Gemini 3.5 Flash
4076°
Run this model
Offers / Ads
Google | 1,048,576 token context | $1.50/M input, $9.00/M output. Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution loops, supporting text, image, video, audio, and PDF inputs. Defaults to medium thinking effort for faster and more cost-efficient responses, with full support for thinking levels (minimal, low, medium, high) for fine-grained cost/performance trade-offs.
Guides for this model
How to choose an AI model in October 2026: the closed source news, then the open weights worth downloading
Open weights vs open source vs API-only: what you are actually allowed to do
The 10 cheapest ChatGPT alternatives in 2026: free local models, free tiers and flat-rate plans
Captain's notes
Notes from 2026-10-13
Gemini 3.5 Flash is Google's mid-tier multimodal model, built for speed and cost efficiency without giving up much ground on coding and reasoning. It accepts text, image, video, audio, and PDF inputs, and its adjustable thinking levels let you dial cost against quality per request. It suits developers running agentic pipelines who need capable throughput without Pro-tier bills.
Known for
- Coding performance that punches above its price tier
- Parallel agentic loop execution as a first-class design goal
- Adjustable thinking effort: minimal through high, per request
- Full multimodal input: images, video, audio, and PDFs
- One million token context window
Watch out for
- Closed weights only — no local deployment, no self-hosting
- Output tokens cost six times the input rate; agentic loops with long outputs add up fast
- Thinking level defaults to medium; switching it off entirely may not be possible
Prompts to try
Debug a parallel agent loop
I have a Python orchestrator that spawns five async agents, each calling an external API and writing results to a shared dict. Occasionally two agents overwrite each other's keys silently. Identify the race condition, explain why it happens in asyncio, and rewrite the relevant section using a lock or queue to fix it.
Reason through a build plan
I need to migrate a monolithic Flask app to a microservices architecture over twelve weeks with a two-person team. One service handles auth, one handles billing, one handles the core product API. List the sequencing risks, the order you would split services, and the one thing most teams get wrong at week six.
Extract data from a PDF table
I'm attaching a PDF invoice with a multi-page line-item table. Extract every row as JSON with keys: description, quantity, unit_price, total. Flag any row where quantity multiplied by unit_price does not equal the total column, and show the discrepancy.
Compare with
- Gemma 4 31BOpen-weights model262,144 token context · $0.20/M input, $0.40/M output
- Gemma 4 26B A4BOpen-weights model262,144 token context · $0.09/M input, $0.30/M output
- gemma 4 31B it UltraOpen-weights model131,072 token context · $0.27/M input, $0.76/M output
- Gemini 3.8 FlashAPI-only model1,048,576 token context · $0.83/M input, $4.12/M output
More text models from google
Questions people ask
- Can I run Gemini 3.5 Flash locally?
- No. Google has not released weights for this model, so it is API access only.
- What does Gemini 3.5 Flash cost and how large is its context?
- Input is $1.50 per million tokens and output is $9.00 per million tokens, with a context window of 1,048,576 tokens.
- How does Gemini 3.5 Flash differ from Gemini Pro?
- Flash is optimised for speed and lower cost; Google positions it as near-Pro on coding and reasoning but at Flash-tier pricing, with the trade-off that you control quality via thinking levels rather than getting maximum effort by default.
Captain's verdictA sensible default for agentic coding work where you want a million-token context and multimodal input without paying Pro prices — just watch the output bill.
Captain writes these notes from the model's own description and model card. Prices and context sizes are the provider's at the time of writing and can change.
Ranking badge
Updated Oct 22, 2026
Made this model? Show this badge on your page.
Paste it into your Hugging Face card or Civitai description.
How this score adds up
This model has no popularity data from any source yet, so it carries a stand-in number below 7,000° that keeps the lists complete. It never ranks above a model with data. The breakdown appears here as soon as a source reports it.
Glossary: the terms used here
- Heat score
- One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
- Floor
- The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
- Download-equivalents
- Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
- Log scale
- Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
- Likes
- Thumbs up and likes from every source, worth half a download each on the log scale.
- Adoption rate
- How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
- Measured and estimated
- Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
- Seeder
- Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
- AI Horde
- A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
- Generation sites
- Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
- OpenRouter tokens
- A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
- Full model (checkpoint)
- The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
- LoRA and embedding
- Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
- Family and weights
- The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
- Age
- Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
- Family boost
- A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
- Stand-in score
- A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
- New! (grace period)
- A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
- Trend
- How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
- Typical model
- The middle of the catalog: half the models with a figure grew faster over the period, half slower.
Gemini 3.5 Flash is a text model for the Text / LLM family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Text / LLM models and check its heat score to see how it is trending.
Browse by Model Family
Text / LLM Models
434
Anima Models
528
Chroma Models
19
Fibo Models
2
Flux Models
1,496
Flux 2 / Klein Models
1,239
Flux 3 Models
3
Moss Models
3
Iris Models
1
MiniMax H3 Models
364
Hunyuan Models
204
Ideogram Models
20
Krea2 Models
717
Qwen Models
20
Qwen2 Models
47
Ltx2 Models
153