Gemini 3.5 Flash pricing, context window, and cost calculator
Gemini 3.5 Flash with official provider identity, pricing, and token limits.
Verified fields
Quick facts
gemini-3.5-flashSupported capabilities
- Streaming
- Function calling
- Structured outputs
- Prompt caching
- Batch API
- Reasoning
Only capabilities explicitly tracked from provider documentation are shown.
Source-tracked rates
Verified pricing profiles
Amounts are USD per 1M tokens unless the column states an hourly storage unit.
| Profile | Input / 1M | Cached input / 1M | Output / 1M | Notes |
|---|---|---|---|---|
| standardDefault | $1.50 USD | $0.15 USD | $9.00 USD | Used for default estimates. |
Workload estimate
Gemini 3.5 Flash cost calculator
Change the workload assumptions. The calculator uses the same shared pricing resolver as StackLens Compare.
Estimated monthly total$60.00
- Monthly input cost
- $15.00
- Monthly output cost
- $45.00
- Per 1,000 requests
- $6.00
- Active profile
- standard
Estimate excludes untracked provider-specific charges.
Explicit assumptions
Common workload examples
1M input tokens
$1.50 under the standard profile, excluding output and other charges.
1M output tokens
$9.00 under the standard profile, excluding input and other charges.
10,000 monthly requests
At 1,000 input and 500 output tokens per request: $60.00 under standard.
50% cached input
The same default workload with 50% cached input is estimated at $53.25. Cache savings apply only to the tracked cached-input rate.
Research layer
Experience and rollout notes
Official facts are separated from user reports. Community reports are useful signals, not controlled benchmarks.
Official model and pricing record
Google publishes Gemini 3.5 Flash model specifications and tiered API pricing separately. StackLens uses the official model and pricing pages for tracked limits and cost calculations.
What this does not prove: Provider specifications and pricing do not measure application-level accuracy or completed-task cost.
Speed and tool use
Some early users report fast responses and more consistent tool use in agentic workflows than they expected from a Flash-tier model.
What this does not prove: The reports use different tools and prompts and do not establish a provider-wide success rate.
Reliability and token overhead
Other users report coding reliability problems, high token use, or inconsistent results over time. These concerns conflict with the positive agentic-workflow reports.
What this does not prove: Treat these as test hypotheses. Track retries, token volume, and accepted outputs on your own workload.
No controlled StackLens benchmark yet
StackLens has not run a controlled Gemini 3.5 Flash benchmark. The notes above separate official documentation from independent user reports.
Research reviewed 2026-07-13. Reports may change as Gemini 3.5 Flash reaches more workflows.
Tracked relationships
Related models
StackLens relationship map based on model families and published decision comparisons. Find a workload match → Open relationship map → Open price map →
Featured comparisons
- Gemini 3.5 Flash vs GPT-5.6 Terra cost
- Gemini 3.5 Flash vs GPT-4o cost
- Gemini 3.5 Flash vs Gemini 3 Flash Preview cost
- Gemini 3.5 Flash vs Gemini 3.6 Flash cost
- Gemini 3.5 Flash vs Gemini 3.1 Pro Preview cost
- Gemini 3.5 Flash vs Gemini 3.1 Flash-Lite cost
Continue your research
Verification
Sources and methodology
Pricing and limits are source-tracked and may change. Verify current values with the provider before making production purchasing decisions.
Calculator profile rule: standard is the verified default.