, returns vision.——FreeFree/M————
gpt-image-1.5Takes text, vision, returns vision.——FreeFree/M————
gpt-image-2Takes text, vision, returns text, vision.——FreeFree/M————
gpt-image-2-freeTakes text, vision, returns text, vision.——FreeFree/M————
sora-2Takes , returns video.——FreeFree/M————
sora-2-proTakes , returns video.——Free$720.00/M————
whisper-1Takes audio, returns text.——FreeFree/M————
whisper-large-v3Takes audio, returns text.——FreeFree/M————
whisper-large-v3-turboTakes audio, returns text.——FreeFree/M————
omni-moderation-latest——$0.02$0.02/M————
text-embedding-3-smallTakes text. Output modality not published.——$0.02$0.02/M————
text-embedding-ada-002Takes text. Output modality not published.——$0.10$0.10/M————
text-embedding-v1Takes text. Output modality not published.——$0.10$0.10/M————
GPT-OSS-20B——$0.11$0.55/M——2619 tok/s0.12 s
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$0.60/M$0.07/M———
gpt-4o-mini-audio-previewTakes text, audio, returns text.——$0.15$0.60/M————
gpt-4o-mini-global——$0.15$0.60/M$0.07/M———
text-moderation-007——$0.20$0.20/M————
text-moderation-latest——$0.20$0.20/M————
text-moderation-stable——$0.20$0.20/M————
aihubmix-routerTakes text, vision, returns text.——$0.40$1.60/M$0.10/M———
text-ada-001——$0.40$0.40/M————
gpt-3.5-turbo——$0.50$1.50/M————
text-babbage-001——$0.50$0.50/M————
gpt-4o-mini-ttsTakes audio, returns audio.——$0.60$12.00/M———0.95 s
gpt-3.5-turbo-1106——$1.00$2.00/M————
o3-mini-global——$1.10$4.40/M$0.55/M———
gpt-3.5-turbo-0301——$1.50$1.50/M————
gpt-3.5-turbo-0613——$1.50$2.00/M————
gpt-3.5-turbo-instruct——$1.50$2.00/M————
davinci-002——$2.00$2.00/M————
o3-global——$2.00$8.00/M$0.50/M———
text-curie-001——$2.00$2.00/M————
gpt-4o-2024-08-06——$2.50$10.00/M$1.25/M———
gpt-4o-2024-08-06-global——$2.50$10.00/M$1.25/M———
gpt-4o-zhTakes text, vision, returns text.——$2.50$10.00/M————
computer-use-preview——$3.00$12.00/M————
gpt-3.5-turbo-16k——$3.00$4.00/M————
gpt-3.5-turbo-16k-0613——$3.00$4.00/M————
o1-mini——$3.00$12.00/M$1.50/M———
o1-mini-2024-09-12——$3.00$12.00/M$1.50/M———
gpt-image-test——$5.00$40.00/M————
distil-whisper-large-v3-enTakes audio, returns text.——$5.56$5.56/M————
gpt-4-0125-preview——$10.00$30.00/M————
gpt-4-1106-preview——$10.00$30.00/M————
gpt-4-turbo——$10.00$30.00/M————
gpt-4-turbo-2024-04-09——$10.00$30.00/M————
gpt-4-turbo-preview——$10.00$30.00/M————
gpt-4-vision-preview——$10.00$30.00/M————
o3-deep-research——$10.00$40.00/M$2.50/M———
o1-2024-12-17Takes text, vision, returns text.——$15.00$60.00/M$7.50/M———
o1-previewTakes text, vision, returns text.——$15.00$60.00/M$7.50/M———
o1-preview-2024-09-12——$15.00$60.00/M$7.50/M———
tts-1Takes audio, returns audio.——$15.00$15.00/M————
tts-1-1106Takes audio, returns audio.——$15.00$15.00/M————
davinci——$20.00$20.00/M————
o3-pro-global——$20.00$80.00/M————
text-davinci-002——$20.00$20.00/M————
text-davinci-003——$20.00$20.00/M————
text-davinci-edit-001——$20.00$20.00/M————
text-search-ada-doc-001——$20.00$20.00/M————
gpt-4——$30.00$60.00/M————
gpt-4-0314——$30.00$60.00/M————
gpt-4-0613——$30.00$60.00/M————
tts-1-hdTakes audio, returns audio.——$30.00$30.00/M————
tts-1-hd-1106Takes audio, returns audio.——$30.00$30.00/M————
gpt-4-32k——$60.00$120.00/M————
gpt-4-32k-0314——$60.00$120.00/M————
gpt-4-32k-0613——$60.00$120.00/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 autoaihubmix-router vs codex-mini-latestaihubmix-router vs gpt-4.1aihubmix-router vs qwen3.8-max-previewaihubmix-router vs kimi-k3

OpenAI on AIHubMix

Which OpenAI model should I start with?

auto is free on input — the cheapest entry here that declares tool calling, and it carries a 1M context. Move up to o1-pro when answer quality matters more than cost, or to gpt-5.5-free for long-form reasoning.

Which of these models reason before answering?

41 of the 132 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 Providers

Qwen
140 modelsGoogle
81 modelsZ.AI
64 modelsLlama
52 modelsByteDance
46 models

Start calling OpenAI in one line

One key, one endpoint, 844 models across 35 providers.

Get API keyRead the docs
AIHubMix

© 2023 - 2026 AIHubMix, LLC

Product

Company

Developer

Connect