Google: Gemini 3.1 Pro (Preview Low)Official docs

Google: Gemini 3.1 Pro (Preview Low)

byGoogle
Official docs

Gemini 3.1 Pro (Preview Low) is a reasoning model from Google released on Feb 19, 2026. It reads text, images, files and audio and writes text, with a 1.05M token context window and up to 66K tokens per reply.

Show more

It costs $2 per million input tokens and $12 per million output tokens. Cached input bills at $0.20, 90% less than fresh input.

It supports tool calling, structured JSON output and prompt caching.

Modalities
In / out price
$2 / $12 per 1M
Context
1.05M
Max output
66K
Released
Feb 19, 2026
Knowledge cutoff
Jan 2025
  • Tool calling
  • Structured output
  • Reasoning
  • Prompt caching
  • Open weights
  • Free to use

Gemini 3.1 Pro (Preview Low) pricing

USD, as listed on Nov 18, 2026. Most bills are input heavy, so the cached input rate matters as much as the headline price.

Input$2 / 1M tokens
Output$12 / 1M tokens
Cached input (read)$0.20 / 1M tokens
Cache write$0.375 / 1M tokens

What Gemini 3.1 Pro (Preview Low) costs per month

Pick a workload close to yours or type your own volumes.

Gemini 3.1 Pro (Preview Low) per month
$195
Without caching
$276
Per request
$0.0065

Supported request parameters

What you can set when you call Gemini 3.1 Pro (Preview Low) through an OpenAI compatible API.

  • Toolstools
  • Structured outputsstructured_outputs
  • Reasoningreasoning
  • Temperaturetemperature

Alternatives to Gemini 3.1 Pro (Preview Low)

Models that take the same inputs and call tools, closest in price, cheaper ones first.

  • Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 24 providers.

    by googleJun 17, 2025$1.25/M input tokens$10/M output tokens24 providers

  • Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 33 providers.

    by googleFeb 19, 2026$2/M input tokens$12/M output tokens33 providers

  • Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 9 providers.

    by googleFeb 19, 2026$2/M input tokens$12/M output tokens9 providers

  • Reads text, images, files, audio and video. Tool calling, structured output, reasoning.

    by googleFeb 19, 2026$2/M input tokens$12/M output tokens

  • Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 5 providers.

    by googleFeb 19, 2026$2/M input tokens$12/M output tokens5 providers

  • Reads text, images, files, audio and video. Tool calling, structured output, reasoning.

    by vivgridFeb 19, 2026$2/M input tokens$12/M output tokens

More from Google

  • Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 15 providers.

    by googleNov 12, 2026$1.50/M input tokens$7.50/M output tokens15 providers

  • Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 16 providers.

    by googleNov 10, 2026$2/M input tokens$10/M output tokens16 providers

  • Generates video from text, images, files and video. Served by 2 providers.

    by googleNov 5, 2026$1.50/M input tokens$9/M output tokens2 providers

  • Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 30 providers.

    by googleOct 13, 2026$2/M input tokens$10/M output tokens30 providers

  • Generates images from text, images and files. Served by 4 providers.

    by googleOct 6, 2026$1.50/M input tokens$7.50/M output tokens4 providers

  • Turns text into spoken audio. Served by 2 providers.

    by googleSep 22, 2026$0.50/M input tokens$6/M output tokens2 providers

All Google models

Gemini 3.1 Pro (Preview Low) questions

How much does the Gemini 3.1 Pro (Preview Low) API cost?

$2 per million input tokens and $12 per million output tokens, with cached input at $0.20. The estimator on this page turns that into a monthly bill for your own workload.

What is the context window of Gemini 3.1 Pro (Preview Low)?

1,048,576 tokens of input, and it can write up to 65,536 tokens in one reply. As a rough guide, a million tokens is around 750,000 English words.

Does Gemini 3.1 Pro (Preview Low) support tool calling?

Yes. It accepts tool definitions and can return JSON that matches a schema, which is what an agent needs to call your APIs.

Is Gemini 3.1 Pro (Preview Low) open source?

No. Google serves it through an API only, so you cannot download the weights or host it yourself.

When was Gemini 3.1 Pro (Preview Low) released?

Feb 19, 2026, with training data up to Jan 2025.

Catalog data from models.dev (MIT licensed), refreshed daily, last on Nov 18, 2026. The summary is written from these facts.