← Model list

Gemini 3.5 Flash Lite

google·google/gemini-3.5-flash-lite·GA·Closed·gemini-flash-lite series·NEW

Fast Gemini model balancing multimodal reasoning, tool use, and cost

At a glance
Official price$0.30 / $2.50 per 1M
Cache read $0.03 · Vertex
Lowest paid$0.27 / $2.25
Requesty Gateway · 1.4× spread
Context1,048,576
⚠ Providers report 1,000,000–1,048,576; the table below is authoritative
Output limit65,536
Capabilities
ReasoningTool useStructured outputTemperatureAttachments
Modalities
TextImageAudioPDFVideo
Knowledge cutoff2026-03
Released / updated2026-07-21 / 2026-07-21

Quality & performanceArtificial Analysis · Intelligence Index v4.1

Intelligence37.4
Value49
Coding49.3
Agentic27.2
Output speed332 tok/s
TTFT9.76 s
Cost per task$0.0965
Value formulaIQ 37.4 ÷ min blended $0.765 = 49

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

Available at 20 providers20 with public prices

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
RequestyGateway$0.27$2.25$0.0271,048,57665,535
NanoGPTGateway$0.30$2.50$0.03$0.0831,048,57665,536
VertexOfficialFirst-party$0.30$2.50$0.031,048,57665,536
GoogleOfficialFirst-party$0.30$2.50$0.031,048,57665,536
ImpossiblGateway$0.30$2.50$0.031,048,57665,536
OpenRouterGateway$0.30$2.50$0.03$0.0831,048,57665,536
CrossModelGateway$0.30$2.50$0.03$0.301,048,57665,536
Merge GatewayGateway$0.30$2.50$0.031,048,57665,536
OfoxGateway$0.30$2.50$0.03$0.0831,048,57665,536
Neon
gemini-3-5-flash-lite
Cloud$0.30$2.50$0.031,048,57665,536

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.

Your usage cost

1Requesty$137.34
2NanoGPT$152.60
3Vertex · Official$152.60
4Google · Official$152.60
5Impossibl$152.60
6OpenRouter$152.60
Switch to Requesty to save $15.26/mo (10%). The gap is small, so staying on the official channel is fine.
Note: this is a gateway; verify availability and rate limits yourself.

Benchmark9 items

NameConditionsScoreMetricSource
SWE-Bench Pro54.2resolve rateSource ↗
Terminal-Benchharness: Terminus 2 · v2.154accuracySource ↗
MLE-Bench39.2average position scoreSource ↗
GDPval-AAvv21140EloSource ↗
OSWorld-Verified74success 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.

Reasoning control

effort = noneeffort = loweffort = mediumeffort = higheffort = maxbudget_tokenseffort = minimalToggle (on / off)

2 / 20 providers expose no reasoning control (reasoning_options: []).

Related models

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$2.50$02026-08-052026-08-212026-08-05 · Input list $0.302026-08-06 · Input list $0.302026-08-07 · Input list $0.302026-08-08 · Input list $0.302026-08-09 · Input list $0.302026-08-10 · Input list $0.302026-08-11 · Input list $0.302026-08-12 · Input list $0.302026-08-13 · Input list $0.302026-08-21 · Input list $0.302026-08-05 · Output list $2.502026-08-06 · Output list $2.502026-08-07 · Output list $2.502026-08-08 · Output list $2.502026-08-09 · Output list $2.502026-08-10 · Output list $2.502026-08-11 · Output list $2.502026-08-12 · Output list $2.502026-08-13 · Output list $2.502026-08-21 · Output list $2.502026-08-05 · Min blended $0.852026-08-06 · Min blended $0.852026-08-07 · Min blended $0.852026-08-08 · Min blended $0.852026-08-09 · Min blended $0.852026-08-10 · Min blended $0.852026-08-11 · Min blended $0.852026-08-12 · Min blended $0.852026-08-13 · Min blended $0.852026-08-21 · Min blended $0.765