LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Gemini 3.5 Flash Lite

google·google/gemini-3.5-flash-lite·GA·Closed·gemini-flash-lite series
Fast Gemini model balancing multimodal reasoning, tool use, and cost

Specs & pricing

Input / output per 1M tokens
Official price·Google
$0.30 / $2.50
Blended $0.85 · Cache read $0.03
Lowest paid·UplinkSwitchGateway
$0.23 / $1.88
Blended $0.64 · 1.9× spread
Context
1,048,576
Output limit
65,536
Knowledge cutoff
2026-03
Released / updated
2026-07-21 / 2026-07-21
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImageAudioVideoPDF

Gemini 3.5 Flash Lite by google is offered by 38 providers on this page. Public prices are shown for 37 of them. Its official list price is $0.30 per 1M input tokens and $2.50 per 1M output tokens. The lowest paid channel is UplinkSwitch at $0.225 / $1.88 per 1M, about 1.3× below the list price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it.

Artificial Analysis rates it 11.7 on the Intelligence Index, with 23.9 for Legal, its strongest domain. Against its lowest blended price of $0.637 per 1M, that is roughly 18 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 402 tokens per second, with 7.73s to the first token. Running one task of the Artificial Analysis suite costs about $0.6929, which reflects how many tokens its reasoning consumes rather than the unit price alone.

The context window is 1,048,576 tokens at the reference host, but hosts report different limits, from 1,000,000 to 1,048,576, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. Accepted input modalities are Text, Image, Audio, Video, and PDF. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2026-03.

Quality & performanceArtificial Analysis · Intelligence Index v5

Intelligence11.7
Value18
Engineering21.2
Finance & Accounting23.3
Legal23.9
Healthcare & Medical20.5
Strategy & Ops20.7
Economics21.9
Output speed402 tok/s
TTFT7.73 s
Cost per task$0.69
Value formulaIQ 11.7 ÷ min blended $0.637 = 18

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 38 providers37 with public prices

  • ProviderInput / Output
  • UplinkSwitchGateway
    $0.23 / $1.88
    Cache read $0.023Context 1,048,576Output limit 65,536
  • AIHubMixGateway
    $0.30 / $2.50
    Cache read $0.03Context 1,048,576Output limit 65,536
  • VertexOfficialCloud
    $0.30 / $2.50
    Cache read $0.03Context 1,048,576Output limit 65,536
  • GoogleOfficialFirst-party
    $0.30 / $2.50
    Cache read $0.03Context 1,048,576Output limit 65,536
  • CrossModelGateway
    $0.30 / $2.50
    Cache read $0.03Context 1,048,576Output limit 65,536
  • LLM GatewayGateway
    $0.30 / $2.50
    Cache read $0.03Context 1,048,576Output limit 65,536
  • LLM GatewayGateway
    $0.30 / $2.50
    Cache read $0.03Context 1,048,576Output limit 65,536
  • CommandCodeGateway
    $0.30 / $2.50
    Cache read $0.03Context 1,000,000 ⚠Output limit 65,536
  • 302.AIGateway
    $0.30 / $2.50
    Cache read $0.03Context 1,048,576Output limit 65,536
  • RequestyGateway
    $0.30 / $2.50
    Cache read $0.03Context 1,048,576Output limit 65,535
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
UplinkSwitchGateway$0.23$1.88$0.023—1,048,57665,536
AIHubMixGateway$0.30$2.50$0.03—1,048,57665,536
VertexOfficialCloud$0.30$2.50$0.03—1,048,57665,536
GoogleOfficialFirst-party$0.30$2.50$0.03—1,048,57665,536
CrossModelGateway$0.30$2.50$0.03$0.301,048,57665,536
LLM GatewayGateway$0.30$2.50$0.03$0.0831,048,57665,536
LLM GatewayGateway$0.30$2.50$0.03$0.0831,048,57665,536
CommandCodeGateway$0.30$2.50$0.03—1,000,000 ⚠65,536
302.AIGateway$0.30$2.50$0.03—1,048,57665,536
RequestyGateway$0.30$2.50$0.03—1,048,57665,535

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Reasoning control

effort = minimaleffort = loweffort = mediumeffort = highToggle (on / off)effort = noneeffort = max

Interleaved thinking (reasoning between tool calls) is declared by 2 of 38 providers.

3 / 38 providers expose no reasoning control (reasoning_options: []).

Audio token pricing7 of 38 providers

ProviderAudio inAudio out
AIHubMix$0.301.0×—
OpenRouter$0.301.0×—
Eden AI$0.301.0×—
Eden AI$0.301.0×—
Ofox$0.301.0×—
Eden AI$0.331.0×—
Eden AI$0.331.0×—

Audio tokens are priced on a separate scale from text tokens, so these are not comparable with the text prices above. The multiplier compares each price with the same provider's text price for the same direction.

Your usage cost

Common scenarios
1UplinkSwitch$114.45
2AIHubMix$152.60
3Vertex · Official$152.60
4Google · Official$152.60
5CrossModel$152.60
6LLM Gateway$152.60
Switch to UplinkSwitch to save $38.15/mo (25%)
Note: this is a gateway; verify availability and rate limits yourself.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$2.50$02026-08-052026-11-18
2026-11-18Input list $0.30Output list $2.50Min blended $0.64

Benchmark9 items

NameConditionsScoreMetricSource
SWE-Bench Pro—54.2resolve rateSource ↗
Terminal-Benchharness: Terminus 2 · v2.154accuracySource ↗
MLE-Bench—39.2average position scoreSource ↗
GDPval-AAvv21140EloSource ↗
OSWorld-Verified—74success rateSource ↗
CharXiv Reasoningvariant: no tools74.5accuracySource ↗
CharXiv Reasoningvariant: with tools76.5accuracySource ↗
GDM-MRCRvariant: 128k average, 8-needle · vv272.2accuracySource ↗
GDM-MRCRvariant: 1M pointwise, 8-needle · vv221.3accuracySource ↗

The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.

Artificial Analysis evaluations23 items

GPQA Diamond83.8%
Humanity's Last Exam18.8%
HLE-Diamond9.9%
MMMU-Pro79.0%
CritPt0.0%
CritPt v2 Hard3.5%
SciCode41.3%
FrontierCode 2.06.0%
Terminal-Bench 2.153.6%
Terminal-Bench 4.01.0%
Terminal-Bench-Science0.0%
τ³-Bench Banking17.5%
AutomationBench-AA25.0%
EnterpriseOps-Gym-AA42.4%
AA-Briefcase651
GDPval-AA995
GDP.pdf13.6%
AA-LCR76.0%
MLCR-AA10.6%
AA-Omniscience Index6.9
AA-Omniscience Accuracy26.5%
AA-Omniscience Non-Hallucination73.3%
Harvey LAB-AA0.0%

Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and scale (percent correct, points or an index), so rows are not comparable with one another.

Related models

Gemini 3.8 Flash Lite TTSsame series—Gemini Flash-Lite Latestsame series$0.30 / $2.50Nano Banana 2 Litesame series$0.25 / $1.50GLM-5.3-Flashcheaper alternative$0.15 / $0.50DeepSeek V4.1 Flash 1017cheaper alternative$0.15 / $0.60GPT-5.6 Lunacheaper alternative$0.20 / $1.20Claude Haiku 5.5cheaper alternative$0.10 / $0.50Gemini 3.5 Flashsame lab$1.50 / $9.00Gemini 3.6 Flashsame lab$0.75 / $3.75
Data partly from models.dev (MIT) · Google official docs ↗