Gemini 3.5 Flash
Google · released May 19, 2026
- Type
- Closed
- Input
- $1.50
- Output
- $9.00
- Cached
- None held
List price · per 1M tokens · Google AI at 1M context · machine-readable source ↗
Our take
Written Sep 2, 2026Gemini 3.5 Flash handles up to one million tokens in a single request and accepts text, images, files, audio and video. It is a strong pick for mathematics and coding workloads, though its agentic and data-analysis scores lag well behind its headline numbers.
Choose this for long-document analysis at one million tokens, or for mathematics and coding where its benchmark scores are high. Use it for multimodal pipelines needing several input types in one endpoint, and seek out the lower-priced tiers for budget-conscious deployment. Skip it if you need autonomous agent behaviour, reliable data analysis, or guaranteed fast throughput at the cheapest rate.
The case for it
- LiveBench Mathematics score of 88.24% on the refreshed 2026 benchmark.
- Strong coding scores: 78.18% on LiveBench and 1507.74 on Arena Coding.
- One-million-token request limit, rare among workhorse models.
- Broad modality support: text, images, files, audio and video input in a single endpoint.
The case against it
- Agentic coding falls 29 percentage points below standard coding, at 48.99%.
- Data analysis is the weakest LiveBench sub-score, at 64.86%.
- All Arena Agent dimensions score below zero, including recovery and steerability.
How good is it?
A general text model for everyday questions, drafting and coding, though it can struggle to get back on track after a failed step.
- answering everyday questionsArena Text (overall) · 19th of 168
- drafting and editing textArena Creative Writing · 13th of 168
- writing and completing codeArena Coding · 42nd of 168
- getting back on track after a failed stepArena Agent · Recovery · 43rd of 55
EverydayGeneral questions and everyday reasoning
Arena Text (overall)19th of 168 · 1477
Also on this board: 1474 (Sep 25, 2026). Read the pair, not the higher one.
CodingWriting and fixing code on its own
Arena Coding42nd of 168 · 1507
Also on this board: 1506 (Sep 25, 2026). Read the pair, not the higher one.
AgenticPlanning, calling tools, staying on task
Arena Agent38th of 55 · −0.035
Also on this board: −0.047 (Sep 5, 2026). Read the pair, not the higher one.
WritingDrafting and rewriting prose
Arena Creative Writing13th of 168 · 1466
Also on this board: 1463 (Sep 25, 2026). Read the pair, not the higher one.
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 model20 scoresEvery figure we hold, from 20 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 between 59 min and 1 hour 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
- $1.50 in / $9.00 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 | $0.75 / $4.50checked 1 hour ago | 1M66K max reply | 108 tok/s | No | Yes55 days | Unknown |
| Google Vertex AIflex tierglobalThrough OpenRouter | $0.75 / $4.50checked 1 hour ago | 1M66K max reply | 3 tok/s | No | No | Confirmed |
| Google AIDirect | $1.50 / $9.00checked 59 min ago | 1M66K max reply | not measured | Unknown | Unknown | Unknown |
| Google AI StudioThrough OpenRouter | $1.50 / $9.00checked 1 hour ago | 1M66K max reply | 103 tok/s | No | Yes55 days | Unknown |
| Google Vertex AIglobalThrough OpenRouter | $1.50 / $9.00checked 1 hour ago | 1M66K max reply | 74 tok/s | No | No | Confirmed |
| OpenRouterOpenRouter's own listing | $1.50 / $9.00checked 1 hour ago | 1M | not measured | Unknown | Unknown | Unknown |
| DeepInfraDirect | $1.50 / $9.00checked 1 hour ago | 1M | not measured | Unknown | Unknown | Unknown |
| Google Vertex AIusThrough OpenRouter | $1.65 / $9.90checked 1 hour ago | 1M66K max reply | 8 tok/s | No | No | Confirmed |
| Google Vertex AIpriority tierglobalThrough OpenRouter | $2.70 / $16.20checked 1 hour ago | 1M66K max reply | 144 tok/s | No | No | Confirmed |
| Google AI Studiopriority tierThrough OpenRouter | $2.70 / $16.20checked 1 hour ago | 1M66K max reply | 59 tok/s | No | Yes55 days | Unknown |
Google AI Studio
Google Vertex AI
OpenRouter
DeepInfraAcross the 10 listings we hold: 7 say they do not train on prompts, 0 say they do and 3 do not say. 4 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 AIDirect | |||
| Google AI StudioThrough OpenRouter | ✓ | ✓ | ✓ |
| Google Vertex AIglobalThrough OpenRouter | ✓ | ✓ | ✓ |
| OpenRouterOpenRouter's own listing | ✓ | ✓ | ✓ |
| DeepInfraDirect | |||
| Google Vertex AIusThrough OpenRouter | ✓ | ✓ | ✓ |
| Google Vertex AIpriority · globalThrough OpenRouter | ✓ | ✓ | ✓ |
| Google AI StudiopriorityThrough OpenRouter | ✓ | ✓ | ✓ |
Tool calling: 8 of 10 listings say yes, 2 publish no parameter list. JSON output: 8 of 10 listings say yes, 2 publish no parameter list. Strict schema: 8 of 10 listings say yes, 2 publish no parameter list.
Models people weigh against Gemini 3.5 Flash
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
- 2 of 10 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.
- 3 of 10 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-3-5-flash