Gemini 3.5 Flash
gemini-3.5-flashGoogle's earlier Flash model, built for speed and foundational performance across routine, high-throughput workloads. Built by Google.
Prices updated
Input price
$1.50
per 1M tokens · Standard
Output price
$9.00
per 1M tokens · Standard
Input limit
1M
tokens
Output limit
66K
tokens
Input formats
Output formats
Gemini 3.5 Flash price history
2 price records since 9/25/2026
Gemini 3.5 Flash cost calculator
$75/month
Standard pricing
Overview
What is Gemini 3.5 Flash?
Gemini 3.5 Flash is a text & reasoning and vision model from Google. Google's earlier Flash model, built for speed and foundational performance across routine, high-throughput workloads. Its 1M context window and $1.50 input price make it a candidate for quality-focused production applications.
Benchmarks
Gemini 3.5 Flash benchmarks & speed
How Gemini 3.5 Flash scores on standardized evaluations, and where it lands among every model we track.
32.6
Intelligence Index
206tok/s
Output speed
1269
DesignArena Elo
Reasoning
GPQA Diamond
92.2%
Graduate-level scientific reasoning · top 13%
HLE
42.7%
Humanity's Last Exam · top 15%
Coding
SciCode
53.9%
Python for scientific computing · top 35%
Latency & design
- Time to first token
- 16.52s
- DesignArena win rate
- 54.3%
- Design battles judged
- 34,556
Independent scores from Artificial Analysis and DesignArena · updated 10/8/2026. Higher is better; ranks compare against every model we track with that score.
Rates
Gemini 3.5 Flash pricing
Pricing is based on token usage. Provider-specific caching, batch, regional, and tool charges may affect the final cost.
Input · Standard
$1.50
Per 1M tokens
Cached input · Standard
$0.15
Per 1M tokens
Capabilities
Gemini 3.5 Flash Tools
Tools available when using Gemini 3.5 Flash through supported provider APIs.
Function calling
Supported
Structured outputs
Supported
JSON mode
Supported
Reasoning
Supported
Built-in web search
Not supported
Log probabilities
Not supported
Deterministic seed
Supported
Parallel tool calls
Not supported
Prompt caching
Supported
Where to run it
Gemini 3.5 Flash API providers
7 providers serve Gemini 3.5 Flash. Prices are per 1M tokens; uptime is the last 24 hours.
| Provider | Input | Output | Cached | Context | Uptime |
|---|---|---|---|---|---|
| $0.75 | $4.50 | $0.07 | 1M | 99.48% | |
| Google AI Studio | $0.75 | $4.50 | $0.07 | 1M | 99.96% |
| $1.50 | $9.00 | $0.15 | 1M | 99.82% | |
| Google AI Studio | $1.50 | $9.00 | $0.15 | 1M | 99.94% |
| $1.65 | $9.90 | $0.17 | 1M | — | |
| $2.70 | $16 | $0.27 | 1M | 99.98% | |
| Google AI Studio | $2.70 | $16 | $0.27 | 1M | 99.88% |
- Input
- $0.75
- Output
- $4.50
- Cached
- $0.07
- Context
- 1M
- Uptime
- 99.48%
- Input
- $0.75
- Output
- $4.50
- Cached
- $0.07
- Context
- 1M
- Uptime
- 99.96%
- Input
- $1.50
- Output
- $9.00
- Cached
- $0.15
- Context
- 1M
- Uptime
- 99.82%
- Input
- $1.50
- Output
- $9.00
- Cached
- $0.15
- Context
- 1M
- Uptime
- 99.94%
- Input
- $1.65
- Output
- $9.90
- Cached
- $0.17
- Context
- 1M
- Uptime
- —
- Input
- $2.70
- Output
- $16
- Cached
- $0.27
- Context
- 1M
- Uptime
- 99.98%
- Input
- $2.70
- Output
- $16
- Cached
- $0.27
- Context
- 1M
- Uptime
- 99.88%
6 of 7
Strengths and limitations
Strengths
- Measured results (AA Intelligence 32.6 · DesignArena Elo 1269 · Arena Elo 1211 · MMLU-Pro 75.4%) position it for demanding production work.
- 1M context supports large documents, repositories and extended conversations.
- Supports text & reasoning and vision workloads in one model.
Limitations
- Generated tokens cost 6× more than input tokens, which matters for verbose responses.
- Large context capacity does not guarantee consistent retrieval across the entire prompt.
- Arena Elo and MMLU-Pro are directional; test accuracy, latency and reliability on your own workload before committing.
Arena Elo, MMLU-Pro and pricing figures are illustrative; validate current vendor terms before purchase.
Same provider