Google Models

97 modelsGeneral models free to startUp to 1.05M context

Usage

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

Tokens

185K

Requests

144

Models in use

10 of 97

Tokens per day, stacked by model

060.6K121K08-1709-0209-102026-08-17 — 0 tokens2026-08-18 — 450 tokens gemini-3.5-flash: 4502026-08-20 — 0 tokens2026-08-26 — 121,165 tokens gemini-3.5-flash: 121,1652026-08-27 — 16,885 tokens gemini-3-pro-image-preview: 9,815 gemini-3.5-flash: 6,885 gemini-2.5-flash: 1852026-08-31 — 2,155 tokens gemini-3.5-flash: 2,1552026-09-01 — 50 tokens gemini-2.5-flash: 502026-09-02 — 2,350 tokens gemini-3.5-flash: 2,3502026-09-03 — 0 tokens2026-09-04 — 0 tokens2026-09-05 — 0 tokens2026-09-06 — 0 tokens2026-09-07 — 820 tokens gemini-3.5-flash: 8202026-09-08 — 19,910 tokens gemini-3.5-flash: 18,395 gemini-2.5-flash: 1,5152026-09-10 — 695 tokens gemini-3.8-flash: 6952026-09-11 — 21,005 tokens gemini-2.5-flash-image: 19,870 gemini-3.8-flash: 1,1352026-09-14 — 0 tokens
  • gemini-3.5-flash
  • gemini-2.5-flash-image
  • gemini-3-pro-image-preview
  • gemini-3.8-flash
  • gemini-2.5-flash

Which models that traffic went to

  1. Gemini 3.5 Flash82.1%152K
  2. Gemini 2.5 Flash Image10.7%19.9K
  3. Gemini 3 Pro Image Preview5.3%9.8K
  4. Gemini 3.8 Flash1.0%1.8K
  5. Gemini 2.5 Flash0.9%1.8K

Share of 185K tokens. 5 models with traffic report no token counts and cannot be ranked here, including veo-3.1-fast-generate-preview and veo-3.1-lite-generate-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 17 days, counting the 97 model IDs listed on this page; traffic routed through upstream-specific IDs that are not in the public catalog is not included.

All 97 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-2.0-flash-preview-image-generationTakes text, vision, returns text, vision.1.05M—FreeFree/M———
gemini-2.0-flash-expTakes text, vision, audio, video, returns text, vision.1.05M—$0.02$0.08/M———
gemini-2.0-flash-liteTakes text, vision, audio, video, returns text.1.05M—$0.076$0.304/M———
gemini-2.0-flash-thinking-exp-01-21Takes text, vision, audio, video, returns text.1.05M—$0.076$0.304/M———
gemini-2.5-pro-exp-03-25Takes text, vision, audio, video, returns text.1.05M—$1.25$5/M$0.31/M——
gemini-2.5-pro-preview-03-25Takes text, vision, returns text.1.05M—$1.25$10/M$0.31/M98 tok/s2.34 s
gemini-2.5-pro-preview-03-25-searchTakes text, vision, audio, video, returns text.1.05M—$1.25$10/M$0.31/M——
gemini-2.5-pro-preview-05-06-searchTakes text, vision, audio, video, returns text.1.05M—$1.25$10/M$0.31/M——
gemini-2.5-pro-preview-06-05Takes text, vision, audio, video, returns text.1.05M—$1.25$10/M$0.31/M78 tok/s7.99 s
gemini-2.5-pro-preview-06-05-searchTakes text, vision, audio, video, returns text.1.05M—$1.25$10/M$0.31/M——
gemini-3.8-flash-freeTakes text, vision, audio, video, PDF. Output modality not published.1.05M66KFreeFree/M———
gemini-2.5-flash-liteTakes text, vision, audio, video, PDF, returns text.1.05M66K$0.1$0.4/M$0.025/M112 tok/s0.43 s
gemini-2.5-flash-lite-preview-09-2025Takes text, vision, audio, video, PDF, returns text.1.05M66K$0.1$0.4/M$0.025/M148 tok/s0.32 s
gemini-2.5-flashTakes text, vision, audio, video, PDF, returns text.1.05M66K$0.3$2.499/M$0.075/M111 tok/s0.41 s
gemini-2.5-flash-nothinkTakes text, vision, audio, video, PDF, returns text.1.05M66K$0.3$2.499/M$0.075/M55 tok/s0.69 s
gemini-2.5-flash-preview-05-20-nothinkTakes text, vision, audio, video, returns text.1.05M66K$0.3$2.499/M$0.075/M55 tok/s0.69 s
gemini-2.5-flash-preview-05-20-searchTakes text, vision, audio, video, returns text.1.05M66K$0.3$2.499/M$0.075/M55 tok/s0.69 s
gemini-2.5-flash-preview-09-2025Takes text, vision, audio, video, returns text.1.05M66K$0.3$2.499/M$0.075/M144 tok/s0.36 s
gemini-2.5-flash-searchTakes text, vision, audio, video, PDF, returns text.1.05M66K$0.3$2.499/M$0.075/M55 tok/s0.69 s
gemini-3-flash-previewTakes text, vision, audio, video, PDF. Output modality not published.1.05M66K$0.5$3/M$0.05/M——
gemini-3-flash-preview-freeTakes text, vision, audio, video, PDF. Output modality not published.1.05M66K$0.5$3/M$0.05/M——
gemini-2.5-proTakes text, vision, audio, video, PDF, returns text.1.05M66K$1.25$10/M$0.31/M101 tok/s2.40 s
gemini-2.5-pro-preview-05-06Takes text, vision, audio, video, PDF, returns text.1.05M66K$1.25$10/M$0.31/M——
gemini-2.5-pro-searchTakes text, vision, audio, video, PDF, returns text.1.05M66K$1.25$10/M$0.31/M101 tok/s3.20 s
gemini-3.5-flashTakes text, vision, audio, video, PDF, returns text.1.05M66K$1.5$9/M—111 tok/s0.41 s
gemini-3.1-pro-previewTakes text, vision, audio, video, PDF. Output modality not published.1.05M66K$2$12/M$0.2/M——
gemini-3.1-pro-preview-customtoolsTakes text, vision, audio, video, PDF. Output modality not published.1.05M66K$2$12/M$0.2/M——
gemini-3.8-flashTakes text, vision, audio, video, PDF. Output modality not published.1.05M66K$2$12/M$0.2/M——
gemini-2.0-flashTakes text, vision, audio, video, returns text.1M—$0.1$0.4/M$0.25/M140 tok/s0.62 s
gemma-4-26b-a4b-it-freeTakes text, vision, video, returns text.262K—FreeFree/M———
gemma-4-31b-it-freeTakes text, vision, video, returns text.262K—FreeFree/M———
gemini-3.1-flash-imageTakes text, vision, video, PDF, returns vision.131K33KFreeFree/M———
gemini-3-pro-imageTakes text, vision. Output modality not published.66K33KFreeFree/M———
gemini-2.5-flash-imageTakes text, vision, returns vision.66K33K$0.04$0.04/M—1314 tok/s5.85 s
gemini-3.1-flash-lite-imageTakes text, vision, returns vision.66K4K$0.04$0.04/M—1314 tok/s5.85 s
gemini-2.5-flash-image-previewTakes text, vision, returns vision.33K—$0.04$0.04/M—1314 tok/s5.85 s
gemini-3.1-flash-image-previewTakes text, vision, returns vision.33K—$0.04$0.04/M—1314 tok/s5.85 s
imagen-3.0-generate-002Takes text, vision, returns vision.——FreeFree/M———
imagen-4.0Takes text, vision, returns vision.——FreeFree/M———
imagen-4.0-fast-generate-001Takes text, vision, returns vision.——FreeFree/M———
imagen-4.0-fast-generate-preview-06-06Takes text, vision, returns vision.——FreeFree/M———
imagen-4.0-generate-001Takes text, vision, returns vision.——FreeFree/M———
imagen-4.0-generate-preview-05-20Takes 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———
imagen-4.0-ultra-generate-exp-05-20Takes text, vision, returns vision.——FreeFree/M———
veo-2.0-generate-001Takes video, returns video.——FreeFree/M———
veo-3Takes text, vision, audio, video, returns video.——FreeFree/M———
veo-3.0-generate-previewTakes text, vision, video, returns video.——FreeFree/M———
veo3Takes text, vision, audio, video, returns video.——FreeFree/M———
veo3.1Takes , 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———
gemini-2.0-flash-lite-preview-02-05——$0.075$0.3/M———
gemini-2.0-flash-lite-001——$0.076$0.304/M———
gemini-2.0-flash-thinking-exp——$0.076$0.304/M———
gemini-2.0-flash-thinking-exp-1219——$0.076$0.304/M———
aistudio_gemini-2.0-flash——$0.1$0.4/M$0.25/M——
gemini-2.0-flash-001——$0.1$0.4/M$0.25/M——
gemini-2.0-flash-exp-image-generation——$0.1$0.4/M———
gemini-2.0-flash-exp-searchTakes text, vision, returns text.——$0.1$0.4/M———
gemini-2.0-flash-free——$0.1$0.4/M$0.025/M——
gemini-2.0-flash-searchTakes text, vision, audio, video, returns text.——$0.1$0.4/M$0.25/M——
gemini-2.5-flash-lite-previewTakes text, vision, audio, video, returns text.——$0.1$0.4/M$0.025/M——
gemma-7b-it——$0.1$0.1/M———
gemini-embedding-001Takes text. Output modality not published.——$0.15$0.15/M———
gemini-embedding-2-previewTakes text. Output modality not published.——$0.2$0.6/M———
gemini-pro——$0.2$0.6/M———
gemma-3-12b-it——$0.2$0.2/M———
gemma-3-1b-it——$0.2$0.2/M———
gemma-3-27b-it——$0.2$0.2/M———
gemma-3-4b-it——$0.2$0.2/M———
gemma-3n-e4b-it——$0.2$0.2/M———
google/gemma-3-27b-it——$0.2$0.2/M———
unsloth/gemma-3-12b-it——$0.2$0.8/M———
unsloth/gemma-3-27b-it——$0.22$0.22/M———
gemma2-9b-it——$0.4$0.4/M———
gemini-2.5-flash-preview-tts——$0.5$0.5/M———
google/gemma-2-27b-it——$0.8$0.8/M———
gemini-2.5-pro-preview-ttsTakes , returns audio.——$1$1/M———
gemini-pro-vision——$1$1/M———
gemini-2.0-pro-exp-02-05Takes text, vision, audio, video, returns text, vision.——$1.25$5/M———
gemini-2.0-pro-exp-02-05-searchTakes text, vision, audio, video. Output modality not published.——$1.25$5/M———
gemini-exp-1114——$1.25$5/M———
gemini-exp-1121——$1.25$5/M———
gemini-exp-1206——$1.25$5/M———
google/gemini-exp-1114——$1.25$5/M———
learnlm-1.5-pro-experimental——$1.25$5/M———
antigravity-preview-05-2026——$2$12/M$0.2/M——
deep-research-max-preview-04-2026——$2$12/M$0.2/M——
deep-research-preview-04-2026——$2$12/M$0.2/M——
gemini-3-pro-image-preview——$2$12/M———
gemini-3-pro-preview——$2$12/M$0.5/M101 tok/s2.40 s
veo-3.1-fast-generate-previewTakes text, vision, video. Output modality not published.——$2$2/M———
veo-3.1-lite-generate-previewTakes text, vision. Output modality not published.——$2$2/M———
gemini-3-flash-preview-pro——$50$150/M$5/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

gemini-2.0-flash vs gemini-2.0-flash-expgemini-2.0-flash vs gemini-2.0-flash-exp-searchgemini-2.0-flash vs gemini-2.0-flash-litegemini-2.0-flash vs gpt-5.6-lunadeepseek-v4-flash vs gemini-2.0-flash

Google on AIHubMix

Which Google model should I start with?

gemma-4-26b-a4b-it-free is free on input — the cheapest entry here that declares tool calling, and it carries a 262K context. Move up to gemini-3-flash-preview-pro when answer quality matters more than cost, or to gemini-2.0-flash-thinking-exp-01-21 for long-form reasoning.

Which of these models reason before answering?

11 of the 97 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 antigravity-preview-05-2026 bills cache hits at 25% of the input rate and deep-research-max-preview-04-2026 bills cache hits at 25% 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 Model Authors

See all model authors →
OpenAI
145 modelsQwen
118 modelsLlama
42 modelsChatGLM
40 modelsDeepSeek
33 models

Start calling Google 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