Gemini 3.5 Flash Lite API Pricing: Sub-Second Multimodal Scale
Detailed Google Gemini 3.5 Flash Lite API pricing ($0.30/M input, $2.50/M output), 1M token context window, context caching discounts, and enterprise SLA budgets.
Full specs, context window and API limits →How much does Gemini 3.5 Flash Lite cost per million tokens?
Google Gemini 3.5 Flash Lite charges $0.30 per million input tokens and $2.50 per million output tokens ($0.85/M blended at 3:1). Supports 1M context with native audio and video understanding. Verified 2026-09-08.
Verified 2026-09-07 — source
How much does Gemini 3.5 Flash Lite cost per 1,000 requests?
Computed from generated token pricing. Each row assumes the listed input and output tokens per request; this model has no measured verbosity factor, so the unadjusted output estimate is shown.
| Request shape | Input tokens | Output tokens | Cost / 1,000 requests |
|---|---|---|---|
| Short | 100 | 50 | $0.1550 |
| Medium | 1,000 | 500 | $1.5500 |
| Long | 4,000 | 2,000 | $6.2000 |
Formula: ((input price × input tokens) + (output price × output tokens × verbosity factor)) ÷ 1,000,000 × 1,000. Assumptions: short 100/50, medium 1,000/500, long 4,000/2,000 input/output tokens per request. Unadjusted — no measured verbosity factor is available.
Three model-specific pricing decisions
Flash Lite’s exact-model bill is separated from Google endpoint policy and the broad version comparison. Legacy status is visible in the neighboring input row.
1. 3.1 Flash Lite → 3.5 migration bill
| Model | Verified | Input / output per M | 100K fixed bill | Lifecycle boundary |
|---|---|---|---|---|
| Gemini 3.5 Flash Lite | 2026-08-14 | $0.30 / $2.50 | $185.00 | Current selected owner |
| Gemini 3.1 Flash Lite | 2026-04-06 | $0.25 / $1.50 | $125.00 | Legacy — superseded by Gemini 3.5 Flash Lite |
2. 1M-context extraction and agent sensitivity
| Fixed workload (input / output) | Gemini 3.5 Flash Lite | Gemini 3.6 Flash | Decision boundary |
|---|---|---|---|
| 1M extraction · 1,000,000 / 2,000 | $30500.00 | $151500.00 | 10% accepted-result uplift required to justify the higher bill |
| Long agent · 250,000 / 4,000 | $8500.00 | $40500.00 | 15% accepted-result uplift required to justify the higher bill |
Formula: 100,000 × (input tokens × input $/M + output tokens × output $/M) ÷ 1,000,000. Uplift is a decision threshold, not a measured quality claim.
3. Unit-safe endpoint evidence
| Surface / unit | Dated evidence | Safe calculation |
|---|---|---|
| Text | $0.000300 $/1K tokens | $185.00 |
| Vision | Unavailable | No image-unit conversion |
| Cache | Unavailable | No discount default |
| Batch | Unavailable | No discount default |
| AI Studio / Vertex | Endpoint distinction unavailable on price row | Do not merge invoices |
Verified 2026-08-14. “Unavailable” means no compatible dated evidence was found; it is never treated as zero. First-party price source · Run this exact scenario.
All three decisions are server-rendered for Gemini 3.5 Flash Lite; fixed inputs, formulas, dated sources, and unavailable states are intentionally visible.
Exact-model pricing guide · verified 2026-09-07
Exact model boundary: Google gemini-3.5-flash-lite (slug gemini-3-5-flash-lite). First-party provider pricing and API documentation remain fact owners.
Token pricing and enterprise tier expenditure matrix
Frozen scenario board. Formula / deterministic rule: monthly_spend = calls * ((in_tokens * 0.30 + out_tokens * 2.50) / 1M) Boundary: Owns base token tariff comparisons and budget expenditure modeling.
| Frozen scenario | Model, identity, provider, and evidence fields | Result | State |
|---|---|---|---|
| 50K customer support classifications | model=gemini-3.5-flash-lite; slug=gemini-3-5-flash-lite; provider=Google; scenario=50K customer support classifications; workload; prompt tokens; completion tokens; standard spend; cached spend; net savings; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-07; measurement versus assumption=explicit | Unavailable — 50K customer support classifications is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| 200K data extraction requests | model=gemini-3.5-flash-lite; slug=gemini-3-5-flash-lite; provider=Google; scenario=200K data extraction requests; workload; prompt tokens; completion tokens; standard spend; cached spend; net savings; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-07; measurement versus assumption=explicit | Unavailable — 200K data extraction requests is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| 500K high-volume utility queries | model=gemini-3.5-flash-lite; slug=gemini-3-5-flash-lite; provider=Google; scenario=500K high-volume utility queries; workload; prompt tokens; completion tokens; standard spend; cached spend; net savings; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-07; measurement versus assumption=explicit | Unavailable — 500K high-volume utility queries is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| prompt caching active (75% read discount) | model=gemini-3.5-flash-lite; slug=gemini-3-5-flash-lite; provider=Google; scenario=prompt caching active (75% read discount); workload; prompt tokens; completion tokens; standard spend; cached spend; net savings; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-07; measurement versus assumption=explicit | Unavailable — prompt caching active (75% read discount) is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| batch processing active (50% both) | model=gemini-3.5-flash-lite; slug=gemini-3-5-flash-lite; provider=Google; scenario=batch processing active (50% both); workload; prompt tokens; completion tokens; standard spend; cached spend; net savings; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-07; measurement versus assumption=explicit | Unavailable — batch processing active (50% both) is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| unresolved pricing currency | model=gemini-3.5-flash-lite; slug=gemini-3-5-flash-lite; provider=Google; scenario=unresolved pricing currency; workload; prompt tokens; completion tokens; standard spend; cached spend; net savings; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-07; measurement versus assumption=explicit | Unavailable — unresolved pricing currency has no matched, dated bilateral observation. | FAIL CLOSED — manual, probe, or source evidence required |
First-party provenance: Google Gemini API pricing; verification date 2026-09-07. Missing or conflicting joins fail closed.
Context window saturation (1M scale) and multimodal gate
Frozen scenario board. Formula / deterministic rule: eligible = (context <= 1M ? Eligible : Excluded); multimodal audio/video support Boundary: Owns context scaling and capability gating for large multimodal inputs.
| Frozen scenario | Model, identity, provider, and evidence fields | Result | State |
|---|---|---|---|
| short text query (5K tokens) | model=gemini-3.5-flash-lite; slug=gemini-3-5-flash-lite; provider=Google; scenario=short text query (5K tokens); context size; text eligible; audio eligible; video eligible; token expenditure; routing verdict; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-07; measurement versus assumption=explicit | Unavailable — short text query (5K tokens) is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| multi-hour audio transcription (300K tokens) | model=gemini-3.5-flash-lite; slug=gemini-3-5-flash-lite; provider=Google; scenario=multi-hour audio transcription (300K tokens); context size; text eligible; audio eligible; video eligible; token expenditure; routing verdict; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-07; measurement versus assumption=explicit | Unavailable — multi-hour audio transcription (300K tokens) is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| dense legal repository (750K tokens) | model=gemini-3.5-flash-lite; slug=gemini-3-5-flash-lite; provider=Google; scenario=dense legal repository (750K tokens); context size; text eligible; audio eligible; video eligible; token expenditure; routing verdict; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-07; measurement versus assumption=explicit | Unavailable — dense legal repository (750K tokens) is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| 1M full context saturation test | model=gemini-3.5-flash-lite; slug=gemini-3-5-flash-lite; provider=Google; scenario=1M full context saturation test; context size; text eligible; audio eligible; video eligible; token expenditure; routing verdict; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-07; measurement versus assumption=explicit | Unavailable — 1M full context saturation test is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| video frame rate downsampling penalty | model=gemini-3.5-flash-lite; slug=gemini-3-5-flash-lite; provider=Google; scenario=video frame rate downsampling penalty; context size; text eligible; audio eligible; video eligible; token expenditure; routing verdict; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-07; measurement versus assumption=explicit | Unavailable — video frame rate downsampling penalty is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| unsupported media payload format | model=gemini-3.5-flash-lite; slug=gemini-3-5-flash-lite; provider=Google; scenario=unsupported media payload format; context size; text eligible; audio eligible; video eligible; token expenditure; routing verdict; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-07; measurement versus assumption=explicit | Unavailable — unsupported media payload format has no matched, dated bilateral observation. | FAIL CLOSED — manual, probe, or source evidence required |
First-party provenance: Google Gemini documentation; verification date 2026-09-07. Missing or conflicting joins fail closed.
Turnaround time latency and high-volume routing SLA audit
Frozen scenario board. Formula / deterministic rule: turnaround = ttft + (tokens_out / tps); Flash Lite optimized for high-volume endpoints Boundary: Owns turnaround time benchmarks and user experience responsiveness.
| Frozen scenario | Model, identity, provider, and evidence fields | Result | State |
|---|---|---|---|
| real-time chat autocomplete (<200ms) | model=gemini-3.5-flash-lite; slug=gemini-3-5-flash-lite; provider=Google; scenario=real-time chat autocomplete (<200ms); task; response SLA; latency; generation speed; SLA compliance; responsiveness verdict; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-07; measurement versus assumption=explicit | Unavailable — real-time chat autocomplete (<200ms) is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| customer support agent reply (<400ms) | model=gemini-3.5-flash-lite; slug=gemini-3-5-flash-lite; provider=Google; scenario=customer support agent reply (<400ms); task; response SLA; latency; generation speed; SLA compliance; responsiveness verdict; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-07; measurement versus assumption=explicit | Unavailable — customer support agent reply (<400ms) is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| structured JSON data parsing | model=gemini-3.5-flash-lite; slug=gemini-3-5-flash-lite; provider=Google; scenario=structured JSON data parsing; task; response SLA; latency; generation speed; SLA compliance; responsiveness verdict; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-07; measurement versus assumption=explicit | Unavailable — structured JSON data parsing is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| high-throughput batch classification | model=gemini-3.5-flash-lite; slug=gemini-3-5-flash-lite; provider=Google; scenario=high-throughput batch classification; task; response SLA; latency; generation speed; SLA compliance; responsiveness verdict; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-07; measurement versus assumption=explicit | Unavailable — high-throughput batch classification is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| concurrency contention latency spike | model=gemini-3.5-flash-lite; slug=gemini-3-5-flash-lite; provider=Google; scenario=concurrency contention latency spike; task; response SLA; latency; generation speed; SLA compliance; responsiveness verdict; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-07; measurement versus assumption=explicit | Unavailable — concurrency contention latency spike is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| unmeasured speed fixture | model=gemini-3.5-flash-lite; slug=gemini-3-5-flash-lite; provider=Google; scenario=unmeasured speed fixture; task; response SLA; latency; generation speed; SLA compliance; responsiveness verdict; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-07; measurement versus assumption=explicit | Unavailable — unmeasured speed fixture is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
First-party provenance: Google Gemini documentation; verification date 2026-09-07. Missing or conflicting joins fail closed.
Method and limitations: formulas are deterministic; observed and assumed inputs are labeled; no missing provider, host, account, region, realm, alias, snapshot, revision, weight, artifact, control, tool, modality, workload, rate-period, timestamp, or result is transferred. Run this scenario →
Verified Model Pricing Intelligence•Audit date: 2026-09-08
Gemini 3.5 Flash Lite API Pricing: Sub-Second Multimodal Scale
Google Gemini 3.5 Flash Lite charges $0.30 per million input tokens and $2.50 per million output tokens ($0.85/M blended at 3:1). Supports 1M context with native audio and video understanding. Verified 2026-09-08.
Token pricing and enterprise tier expenditure matrix
Frozen scenario board. Formula / deterministic rule: monthly_spend = calls * ((in_tokens * 0.30 + out_tokens * 2.50) / 1M) Boundary: Owns base token tariff comparisons and budget expenditure modeling.
| Frozen scenario | Model, identity, provider, and evidence fields | Result | State |
|---|---|---|---|
| 50K customer support classifications | model=gemini-3.5-flash-lite; slug=gemini-3-5-flash-lite; provider=Google; scenario=50K customer support classifications; workload; prompt tokens; completion tokens; standard spend; cached spend; net savings; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — 50K customer support classifications is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| 200K data extraction requests | model=gemini-3.5-flash-lite; slug=gemini-3-5-flash-lite; provider=Google; scenario=200K data extraction requests; workload; prompt tokens; completion tokens; standard spend; cached spend; net savings; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — 200K data extraction requests is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| 500K high-volume utility queries | model=gemini-3.5-flash-lite; slug=gemini-3-5-flash-lite; provider=Google; scenario=500K high-volume utility queries; workload; prompt tokens; completion tokens; standard spend; cached spend; net savings; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — 500K high-volume utility queries is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| prompt caching active (75% read discount) | model=gemini-3.5-flash-lite; slug=gemini-3-5-flash-lite; provider=Google; scenario=prompt caching active (75% read discount); workload; prompt tokens; completion tokens; standard spend; cached spend; net savings; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — prompt caching active (75% read discount) is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| batch processing active (50% both) | model=gemini-3.5-flash-lite; slug=gemini-3-5-flash-lite; provider=Google; scenario=batch processing active (50% both); workload; prompt tokens; completion tokens; standard spend; cached spend; net savings; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — batch processing active (50% both) is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| unresolved pricing currency | model=gemini-3.5-flash-lite; slug=gemini-3-5-flash-lite; provider=Google; scenario=unresolved pricing currency; workload; prompt tokens; completion tokens; standard spend; cached spend; net savings; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — unresolved pricing currency has no matched, dated bilateral observation. | FAIL CLOSED — manual, probe, or source evidence required |
First-party provenance: Google Cloud AI pricing; verification date 2026-09-08. Missing or conflicting joins fail closed.
Context window saturation (1M scale) and multimodal gate
Frozen scenario board. Formula / deterministic rule: eligible = (context <= 1M ? Eligible : Excluded); multimodal audio/video support Boundary: Owns context scaling and capability gating for large multimodal inputs.
| Frozen scenario | Model, identity, provider, and evidence fields | Result | State |
|---|---|---|---|
| short text query (5K tokens) | model=gemini-3.5-flash-lite; slug=gemini-3-5-flash-lite; provider=Google; scenario=short text query (5K tokens); context size; text eligible; audio eligible; video eligible; token expenditure; routing verdict; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — short text query (5K tokens) is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| multi-hour audio transcription (300K tokens) | model=gemini-3.5-flash-lite; slug=gemini-3-5-flash-lite; provider=Google; scenario=multi-hour audio transcription (300K tokens); context size; text eligible; audio eligible; video eligible; token expenditure; routing verdict; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — multi-hour audio transcription (300K tokens) is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| dense legal repository (750K tokens) | model=gemini-3.5-flash-lite; slug=gemini-3-5-flash-lite; provider=Google; scenario=dense legal repository (750K tokens); context size; text eligible; audio eligible; video eligible; token expenditure; routing verdict; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — dense legal repository (750K tokens) is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| 1M full context saturation test | model=gemini-3.5-flash-lite; slug=gemini-3-5-flash-lite; provider=Google; scenario=1M full context saturation test; context size; text eligible; audio eligible; video eligible; token expenditure; routing verdict; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — 1M full context saturation test is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| video frame rate downsampling penalty | model=gemini-3.5-flash-lite; slug=gemini-3-5-flash-lite; provider=Google; scenario=video frame rate downsampling penalty; context size; text eligible; audio eligible; video eligible; token expenditure; routing verdict; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — video frame rate downsampling penalty is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| unsupported media payload format | model=gemini-3.5-flash-lite; slug=gemini-3-5-flash-lite; provider=Google; scenario=unsupported media payload format; context size; text eligible; audio eligible; video eligible; token expenditure; routing verdict; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — unsupported media payload format has no matched, dated bilateral observation. | FAIL CLOSED — manual, probe, or source evidence required |
First-party provenance: Google Gemini documentation; verification date 2026-09-08. Missing or conflicting joins fail closed.
Turnaround time latency and high-volume routing SLA audit
Frozen scenario board. Formula / deterministic rule: turnaround = ttft + (tokens_out / tps); Flash Lite optimized for high-volume endpoints Boundary: Owns turnaround time benchmarks and user experience responsiveness.
| Frozen scenario | Model, identity, provider, and evidence fields | Result | State |
|---|---|---|---|
| real-time chat autocomplete (<200ms) | model=gemini-3.5-flash-lite; slug=gemini-3-5-flash-lite; provider=Google; scenario=real-time chat autocomplete (<200ms); task; response SLA; latency; generation speed; SLA compliance; responsiveness verdict; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — real-time chat autocomplete (<200ms) is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| customer support agent reply (<400ms) | model=gemini-3.5-flash-lite; slug=gemini-3-5-flash-lite; provider=Google; scenario=customer support agent reply (<400ms); task; response SLA; latency; generation speed; SLA compliance; responsiveness verdict; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — customer support agent reply (<400ms) is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| structured JSON data parsing | model=gemini-3.5-flash-lite; slug=gemini-3-5-flash-lite; provider=Google; scenario=structured JSON data parsing; task; response SLA; latency; generation speed; SLA compliance; responsiveness verdict; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — structured JSON data parsing is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| high-throughput batch classification | model=gemini-3.5-flash-lite; slug=gemini-3-5-flash-lite; provider=Google; scenario=high-throughput batch classification; task; response SLA; latency; generation speed; SLA compliance; responsiveness verdict; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — high-throughput batch classification is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| concurrency contention latency spike | model=gemini-3.5-flash-lite; slug=gemini-3-5-flash-lite; provider=Google; scenario=concurrency contention latency spike; task; response SLA; latency; generation speed; SLA compliance; responsiveness verdict; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — concurrency contention latency spike is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| unmeasured speed fixture | model=gemini-3.5-flash-lite; slug=gemini-3-5-flash-lite; provider=Google; scenario=unmeasured speed fixture; task; response SLA; latency; generation speed; SLA compliance; responsiveness verdict; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — unmeasured speed fixture is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
First-party provenance: Google Gemini documentation; verification date 2026-09-08. Missing or conflicting joins fail closed.
Exact-Model Pricing Evidence•Verified 2026-08-14; revalidation required before current claims.
Gemini 3.5 Flash Lite pricing evidence
Source-backed dated rate shape: input=$0.300000/M; output=$2.500000/M. Gemini 3.5 Flash Lite exact-model unit economics only; Google quota policy, Flash-family rankings, and 3.6/3.7 comparisons retain their owners. Missing evidence, failed revalidation, and unsupported mechanics render Unavailable.
Module 1 of 3: Classification and summarization volume ladder
Novel contribution boundary: Owns dated Lite arithmetic for fixed high-volume text shapes; throughput and quality are not asserted. Formula / deterministic rule: spend = requests × (inputTokens × inputRate + outputTokens × outputRate) / 1,000
| Scenario | Exact model, provider, and fixed inputs | Result | State |
|---|---|---|---|
| 100K classification requests | model=gemini-3.5-flash-lite; provider=google; registryRates=input=$0.300000/M; output=$2.500000/M; comparisonModel=gemini-3.6-flash; fixedInputs=requests=100,000; inputTokens=300; outputTokens=80; FAIL CLOSED — no revalidated observation or provider guarantee; measurement versus assumption=explicit | Unavailable — Last verified 2026-08-14, before revalidation date 2026-09-14. | FAIL CLOSED — no revalidated observation or provider guarantee |
| 1M extraction requests | model=gemini-3.5-flash-lite; provider=google; registryRates=input=$0.300000/M; output=$2.500000/M; comparisonModel=gemini-3.6-flash; fixedInputs=requests=1,000,000; inputTokens=600; outputTokens=120; FAIL CLOSED — no revalidated observation or provider guarantee; measurement versus assumption=explicit | Unavailable — Last verified 2026-08-14, before revalidation date 2026-09-14. | FAIL CLOSED — no revalidated observation or provider guarantee |
| 10M compact summary requests | model=gemini-3.5-flash-lite; provider=google; registryRates=input=$0.300000/M; output=$2.500000/M; comparisonModel=gemini-3.6-flash; fixedInputs=requests=10,000,000; inputTokens=1,000; outputTokens=200; FAIL CLOSED — no revalidated observation or provider guarantee; measurement versus assumption=explicit | Unavailable — Last verified 2026-08-14, before revalidation date 2026-09-14. | FAIL CLOSED — no revalidated observation or provider guarantee |
First-party registry provenance: https://ai.google.dev/gemini-api/docs/latest-model; registry provider google; verified 2026-08-14; freshness gate=2026-09-14. Revalidate before any current-price claim.
Module 2 of 3: Lite→3.6 accepted-result premium
Novel contribution boundary: Owns dated escalation arithmetic with explicit retry input; accepted-result uplift and routing quality are not sourced. Formula / deterministic rule: requiredAcceptedRate = 3.6 Flash attempt-plus-retry cost / Lite attempt cost; observed acceptance = Unavailable
| Scenario | Exact model, provider, and fixed inputs | Result | State |
|---|---|---|---|
| Short classification; 10% retry share; 100 retry-input tokens | model=gemini-3.5-flash-lite; provider=google; registryRates=input=$0.300000/M; output=$2.500000/M; comparisonModel=gemini-3.6-flash; fixedInputs=requests=1; inputTokens=300; outputTokens=80; retryInputTokens=100; retryShare=10%; FAIL CLOSED — no revalidated observation or provider guarantee; measurement versus assumption=explicit | Unavailable — Last verified 2026-08-14, before revalidation date 2026-09-14. | FAIL CLOSED — no revalidated observation or provider guarantee |
| Medium extraction pass; 20% retry share; 250 retry-input tokens | model=gemini-3.5-flash-lite; provider=google; registryRates=input=$0.300000/M; output=$2.500000/M; comparisonModel=gemini-3.6-flash; fixedInputs=requests=1; inputTokens=600; outputTokens=120; retryInputTokens=250; retryShare=20%; FAIL CLOSED — no revalidated observation or provider guarantee; measurement versus assumption=explicit | Unavailable — Last verified 2026-08-14, before revalidation date 2026-09-14. | FAIL CLOSED — no revalidated observation or provider guarantee |
| Long summary pass; 30% retry share; 500 retry-input tokens | model=gemini-3.5-flash-lite; provider=google; registryRates=input=$0.300000/M; output=$2.500000/M; comparisonModel=gemini-3.6-flash; fixedInputs=requests=1; inputTokens=1,000; outputTokens=200; retryInputTokens=500; retryShare=30%; FAIL CLOSED — no revalidated observation or provider guarantee; measurement versus assumption=explicit | Unavailable — Last verified 2026-08-14, before revalidation date 2026-09-14. | FAIL CLOSED — no revalidated observation or provider guarantee |
First-party registry provenance: https://ai.google.dev/gemini-api/docs/latest-model; registry provider google; verified 2026-08-14; freshness gate=2026-09-14. Revalidate before any current-price claim.
Module 3 of 3: 1M-context and cache evidence register
Novel contribution boundary: Owns exact-model registry evidence only; context and cache terms are not inferred from the Flash family. Formula / deterministic rule: evidence = exact-model registry field when present; missing unit data = Unavailable
| Scenario | Exact model, provider, and fixed inputs | Result | State |
|---|---|---|---|
| 1M context limit or price treatment | model=gemini-3.5-flash-lite; provider=google; registryRates=input=$0.300000/M; output=$2.500000/M; comparisonModel=gemini-3.6-flash; fixedInputs=evidenceField=context; FAIL CLOSED — no revalidated observation or provider guarantee; measurement versus assumption=explicit | Unavailable — Last verified 2026-08-14, before revalidation date 2026-09-14. | FAIL CLOSED — no revalidated observation or provider guarantee |
| Prompt-cache price or eligibility | model=gemini-3.5-flash-lite; provider=google; registryRates=input=$0.300000/M; output=$2.500000/M; comparisonModel=gemini-3.6-flash; fixedInputs=evidenceField=cache; FAIL CLOSED — no revalidated observation or provider guarantee; measurement versus assumption=explicit | Unavailable — Last verified 2026-08-14, before revalidation date 2026-09-14. | FAIL CLOSED — no revalidated observation or provider guarantee |
| Unpriced modality unit | model=gemini-3.5-flash-lite; provider=google; registryRates=input=$0.300000/M; output=$2.500000/M; comparisonModel=gemini-3.6-flash; fixedInputs=evidenceField=modality; FAIL CLOSED — no revalidated observation or provider guarantee; measurement versus assumption=explicit | Unavailable — Last verified 2026-08-14, before revalidation date 2026-09-14. | FAIL CLOSED — no revalidated observation or provider guarantee |
First-party registry provenance: https://ai.google.dev/gemini-api/docs/latest-model; registry provider google; verified 2026-08-14; freshness gate=2026-09-14. Revalidate before any current-price claim.
How fast is Gemini 3.5 Flash Lite?
Tokens / sec
162
TTFT
240 ms
Rank
#7 of 31
$ / M ÷ t/s
$0.0052
Measured with 5 runs on a fixed prompt — see the full methodology.
How much does Gemini 3.5 Flash Lite cost at scale?
| Tokens / month | Est. cost (blended 3:1) |
|---|---|
| 100,000 | $0.09 |
| 1,000,000 | $0.85 |
| 10,000,000 | $8.50 |
| 100,000,000 | $85.00 |
How does Gemini 3.5 Flash Lite compare with other models?
Gemini 2.5 Flash Lite — $0.18/MGemini 3.1 Flash Lite — $0.56/MGemini 2.5 Flash — $0.85/MGemini 3.7 Flash — $1.50/MGemini 3.1 Flash — $1.69/MGemini 2.5 Flash — $0.85/MMistral Large 3 — $0.75/MGLM-5.1 — $1.00/M
What is Gemini 3.5 Flash Lite best for?
What should you explore next for Gemini 3.5 Flash Lite?
Looking for a cheaper option?
GPT-6 Luna is 76.5% cheaper — a config migration. See all 8 alternatives to Gemini 3.5 Flash Lite →
Which Gemini 3.5 Flash Lite head-to-head comparisons are available?
What are common questions about Gemini 3.5 Flash Lite?
Is Gemini 3.5 Flash Lite cheaper than Gemini 2.5 Flash?
Gemini 3.5 Flash Lite costs $0.85/M blended tokens, Gemini 2.5 Flash costs $0.85/M — Gemini 2.5 Flash is cheaper.
How much does 1 million tokens cost with Gemini 3.5 Flash Lite?
At a 3:1 input:output ratio, 1 million blended tokens costs approximately $0.85. Pure input costs $0.30/M; pure output costs $2.50/M.
What does Gemini 3.5 Flash Lite cost at high volume?
At 100 million blended tokens a month, Gemini 3.5 Flash Lite costs approximately $85.00. See the cost-at-scale table below for other volumes.