Gemini 3.5 Flash
Google · released May 19, 2026
- Type
- Proprietary
- Input
- $1.50
- Output
- $9.00
- 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 3, 2026Gemini 3.5 Flash is a general-purpose multimodal model from Google that can handle up to one million tokens in a single request and accepts text, images, files, audio and video. It sits between budget and frontier options on price, with strong math and coding scores but weaker creative writing and instruction-following performance.
Choose this for long-document or video analysis where a one-million-token request limit matters, or for multimodal pipelines that need several input types in one model. It is a natural fit for teams already in the Google ecosystem via Vertex AI. Skip it if you need open weights for self-hosting, if your workload is output-heavy and cost-sensitive, or if creative writing and precise instruction following are central to your use case.
The case for it
- One of the longest request limits in the catalogue at 1,048,576 tokens, enabling long-document and video workloads.
- Broadest modality support in its class: text, images, files, audio and video inputs with text output.
- Math performance 44.6 points above its overall text rating on the Arena leaderboard; coding 31.1 points above.
- Lowest price tier from the same provider is several times cheaper than the highest tier.
The case against it
- Creative writing and instruction following lag well behind its math and coding scores.
- Output pricing at the cheapest tier is six times the input price, making output-heavy workloads expensive.
- Throughput at the cheapest tier is severely limited: about 20 times slower than the premium tier on the same provider.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)10th of 143 · 1476.4via High
Also on this board: 1474.1 via Medium (Aug 2, 2026). Read the pair, not the higher one.
CodingWriting and fixing code on its own
Arena Coding27th of 143 · 1507.5via Medium
Also on this board: 1506.8 via High (Aug 2, 2026). Read the pair, not the higher one.
AgenticPlanning, calling tools, staying on task
Arena Agent (IPS)22nd of 36 · −0.01via High
Also on this board: −0.053 via Medium (Jul 28, 2026). Read the pair, not the higher one.
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 3.5 Flash 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 model16 scoresEvery figure we hold, from 16 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
The lab is also the cheapest we hold. The strip above and this offer are the same one, so nothing on this page undercuts Google AI on 1M of context.
- 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 Vertex AIglobal | $0.75 / $4.50 | 1M | 4 tok/s | No | No | Confirmed |
| Google AI Studioflex tier | $0.75 / $4.50 | 1M | 131 tok/s | No | Yes55 days | Unknown |
| Google AI | $1.50 / $9.00 | 1M66K out | not measured | Unknown | Unknown | Unknown |
| OpenRouter | $1.50 / $9.00 | 1M | not measured | Unknown | Unknown | Unknown |
| Google AI Studio | $1.50 / $9.00 | 1M | 144 tok/s | No | Yes55 days | Unknown |
| DeepInfra | $1.50 / $9.00 | 1M | not measured | Unknown | Unknown | Unknown |
| Google AI Studiopriority tier | $2.70 / $16.20 | 1M | 36 tok/s | No | Yes55 days | Unknown |
Google Vertex AI
Google AI Studio
OpenRouter
DeepInfraAcross the 7 listings we hold: 4 say they do not train on prompts, 0 say they do and 3 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 | ✓ | ✓ | ✓ |
| Google AI | |||
| OpenRouter | ✓ | ✓ | ✓ |
| Google AI Studio | ✓ | ✓ | ✓ |
| DeepInfra | |||
| Google AI Studiopriority | ✓ | ✓ | ✓ |
Tool calling: 5 of 7 listings say yes, 2 publish no parameter list. JSON output: 5 of 7 listings say yes, 2 publish no parameter list. Strict schema: 5 of 7 listings say yes, 2 publish no parameter list.
Models people weigh against Gemini 3.5 Flash
When we formed this view
Dates behind this page
Prices last checked 9d ago
What we do not know about this model yet
- 2 of 7 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 7 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-3-5-flash