Gemini 3.1 Pro Preview
Improved SWE and agentic capabilities, improved token efficiency and thinking, and expanded thinking levels.
text + image + file → text · made by Google
Available within a subscription 1 plan
Bought by the month. What a plan allows is the half of its price that a rate card cannot carry, so it is printed beside every one.
Sold by 34 ways
| Seller | Lane | Rate |
|---|---|---|
| Google 0 ways | $1per Mtok in$6per Mtok out$0.2per Mtok cached | |
| Google apinot on the seller's list today | batch | $1per Mtok in$6per Mtok out$0.2per Mtok cachedai.google.dev · read 2026-08-24 |
| Google Vertex AI cloud | batch | $1per Mtok in$6per Mtok outraw.githubusercontent.com · read 2026-10-31 |
| Google Vertex AI cloud | flex | $1per Mtok in$6per Mtok outraw.githubusercontent.com · read 2026-10-31 |
| Databricks cloud | standard | $2per Mtok in$12per Mtok out$0.2per Mtok cached$2.5per Mtok cache writemodels.dev · read 2026-10-31 |
| Google 0 ways | $2per Mtok in$12per Mtok out$0.2per Mtok cached | |
| Google apinot on the seller's list today | standard | $2per Mtok in$12per Mtok out$0.2per Mtok cachedai.google.dev · read 2026-08-24 |
| Google Vertex AI cloud | standard | $2per Mtok in$12per Mtok out$0.00012per image$0.2per Mtok cachedmodels.dev · read 2026-10-31 |
| Writer api | standard | $2per Mtok in$12per Mtok outdev.writer.com · read 2026-08-25 |
| Google Vertex AI cloud | priority | $3.6per Mtok in$21.6per Mtok out$0.36per Mtok cachedraw.githubusercontent.com · read 2026-10-31 |
| Google Vertex AI cloud | long-context | $4per Mtok in$18per Mtok out$0.4per Mtok cachedraw.githubusercontent.com · read 2026-10-31 |
| Databricks cloud | priority | $4.5per Mtok in$27per Mtok out$0.45per Mtok cachedraw.githubusercontent.com · read 2026-10-31 |
| Databricks cloud | long-context | $5per Mtok in$22.5per Mtok out$0.5per Mtok cachedraw.githubusercontent.com · read 2026-10-31 |
| Requesty 2 ways | $0.9per Mtok in$5.4per Mtok out$0.18per Mtok cached | |
| Requesty aggregatornot on the seller's list today | google flex | $0.9per Mtok in$5.4per Mtok out$0.18per Mtok cachedrouter.requesty.ai · read 2026-08-25 |
| Requesty aggregatornot on the seller's list today | vertex flex | $0.9per Mtok in$5.4per Mtok out$0.09per Mtok cachedrouter.requesty.ai · read 2026-08-25 |
| Requesty aggregator | $2per Mtok in$12per Mtok out$0.2per Mtok cachedrouter.requesty.ai · read 2026-10-09 | |
| Requesty aggregator | vertex | $2per Mtok in$12per Mtok out$0.2per Mtok cachedrouter.requesty.ai · read 2026-10-09 |
| Nous Research 2 ways | $2per Mtok in$12per Mtok out$0.000002per image$0.2per Mtok cached$0.38per Mtok cache write | |
| Nous Research aggregator | batch | $1per Mtok in$6per Mtok out$0.000001per imageinference-api.nousresearch.com · read 2026-09-12 |
| Nous Research aggregator | standard | $2per Mtok in$12per Mtok out$0.000002per image$0.2per Mtok cached$0.38per Mtok cache writeinference-api.nousresearch.com · read 2026-09-12 |
| OpenRouter 8 ways | $2per Mtok in$12per Mtok out$0.000002per image$0.2per Mtok cached$0.38per Mtok cache write | |
| OpenRouter aggregator | batch | $1per Mtok in$6per Mtok out$0.000001per imageopenrouter.ai · read 2026-08-24 |
| OpenRouter aggregator | google-ai-studio/flex | $1per Mtok in$6per Mtok out$0.1per Mtok cached$0.19per Mtok cache writeopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | google-vertex/global/flex | $1per Mtok in$6per Mtok out$0.1per Mtok cached$0.19per Mtok cache writeopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | standard | $2per Mtok in$12per Mtok out$0.000002per image$0.2per Mtok cached$0.38per Mtok cache writeopenrouter.ai · read 2026-08-24 |
| OpenRouter aggregator | google-ai-studio | $2per Mtok in$12per Mtok out$0.2per Mtok cached$0.38per Mtok cache writeopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | google-vertex/global | $2per Mtok in$12per Mtok out$0.2per Mtok cached$0.38per Mtok cache writeopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | google-ai-studio/priority | $3.6per Mtok in$21.6per Mtok out$0.36per Mtok cached$0.68per Mtok cache writeopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | google-vertex/global/priority | $3.6per Mtok in$21.6per Mtok out$0.36per Mtok cached$0.68per Mtok cache writeopenrouter.ai · read 2026-08-25 |
| AtlasCloud aggregator | standard | $2per Mtok in$12per Mtok out$0.2per Mtok cachedapi.atlascloud.ai · read 2026-09-20 |
| DeepInfra aggregator | standard | $2per Mtok in$12per Mtok outapi.deepinfra.com · read 2026-08-25 |
| GitHub Copilot 0 ways | $2per Mtok in$12per Mtok out$0.2per Mtok cached | |
| GitHub Copilot aggregatornot on the seller's list today | standard | $2per Mtok in$12per Mtok out$0.2per Mtok cachedmodels.dev · read 2026-09-04 |
| Inference.net aggregator | standard | $2per Mtok in$12per Mtok out$0.2per Mtok cachedapi.inference.net · read 2026-10-31 |
| Vercel AI Gateway aggregator | standard | $2per Mtok in$12per Mtok out$0.2per Mtok cachedvercel.com · read 2026-08-25 |
| Vercel AI Gateway aggregatornot on the seller's list today | sandbox | $2per Mtok in$12per Mtok outvercel.com · read 2026-08-25 |
| Venice AI aggregator | standard | $2.5per Mtok in$15per Mtok out$0.5per Mtok cached$0.5per Mtok cache writemodels.dev · read 2026-10-31 |
| ElectronHub aggregator | standard | $3per Mtok in$15per Mtok outapi.electronhub.ai · read 2026-10-31 |
| RedPill aggregator | standard | $4per Mtok in$18per Mtok outapi.redpill.ai · read 2026-09-20 |
Measured 79 standings
About
Gemini 3.1 Pro Preview — a text model from Google, sold by 13 companies from $2 in and $12 out per million tokens, placed 3rd of 102 on Simplebench — Epoch AI.
It takes text, images and files and returns text, with a context window of 1,048,576 tokens. It was published in February 2026, trained on material up to January 2025. Its sellers say it can reason step by step and call a tool. The catalogue files it under reasoning, code and agents. Thirteen companies sell it. The cheapest is $2 in and $12 out per million tokens at AtlasCloud. Beside the standard rate there are separately routed, faster, batch, flex and regional lanes. It has been measured on 79 boards, and stands best at 3rd of 102 on Simplebench — Epoch AI.
Every current figure
- Maker
- Register
- model
- Takes
- text + image + file
- Returns
- text
- Context
- 1,048,576 tokens
- Longest answer
- 65,536 tokens
- Published
- February 2026
- Knowledge to
- January 2025
- Licence
- not read
- Sellers
- 13
- Price
- $2 in and $12 out per million tokens — AtlasCloud
- Boards
- 79
- Best place
- 3rd of 102 — Simplebench — Epoch AI
Known as 18 names
Gemini 3.1 Pro (Preview)gemini-3.1-pro-previewGemini 3.1 Pro Preview (high)gemini-3.1-pro-preview_highgemini-3.1-pro-groundingGemini-3.1-ProOpenAPA w/ gemini-3.1-progemini-3.1-pro (thinking)gemini-3.1-pro (thinking)*Gemini 3.1 Progoogle/gemini-3.1-pro-previewgoogle/gemini-3.1-progoogle/gemini-3.1-pro-preview:batchgoogle/gemini-3.1-pro-preview:flexvertex/gemini-3.1-pro-previewvertex/gemini-3.1-pro-preview:flexgoogle/gemini-3.1-pro-preview-batchGoogle: Gemini 3.1 Pro Preview (batch)