Gemini 3.1 Pro Preview Custom Tools
Google · released Feb 25, 2026
- Type
- Proprietary
- Input
- $2.00
- Output
- $12.00
- Cached
- Not published
List price · per 1M tokens · Google AI at 1M context · source ↗ · a reseller below undercuts it; the table carries the spread
Our take
Written Aug 2, 2026Gemini 3.1 Pro Preview Custom Tools is Google's flagship multimodal model with a one-million-token request limit and built-in tool support. It handles text, images, audio, video and files, and scores strongly on live coding leaderboards, though its agentic capability measurement is near zero.
Choose this for long-context multimodal workflows or coding tasks where live leaderboard scores matter. Use Vertex for budget-sensitive production, or Google AI Studio for faster prototyping. Skip it if you need reliable autonomous agent behaviour, or if you cannot tolerate the fourfold speed gap between tiers.
The case for it
- One-million-token request limit, among the largest disclosed in our data.
- Strong measured coding performance: Arena Coding Elo 1521.3 and Arena Code (WebDev) Elo 1446.8 on the latest leaderboard.
- Broad native input coverage across text, images, files, audio and video.
- Base-tier pricing is several times cheaper than the premium tier for the same model.
The case against it
- Agentic capability score is near zero on the only measurement we hold: Arena Agent (IPS) at -0.0052, where higher is better.
- Throughput varies dramatically by provider and tier, from under thirty to over one hundred thirty tokens per second.
- Premium tiers cost several times the base rate, eroding the price advantage for the same model.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)6th of 143 · 1485.4
CodingWriting and fixing code on its own
Arena Coding13th of 143 · 1520.8
AgenticPlanning, calling tools, staying on task
Arena Agent (IPS)19th of 36 · −0.005
Arena Agent (IPS) is the only board that has scored it for this.
WritingWe do not rate this
Two boards come close and neither tests writing: Arena Creative Writing asks people which of two replies they prefer, and LiveBench Language tests whether a model understood a passage. So we show where Gemini 3.1 Pro Preview Custom Tools placed and give it no mark out of five.
These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done, which is why they get no rating.
Every published score for this model8 scoresEvery figure we hold, from 8 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Or rent it from someone else
Why this differs from the header. The strip above quotes Google AI's own list price. This is the cheapest live offer at the widest standard context we hold, whoever is serving it — a reseller undercutting a lab is ordinary commerce, not an error.
- per 1M tokens
- $2.00 in / $12.00 out
- Context served
- 1M
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| Google Vertex AIglobal | $1.00 / $6.00 | 1M | 19 tok/s | No | No | Confirmed |
| Google AI Studioflex tier | $1.00 / $6.00 | 1M | 110 tok/s | No | Yes55 days | Unknown |
| OpenRouter | $2.00 / $12.00 | 1M | not measured | Unknown | Unknown | Unknown |
| Google AI | $2.00 / $12.00 | 1M66K out | not measured | Unknown | Unknown | Unknown |
| Google AI Studio | $2.00 / $12.00 | 1M | 78 tok/s | No | Yes55 days | Unknown |
| Google AI Studiopriority tier | $3.60 / $21.60 | 1M | 56 tok/s | No | Yes55 days | Unknown |
Google Vertex AI
Google AI StudioAcross the 6 listings we hold: 4 say they do not train on prompts, 0 say they do and 2 do not say. 1 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| Google Vertex AIglobal | ✓ | ✓ | ✓ |
| Google AI Studioflex | ✓ | ✓ | ✓ |
| OpenRouter | ✓ | ✓ | ✓ |
| Google AI | |||
| Google AI Studio | ✓ | ✓ | ✓ |
| Google AI Studiopriority | ✓ | ✓ | ✓ |
Tool calling: 5 of 6 listings say yes, 1 publishes no parameter list. JSON output: 5 of 6 listings say yes, 1 publishes no parameter list. Strict schema: 5 of 6 listings say yes, 1 publishes no parameter list.
When we formed this view
Dates behind this page
Prices last checked 9d ago
What we do not know about this model yet
- 1 of 6 listings publish no parameter list, so what their API accepts is unknown to us.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 2 of 6 listings do not say whether they train on prompts.
Licence and identifiers
What the licence allowsWe hold no licence record for this model. Inside are the identifiers you need to pull it — its Hugging Face repo where we have one, our slug and a machine-readable card.
Licence
Commercial API terms. We hold no licence record for this model, so there is nothing to summarise here.
Identifiers
- Modality record
- text+image+file+audio+video->text
- Catalogue slug
- google-gemini-3-1-pro-preview-custom-tools