Last verified
DEPRECATED OCT 20261M CONTEXTMULTIMODALAGENTIC CODINGBATCH + FLEX

Gemini 3.5 Flash API Pricing

Gemini 3.5 Flash was Google's GA model for sustained frontier performance on agentic and coding tasks, released May 19, 2026. Google deprecated it on October 8, 2026: API requests to gemini-3.5-flash are now routed to Gemini 3.6 Flash, and the model is gone from Google's pricing page. Its last published rates were $1.50/M input, $9.00/M output, and $0.15/M cached input.

Input - per 1M tokens
$1.50/M
Base token price standard
Output - per 1M tokens
$9.00/M
Output tokens standard
Cached input
$0.15/M
Cache plus storage fee -90%
Effective - agentic blend
$1.08/M
92/8 split - 82% cache
§ 01 / TERMINAL

Gemini 3.5 Flash API cost calculator.

Live calculator pre-loaded with Gemini 3.5 Flash standard rates. Google lists standard input at $1.50/M, output including thinking tokens at $9.00/M, and cached input at $0.15/M.

$ /mo
Workload split
Prompt cache hit rate
Tokens you can process
—
Words equivalent (English)
—
Effective rate
—
Open full calculator (all models · share URL · CSV) →
§ 02 / SCENARIOS

Gemini 3.5 Flash cost on real workloads.

CODING AGENT

Repository iteration loop

$0.137/task
120k cache-heavy in / 10k out~729 units/$100
MULTIMODAL

Video + docs briefing

$0.060/brief
60k mixed in / 4k out~1,677 units/$100
RAG

Search-grounded answer

$0.045/answer
45k in / 3k out~2,237 units/$100
BULK

Batch classification

$0.0074/item
15k batch in / 1k out~13,513 units/$100
§ 03 / TOKENIZER

Gemini 3.5 Flash token counter and cost.

What's a token →
Estimate · gemini-tokenizer-estimate · ≈3.85 chars/token Auto-counts as you type

This is a chars-per-token approximation, not a real tokenizer. Actual tokens vary by language, code density, and tool-call overhead — counts are typically ±10–20% off for English prose, more for code or non-Latin scripts. For exact billing, use the vendor's official tokenizer.

Characters 406
Words 64
Tokens (estimated) 105 tokens
Cost as input · uncached $0.00016 USD
Cost as output · uncached $0.00094 USD
Cost as cached input $0.00002 USD
§ 04 / SHELF

Gemini 3.5 Flash vs similar models.

All models →
Model Input /M Output /M Effective blended Context Best for
Gemini 3.5 Flash Current $1.50 cache $0.15 $9.00 $1.08 agentic 92/8 1M Newest GA Gemini agent model
Gemini 3.1 Pro Preview $2.00 cache $0.20 $12.00 $1.44 +33% 1M Higher-ceiling preview reasoning
Gemini 3.1 Flash-Lite $0.25 cache $0.025 $1.50 $0.18 deprecated · −6.0× 1M Low-latency high-volume tasks
Gemini 3 Flash Preview $0.50 cache $0.05 $3.00 $0.361 −3.0× 1M Gemini 3 preview workloads
§ 07 / BENCHMARKS

Gemini 3.5 Flash benchmarks

All benchmarks →

Gemini 3.5 Flash has published scores on 9 benchmarks we track; its best placing is #25 of 105 on ARC-AGI-2. 2 of these scores come from an independent leaderboard; the rest are the lab's own reports.

Benchmark Score Rank Leader Source
ARC-AGI-2 Reasoning 72.1% ARC Prize verified, best result #25 of 105 GPT-6 Astra · 95% Official leaderboard ARC Prize Foundation
ARC-AGI-1 Reasoning 92.5% ARC Prize verified, best result #26 of 99 6 tied · 98.5% Official leaderboard ARC Prize Foundation
SWE-Bench Pro Coding · Public set (731 tasks) 55.1% public set #2 of 6 Gemini 3.6 Flash · 58.7% Vendor-reported Google DeepMind
MLE-bench AI research 49.7% as reported #2 of 5 Gemini 3.6 Flash · 63.9% Vendor-reported Google DeepMind
MRCR v2 Long context · 8-needle, up to 128K 77.3% 128K average #4 of 7 Gemini 3.7 Flash · 97% Vendor-reported Google DeepMind
OSWorld-Verified Agents and computer use 78.4% as reported #5 of 8 Kimi K3 · 84.8% Vendor-reported Google DeepMind
CharXiv Reasoning Vision and documents · No tools 84.2% no tools #6 of 9 Kimi K3.1 Pro · 89% Vendor-reported Google DeepMind
Terminal-Bench 2 Agents and computer use · Terminal-Bench 2.1 76.2% Terminus-2 harness #13 of 17 DeepSeek V4.1 Flash · 90.6% Vendor-reported Google DeepMind
DeepSWE Coding 37% as reported #25 of 27 Gemini 4 Argon · 77.9% Vendor-reported Google DeepMind

Gemini 3.5 Flash API pricing FAQ.

Practical Gemini 3.5 Flash pricing questions, with standard, batch, flex, and priority tiers separated.

Q · 01 What is Gemini 3.5 Flash priced at? +
Google last listed gemini-3.5-flash at $1.50/M input, $9.00/M output, and $0.15/M cached input. These were USD prices per 1M tokens on the paid Gemini API tier; the model left the pricing page when Google deprecated it on October 8, 2026.
Q · 02 Can I still use Gemini 3.5 Flash? +
Not as itself. Google deprecated gemini-3.5-flash on October 8, 2026 and replaced it with Gemini 3.6 Flash. The endpoint is not shutting down, but API requests to it are routed automatically to gemini-3.6-flash, and the model can no longer be selected in Google AI Studio. Google asks developers to switch the model string to gemini-3.6-flash or gemini-3.8-flash, and does not say which rate a routed request is billed at.
Q · 03 Does output pricing include thinking tokens? +
Yes. Google's pricing table labels the output row as Output price (including thinking tokens), so this page treats generated thinking and answer tokens as output.
Q · 04 How much do Batch and Flex cost? +
Google listed Batch at $0.75/M input, $4.50/M output, and $0.075/M cached input. Flex uses the same input/output rates, with cached input listed at $0.08/M.
Q · 05 What about Priority pricing? +
Priority was higher-priced: $2.70/M input, $16.20/M output, and $0.27/M cached input.
Q · 06 What context window does it support? +
Google's model page lists an input token limit of 1,048,576 and an output token limit of 65,536. AI//COST rounds that to a 1M context label.
Q · 07 Is this a preview model? +
No. Google released gemini-3.5-flash as the GA version on May 19, 2026. The older preview row remains separate as gemini-3-flash-preview.
Y
Reviewed by Yaroslav Vikhariev Founder · AI//COST · Prices checked by hand against ai.google.dev · Last verified Jun 8, 2026
Methodology Report a correction More by Y.V.