AIHubMixAIHubMix

Google Models

81 modelsGeneral models free to startUp to 1.05M context

Usage

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

Tokens

214B

Requests

10M

Models in use

61 of 81

Tokens per day

05.4B10.8B07-1307-2007-2708-0308-102026-07-13 — 8,832,449,225 tokens2026-07-14 — 9,736,433,250 tokens2026-07-15 — 8,805,209,180 tokens2026-07-16 — 8,460,816,125 tokens2026-07-17 — 8,866,332,850 tokens2026-07-18 — 5,146,173,010 tokens2026-07-19 — 3,497,718,275 tokens2026-07-20 — 8,897,868,700 tokens2026-07-21 — 7,941,650,970 tokens2026-07-22 — 8,150,756,970 tokens2026-07-23 — 7,159,427,365 tokens2026-07-24 — 7,028,359,445 tokens2026-07-25 — 5,733,912,780 tokens2026-07-26 — 4,706,479,655 tokens2026-07-27 — 8,545,324,240 tokens2026-07-28 — 10,802,619,705 tokens2026-07-29 — 7,310,657,915 tokens2026-07-30 — 7,856,012,750 tokens2026-07-31 — 7,893,096,470 tokens2026-08-01 — 4,715,010,330 tokens2026-08-02 — 3,770,330,610 tokens2026-08-03 — 7,546,038,070 tokens2026-08-04 — 7,250,277,565 tokens2026-08-05 — 8,254,070,455 tokens2026-08-06 — 8,575,011,610 tokens2026-08-07 — 6,947,614,675 tokens2026-08-08 — 3,443,995,085 tokens2026-08-09 — 3,272,614,455 tokens2026-08-10 — 7,243,182,415 tokens2026-08-11 — 7,125,078,760 tokens

Which models that traffic went to

  1. gemini-3-flash-preview21.7%46.3B
  2. gemini-3.1-pro-preview15.6%33.4B
  3. gemini-3.1-flash-lite15.4%32.9B
  4. gemini-2.5-flash-lite10.7%22.8B
  5. gemini-3.5-flash10.1%21.6B
  6. gemini-2.5-flash5.3%11.3B
  7. gemini-3.6-flash4.9%10.5B
  8. gemini-2.5-flash-nothink3.6%7.6B
  9. 34 more models12.7%27.2B

Share of 214B tokens. 19 models with traffic report no token counts and cannot be ranked here, including gemini-3.1-flash-image-preview and gemini-3-pro-image-preview — 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 81 model IDs listed on this page; traffic routed through upstream-specific IDs that are not in the public catalog is not included.

All 81 Google Models

Open in model list
Google 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
gemini-3-flash-preview-freeTakes text, vision, audio, video, returns text.1.05M66KFreeFree/M———
gemini-3.5-flash-lite-freeTakes text, vision, audio, video, returns text.1.05M66KFreeFree/M—124 tok/s5.21 s
gemini-3.6-flash-freeTakes text, vision, audio, video, returns text.1.05M64KFreeFree/M—124 tok/s5.21 s
gemini-2.5-flash-liteTakes text, vision, audio, video, returns text.1.05M66K$0.10$0.40/M$0.01/M75 tok/s3.20 s
gemini-2.5-flash-lite-nothinkTakes text, vision, audio, video, returns text.1.05M66K$0.10$0.40/M$0.01/M237 tok/s0.88 s
gemini-2.5-flash-lite-preview-09-2025Takes text, vision, audio, video, returns text.1.05M66K$0.10$0.40/M$0.01/M148 tok/s0.32 s
gemini-2.5-flash-lite-preview-09-2025-nothinkTakes text, vision, audio, video, returns text.1.05M66K$0.10$0.40/M$0.01/M205 tok/s0.76 s
gemini-2.5-flashTakes text, vision, audio, video, returns text.1.05M66K$0.30$2.50/M$0.03/M103 tok/s2.73 s
gemini-2.5-flash-preview-05-20-nothinkTakes text, vision, audio, video, returns text.1.05M66K$0.30$2.50/M$0.03/M55 tok/s0.69 s
gemini-2.5-flash-preview-05-20-searchTakes text, vision, audio, video, returns text.1.05M66K$0.30$2.50/M$0.03/M55 tok/s0.69 s
gemini-2.5-flash-preview-09-2025Takes text, vision, audio, video, returns text.1.05M66K$0.30$2.50/M$0.03/M144 tok/s0.36 s
gemini-2.5-flash-searchTakes text, vision, audio, video, returns text.1.05M66K$0.30$2.50/M$0.03/M55 tok/s0.69 s
gemini-3.5-flash-liteTakes text, vision, audio, video, returns text.1.05M66K$0.30$2.50/M$0.03/M76 tok/s1.26 s
gemini-3-flash-previewTakes text, vision, audio, returns text.1.05M—$0.50$3.00/M$0.05/M150 tok/s4.43 s
gemini-3-flash-preview-searchTakes text, vision, audio, returns text.1.05M—$0.50$3.00/M$0.05/M153 tok/s2.99 s
gemini-2.5-proTakes text, vision, audio, video, pdf, returns text.1.05M66K$1.25$10.00/M$0.13/M68 tok/s1.72 s
gemini-2.5-pro-preview-05-06Takes text, vision, audio, video, returns text.1.05M66K$1.25$10.00/M$0.13/M98 tok/s2.34 s
gemini-2.5-pro-preview-06-05Takes text, vision, audio, video, returns text.1.05M66K$1.25$10.00/M$0.13/M78 tok/s7.99 s
gemini-2.5-pro-searchTakes text, vision, audio, video, pdf, returns text.1.05M66K$1.25$10.00/M$0.13/M101 tok/s3.20 s
gemini-3.5-flashTakes text, vision, audio, video, returns text.1.05M64K$1.50$9.00/M$0.15/M111 tok/s5.97 s
gemini-3.6-flashTakes text, vision, audio, video, returns text.1.05M66K$1.50$7.50/M$0.15/M115 tok/s4.37 s
gemini-3.1-pro-previewTakes text, vision, audio, video, returns text.1.05M64K$2.00$12.00/M$0.20/M81 tok/s6.33 s
gemini-2.5-flash-nothinkTakes text, vision, audio, video, returns text.1.05M66K$0.30$2.50/M$0.03/M55 tok/s0.69 s
gemini-3.1-flash-liteTakes text, vision, audio, video, returns text.1M64K$0.25$1.50/M—130 tok/s0.83 s
gemini-3.1-flash-lite-nothinkTakes text, vision, audio, video, returns text.1M64K$0.25$1.50/M—97 tok/s0.59 s
gemini-3.1-pro-preview-customtoolsTakes text, vision, audio, video, returns text.1M64K$2.00$12.00/M$0.20/M98 tok/s11.49 s
gemma-4-26b-a4b-it-freeTakes text, vision, returns text.262K—FreeFree/M———
gemma-4-31b-it-freeTakes text, vision, returns text.262K—FreeFree/M———
deepinfra-gemma-4-26b-a4b-itTakes , returns text.262K131K$0.09$0.39/M$0.01/M43 tok/s0.43 s
gemma-4-26b-a4b-itTakes , returns text.262K131K$0.14$0.40/M—16 tok/s0.40 s
gemma-4-31b-itTakes , returns text.262K131K$0.14$0.40/M—43 tok/s0.43 s
gemini-3.1-flash-imageTakes text, vision, returns text, vision.131K—FreeFree/M—67 tok/s14.10 s
gemini-3-pro-imageTakes text, vision, returns text, vision.66K—FreeFree/M—51 tok/s36.13 s
gemini-3.1-flash-lite-imageTakes text, vision, returns text, vision.66K—FreeFree/M—60 tok/s1.47 s
gemini-2.5-flash-imageTakes text, vision, returns text, vision.33K8K$0.04$0.04/M—100 tok/s14.64 s
gemini-2.5-flash-image-previewTakes text, vision, returns vision.33K8K$0.04$0.04/M—1314 tok/s5.85 s
gemini-2.5-flash-preview-ttsTakes text, returns audio.——FreeFree/M———
gemini-2.5-pro-preview-ttsTakes text, returns audio.——FreeFree/M———
gemini-3-pro-image-previewTakes text, vision, returns text, vision.——FreeFree/M—101 tok/s2.40 s
gemini-3.1-flash-image-previewTakes text, vision, returns text, vision.——FreeFree/M—122 tok/s10.13 s
gemini-3.1-flash-image-preview-freeTakes text, vision, returns vision.——FreeFree/M—34 tok/s35.35 s
imagen-4.0Takes text, vision, returns vision.——FreeFree/M———
imagen-4.0-fast-generate-001Takes text, vision, returns vision.——FreeFree/M———
imagen-4.0-generate-001Takes text, vision, returns vision.——FreeFree/M———
imagen-4.0-ultraTakes text, vision, returns vision.——FreeFree/M———
imagen-4.0-ultra-generate-001Takes text, vision, returns vision.——FreeFree/M———
veo-2.0-generate-001Takes video, returns video.——FreeFree/M———
veo-3.0-generate-previewTakes text, vision, video, returns video.——FreeFree/M———
veo-3.1-fast-generate-previewTakes text, vision, video, returns video.——FreeFree/M———
veo-3.1-generate-previewTakes text, vision, video, returns video.——FreeFree/M———
gemini-embedding-exp-03-07Takes text. Output modality not published.——$0.02$0.02/M———
google/gemma-2-9b-it:free——$0.02$0.02/M———
text-embedding-004——$0.02$0.02/M———
gemma-7b-it——$0.10$0.10/M———
gemini-embedding-001Takes text. Output modality not published.——$0.15$0.15/M———
gemini-embedding-2Takes text, vision, audio, video. Output modality not published.——$0.20$0.60/M———
gemini-pro——$0.20$0.60/M———
gemma-3-12b-it——$0.20$0.20/M—37 tok/s0.89 s
gemma-3-1b-it——$0.20$0.20/M———
gemma-3-27b-it——$0.20$0.20/M—19 tok/s0.51 s
gemma-3-4b-it——$0.20$0.20/M—44 tok/s0.57 s
gemma-3n-e4b-it——$0.20$0.20/M———
google-gemma-3-12b-it——$0.20$0.20/M———
google-gemma-3-27b-it——$0.20$0.20/M———
google-gemma-3-4b-it——$0.20$0.20/M———
unsloth/gemma-3-12b-it——$0.20$0.80/M———
unsloth/gemma-3-27b-it——$0.22$0.22/M———
google/gemma-2-27b-it——$0.80$0.80/M———
gemini-pro-vision——$1.00$1.00/M———
gemini-2.5-pro-exp-03-25Takes text, vision, audio, video, returns text.——$1.25$5.00/M$0.13/M122 tok/s8.30 s
gemini-2.5-pro-preview-03-25Takes text, vision, returns text.——$1.25$10.00/M$0.13/M98 tok/s2.34 s
gemini-2.5-pro-preview-03-25-searchTakes text, vision, audio, video, returns text.——$1.25$10.00/M$0.13/M98 tok/s2.34 s
gemini-2.5-pro-preview-05-06-searchTakes text, vision, audio, video, returns text.——$1.25$10.00/M$0.13/M98 tok/s2.34 s
gemini-2.5-pro-preview-06-05-searchTakes text, vision, audio, video, returns text.——$1.25$10.00/M$0.13/M78 tok/s7.99 s
gemini-exp-1114——$1.25$5.00/M———
gemini-exp-1121——$1.25$5.00/M———
gemini-exp-1206——$1.25$5.00/M———
google/gemini-exp-1114——$1.25$5.00/M———
learnlm-1.5-pro-experimental——$1.25$5.00/M———
gemini-3.1-pro-preview-searchTakes text, vision, audio, video, returns text.——$2.00$12.00/M$0.20/M95 tok/s7.91 s
veo-3.1-lite-generate-previewTakes text, vision, video, returns video.——$720.00$720.00/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

deepinfra-gemma-4-26b-a4b-it vs gemini-2.5-flashdeepinfra-gemma-4-26b-a4b-it vs gemini-2.5-flash-imagedeepinfra-gemma-4-26b-a4b-it vs gemini-2.5-flash-litedeepinfra-gemma-4-26b-a4b-it vs qwen3.8-max-previewdeepinfra-gemma-4-26b-a4b-it vs kimi-k3

Google on AIHubMix

Which Google model should I start with?

gemini-3-flash-preview-free is free on input — the cheapest entry here that declares tool calling, and it carries a 1.05M context. Move up to veo-3.1-lite-generate-preview when answer quality matters more than cost, or to gemini-3.5-flash-lite-free for long-form reasoning.

Which of these models reason before answering?

28 of the 81 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-), some are the open-weight repository form (google/…), 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 gemini-2.5-flash bills cache hits at 10% of the input rate and gemini-2.5-flash-lite 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 Google 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 modelsOpenAI
132 modelsZ.AI
64 modelsLlama
52 modelsByteDance
46 models

Start calling Google 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