Gemini 3.1 Pro Preview Custom Tools
Google · released Feb 25, 2026
- Type
- Closed
- Input
- $2.00
- Output
- $12.00
- Cached
- None held
List price · per 1M tokens · Google AI at 1M context · machine-readable source ↗
Our take
Written Sep 4, 2026Gemini 3.1 Pro Preview Custom Tools is Google's proprietary multimodal model built for long documents, code and tool-calling workflows. It handles up to one million tokens in a single request across text, images, audio and video, with measured coding strength and a tool-use score that is its only bright spot in agent tests.
Choose this for coding workloads where its measured coding score is the relevant signal, or for long-context multimodal tasks needing one million tokens of working memory. Use it inside Google Vertex or AI Studio for the steepest price cut versus the same model on other platforms. Skip it if you need strong general agent performance, consistent speed across providers, or the ability to run offline.
The case for it
- One-million-token request limit, the largest context we hold for this model, for document and video analysis.
- Arena Coding score of 1521.2, indicating strong measured programming performance.
- Half the price on Google Vertex and AI Studio versus the same model on OpenRouter and direct Google.
- Positive tool-use score in agent evaluation, its only agent sub-score above zero.
The case against it
- Poor general agent performance: negative scores on recovery, steerability and task outcome.
- Throughput varies nearly fourfold by platform, from 29.5 to 111.5 tokens per second, with no data for mid-priced tiers.
- Proprietary with no published parameter count and no downloadable weights.
How good is it?
A text model for everyday questions, drafting and coding, though it struggles with multi-step agent work and tool calls.
- getting answers to everyday questionsArena Text (overall) · 13th of 168
- drafts, rewrites and editingArena Creative Writing · 7th of 168
- writing and completing codeArena Coding · 25th of 168
- multi-step work it carries out for youArena Agent · 44th of 55
- calling tools to carry out requestsArena Agent · Tool use · 43rd of 55
- getting back on track after a step failsArena Agent · Recovery · 48th of 55
EverydayGeneral questions and everyday reasoning
Arena Text (overall)13th of 168 · 1487
CodingWriting and fixing code on its own
Arena Coding25th of 168 · 1521
AgenticPlanning, calling tools, staying on task
Arena Agent44th of 55 · −0.069
Arena Agent is the only board that has scored it for this.
WritingDrafting and rewriting prose
Arena Creative Writing7th of 168 · 1480
Arena Creative Writing is the only board that has scored it for this.
Placings on Arena's agent boards, from live sessions people ran themselves. A model can lead on one of these and sit mid-field on the others.
Boards this model appears on that none of the ratings above are built on.
Every published score for this model12 scoresEvery figure we hold, from 12 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Where to rent it
Prices checked 4 hours ago — each listing carries its own date.
Google AI, direct
The lab is the cheapest at this context. The strip above and this offer are the same one, compared at 1M of context. 2 cheaper rows below are outside that comparison: a non-standard pricing tier.
- 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 AI Studioflex tierThrough OpenRouter | $1.00 / $6.00checked 4 hours ago | 1M66K max reply | 97 tok/s | No | Yes55 days | Unknown |
| Google Vertex AIflex tierglobalThrough OpenRouter | $1.00 / $6.00checked 4 hours ago | 1M66K max reply | 17 tok/s | No | No | Confirmed |
| Google Vertex AIglobalThrough OpenRouter | $2.00 / $12.00checked 4 hours ago | 1M66K max reply | 80 tok/s | No | No | Confirmed |
| Google AI StudioThrough OpenRouter | $2.00 / $12.00checked 4 hours ago | 1M66K max reply | 96 tok/s | No | Yes55 days | Unknown |
| OpenRouterOpenRouter's own listing | $2.00 / $12.00checked 4 hours ago | 1M | not measured | Unknown | Unknown | Unknown |
| Google AIDirect | $2.00 / $12.00checked 4 hours ago | 1M66K max reply | not measured | Unknown | Unknown | Unknown |
| Google AI Studiopriority tierThrough OpenRouter | $3.60 / $21.60checked 4 hours ago | 1M66K max reply | 69 tok/s | No | Yes55 days | Unknown |
| Google Vertex AIpriority tierglobalThrough OpenRouter | $3.60 / $21.60checked 4 hours ago | 1M66K max reply | 42 tok/s | No | No | Confirmed |
Google AI Studio
Google Vertex AI
OpenRouterAcross the 8 listings we hold: 6 say they do not train on prompts, 0 say they do and 2 do not say. 3 appear in the zero-retention registry we check; the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| Google AI StudioflexThrough OpenRouter | ✓ | ✓ | ✓ |
| Google Vertex AIflex · globalThrough OpenRouter | ✓ | ✓ | ✓ |
| Google Vertex AIglobalThrough OpenRouter | ✓ | ✓ | ✓ |
| Google AI StudioThrough OpenRouter | ✓ | ✓ | ✓ |
| OpenRouterOpenRouter's own listing | ✓ | ✓ | ✓ |
| Google AIDirect | |||
| Google AI StudiopriorityThrough OpenRouter | ✓ | ✓ | ✓ |
| Google Vertex AIpriority · globalThrough OpenRouter | ✓ | ✓ | ✓ |
Tool calling: 7 of 8 listings say yes, 1 publishes no parameter list. JSON output: 7 of 8 listings say yes, 1 publishes no parameter list. Strict schema: 7 of 8 listings say yes, 1 publishes no parameter list.
Models people weigh against Gemini 3.1 Pro Preview Custom Tools
When we formed this view
Recent changes
Each date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- 1 of 8 listings publishes no parameter list, so what its API accepts is unknown to us.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 2 of 8 listings do not say whether they train on prompts.
- We hold no batch or off-peak rate for any of its listings.
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
We hold no licence record for this model, and no record of published weights either — so we can neither summarise its terms nor point you at the weights.
Identifiers
- Takes in, gives back
- Text, images, audio, video and documents in, text out
- Catalogue slug
- google-gemini-3-1-pro-preview-custom-tools