LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Gemini 3.1 Flash Lite

google·google/gemini-3.1-flash-lite·GA·Closed·gemini-flash-lite series
Low-latency Gemini model for high-volume multimodal and agent workloads

Specs & pricing

Input / output per 1M tokens
Official price·Google
$0.25 / $1.50
Blended $0.56 · Cache read $0.025
Lowest paid·VertexCloud
$0.25 / $1.50
Blended $0.56 · 1.1× spread
Context
1,048,576
Output limit
65,536
Knowledge cutoff
2025-01
Released / updated
2026-05-07 / 2026-05-07
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
Modalities
TextImageVideoAudioPDF

Gemini 3.1 Flash Lite by google is offered by 31 providers on this page. Its official list price is $0.25 per 1M input tokens and $1.50 per 1M output tokens. No paid channel is priced below the official list price.

Artificial Analysis rates it 6.2 on the Intelligence Index, with 14.7 for Legal, its strongest domain. Against its lowest blended price of $0.563 per 1M, that is roughly 11 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 322 tokens per second, with 5.04s to the first token. Running one task of the Artificial Analysis suite costs about $0.1945, 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, Video, Audio, and PDF. Its training knowledge cuts off at 2025-01.

Quality & performanceArtificial Analysis · Intelligence Index v5

Intelligence6.2
Value11
Engineering14.6
Finance & Accounting12.1
Legal14.7
Healthcare & Medical10.6
Strategy & Ops10.5
Economics13.7
Output speed322 tok/s
TTFT5.04 s
Cost per task$0.19
Value formulaIQ 6.2 ÷ min blended $0.563 = 11

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

Available at 31 providers31 with public prices

  • ProviderInput / Output
  • VertexOfficialCloud
    $0.25 / $1.50
    Cache read $0.025Context 1,048,576Output limit 65,536
  • GoogleOfficialFirst-party
    $0.25 / $1.50
    Cache read $0.025Context 1,048,576Output limit 65,536
  • LLM GatewayGateway
    $0.25 / $1.50
    Cache read $0.025Context 1,048,576Output limit 65,536
  • LLM GatewayGateway
    $0.25 / $1.50
    Cache read $0.025Context 1,048,576Output limit 65,536
  • CommandCodeGateway
    $0.25 / $1.50
    Cache read $0.03Context 1,000,000 ⚠Output limit 65,536
  • 302.AIGateway
    $0.25 / $1.50
    Cache read $0.03Context 1,048,576Output limit 65,536
  • RequestyGateway
    $0.25 / $1.50
    Cache read $0.025Context 1,048,576Output limit 65,535
  • NanoGPTGateway
    $0.25 / $1.50
    Cache read $0.025Context 1,048,576Output limit 65,536
  • DevPass (LLM Gateway)Gateway
    $0.25 / $1.50
    Cache read $0.025Context 1,048,576Output limit 65,536
  • NEAR AI CloudGateway
    $0.25 / $1.50
    Cache read $0.025Context 1,048,576Output limit 65,536
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
VertexOfficialCloud$0.25$1.50$0.025—1,048,57665,536
GoogleOfficialFirst-party$0.25$1.50$0.025—1,048,57665,536
LLM GatewayGateway$0.25$1.50$0.025$0.0831,048,57665,536
LLM GatewayGateway$0.25$1.50$0.025$0.0831,048,57665,536
CommandCodeGateway$0.25$1.50$0.03—1,000,000 ⚠65,536
302.AIGateway$0.25$1.50$0.03—1,048,57665,536
RequestyGateway$0.25$1.50$0.025$0.0831,048,57665,535
NanoGPTGateway$0.25$1.50$0.025$0.0831,048,57665,536
DevPass (LLM Gateway)Gateway$0.25$1.50$0.025$0.0831,048,57665,536
NEAR AI CloudGateway$0.25$1.50$0.025—1,048,57665,536

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.

Reasoning control

effort = minimaleffort = loweffort = mediumeffort = higheffort = noneeffort = maxToggle (on / off)

2 / 31 providers expose no reasoning control (reasoning_options: []).

Audio token pricing17 of 31 providers

ProviderAudio inAudio out
Vertex$0.502.0×—
Google$0.502.0×—
LLM Gateway$0.502.0×—
LLM Gateway$0.502.0×—
NEAR AI Cloud$0.502.0×—
Merge Gateway$0.502.0×—
OpenRouter$0.502.0×—
SAP AI Core$0.502.0×—
AIHubMix$0.502.0×—
ZenMux$0.502.0×—
Eden AI$0.502.0×—
Eden AI$0.502.0×—
Ofox$0.502.0×—
OrcaRouter$0.502.0×—
Impossibl$0.502.0×—
Eden AI$0.552.0×—
Eden AI$0.552.0×—

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
1Vertex · Official$98.00
2Google · Official$98.00
3LLM Gateway$98.00
4LLM Gateway$98.00
5Requesty$98.00
6NanoGPT$98.00
The cheapest paid channel is official.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$1.50$02026-08-052026-11-18
2026-11-18Input list $0.25Output list $1.50Min blended $0.56

Related models

Gemini 3.8 Flash Lite TTSsame series—Gemini 3.5 Flash Litesame series$0.30 / $2.50Gemini Flash-Lite Latestsame series$0.30 / $2.50GLM-5.3-Flashcheaper alternative$0.15 / $0.50DeepSeek V4.1 Flash 1017cheaper alternative$0.15 / $0.60Claude Haiku 5.5cheaper alternative$0.10 / $0.50GPT-6 Lunacheaper alternative$0.10 / $0.50Nano Banana 2 Previewsame lab—Nano Banana 2 Litesame lab$0.25 / $1.50
Data partly from models.dev (MIT) · Google official docs ↗