Gemini 3 Flash Preview
Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool...
Input / 1M
$0.50
Output / 1M
$3.00
Context
1M
AA Intelligence
26.3
Closed weights — available only as a hosted API
text + image + file + audio + video → text
View on OpenRouter ↗
Pricing
via OpenRouter · USD per 1M tokens · synced 2026-10-24$0.50
input / 1M
$3.00
output / 1M
$0.05
cached input / 1M
$3.50
1M in + 1M out
:batch variant
$0.25 in · $1.50 out
- Context window
- 1,048,576 tokens
- Max output
- 65,536 tokens
- Providers
- 2
- Cheapest provider
- Google AI Studio · $0.25 / $1.50
- Best throughput
- —
- AA Intelligence / Coding / Agentic
- 26.3 / — / —
✓ Tool calling
✓ Reasoning
✓ Structured outputs
✓ Image input
✓ File input
✓ Audio input
✓ Prompt caching
Price history
tracking started — chart appears after 7 days of snapshots (6 recorded)Current: $0.50 input · $3.00 output per 1M tokens
Benchmarks
Third-party indices as published through OpenRouter — Artificial Analysis and Design Arena. Not measured by us.
- AA Intelligence Index
- 26.3
- AA Coding Index
- —
- AA Agentic Index
- —
Design Arena
CategoryEloWin %Rank
agenticslides
1073
39.3%
#8
agenticslides(python-pptx)
1075
39.3%
#8
androidnative
1052
48.1%
#34
fullstack
1063
47.4%
#33
godotgamedev
1161
50.6%
#19
mobileapps
1090
46.6%
#41
python-pptxslides
1036
38.3%
#28
webapps
1110
48.5%
#37
3d
1184
62.7%
#56
codecategories
1189
57.6%
#62
gamedev
1166
58.3%
#71
website
1196
57%
#64
Providers
2 providers · per 1M tokens · last 30 min metrics| Provider | Quant | Context | Input | Output | Uptime | Tok/s |
|---|---|---|---|---|---|---|
| unknown | 1M | $0.25 | $1.50 | 67% | — | |
| Google AI Studio | unknown | 1M | $0.25 | $1.50 | 100% | — |
| unknown | 1M | $0.50 | $3.00 | 100% | — | |
| Google AI Studio | unknown | 1M | $0.50 | $3.00 | 100% | — |
| unknown | 1M | $0.90 | $5.40 | 100% | — | |
| Google AI Studio | unknown | 1M | $0.90 | $5.40 | 100% | — |
Provider data from OpenRouter's endpoint listing, refreshed daily.
Specifications
- Organisation
- Released on OpenRouter
- 2025-12-17
- Context window
- 1,048,576 tokens
- Max output
- 65,536 tokens
- Input
- text, image, file, audio, video
- Output
- text
- Tokenizer
- Gemini
- Moderated by provider
- No
- OpenRouter id
- google/gemini-3-flash-preview
Compare with
Popular comparisons
Prices, context and providers from the public OpenRouter API, snapshotted daily; benchmark indices from Artificial Analysis. See /methodology.