LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Gemini 2.5 Flash-Lite

google·google/gemini-2.5-flash-lite·GA·Closed·gemini-flash-lite series
Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents

Specs & pricing

Input / output per 1M tokens
Official price·Google
$0.10 / $0.40
Blended $0.18 · Cache read $0.01
Lowest paid·LLMTRGateway
$0.10 / $0.10
Blended $0.10 · 1.4× spread
Context
1,048,576
Output limit
65,536
Knowledge cutoff
2025-01
Released / updated
2025-06-17 / 2025-06-17
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImageAudioVideoPDF

Gemini 2.5 Flash-Lite by google is offered by 23 providers on this page. Public prices are shown for 21 of them. Its official list price is $0.10 per 1M input tokens and $0.40 per 1M output tokens. The lowest paid channel is LLMTR at $0.10 / $0.10 per 1M, about 1.7× below the list price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it.

Median output speed is 283 tokens per second, with 0.31s to the first token.

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 2025-01.

Quality & performanceArtificial Analysis · Intelligence Index v5 · rep. tier Non-reasoning

Intelligence—
Value—
Output speed283 tok/s
TTFT0.31 s

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

Available at 23 providers21 with public prices

  • ProviderInput / Output
  • LLMTRGateway
    $0.10 / $0.10
    Context 1,048,576Output limit 65,536deprecated
  • PoeGateway
    $0.07 / $0.28
    Context 1,024,000 ⚠Output limit 64,000deprecated
  • Jiekou.AIGateway
    $0.095 / $0.38
    Cache read $0.0095Context 1,048,576Output limit 65,535
  • VertexOfficialCloud
    $0.10 / $0.40
    Cache read $0.01Context 1,048,576Output limit 65,536deprecated
  • GoogleOfficialFirst-party
    $0.10 / $0.40
    Cache read $0.01Context 1,048,576Output limit 65,536
  • CrossModelGateway
    $0.10 / $0.40
    Cache read $0.01Context 1,048,576Output limit 65,536
  • RequestyGateway
    gemini-2.5-flash-lite@eu
    $0.10 / $0.40
    Cache read $0.01Context 1,048,576Output limit 65,535
  • NanoGPTGateway
    $0.10 / $0.40
    Cache read $0.01Context 1,048,576Output limit 65,536
  • NEAR AI CloudGateway
    $0.10 / $0.40
    Cache read $0.01Context 1,048,576Output limit 65,536
  • Merge GatewayGateway
    $0.10 / $0.40
    Cache read $0.01Context 1,000,000 ⚠Output limit 65,536
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
LLMTRGateway$0.10$0.10——1,048,57665,536deprecated
PoeGateway$0.07$0.28——1,024,000 ⚠64,000deprecated
Jiekou.AIGateway$0.095$0.38$0.0095—1,048,57665,535
VertexOfficialCloud$0.10$0.40$0.01—1,048,57665,536deprecated
GoogleOfficialFirst-party$0.10$0.40$0.01—1,048,57665,536
CrossModelGateway$0.10$0.40$0.01$0.101,048,57665,536
Requesty
gemini-2.5-flash-lite@eu
Gateway$0.10$0.40$0.01$0.181,048,57665,535
NanoGPTGateway$0.10$0.40$0.01—1,048,57665,536
NEAR AI CloudGateway$0.10$0.40$0.01—1,048,57665,536
Merge GatewayGateway$0.10$0.40$0.01—1,000,000 ⚠65,536

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

budget_tokens ≥ 512 ≤ 24,576effort = noneeffort = loweffort = mediumeffort = highToggle (on / off)effort = minimaleffort = max

3 / 23 providers expose no reasoning control (reasoning_options: []).

Audio token pricing11 of 23 providers

ProviderAudio inAudio out
Vertex$0.303.0×—
Google$0.303.0×—
NEAR AI Cloud$0.303.0×—
Merge Gateway$0.303.0×—
OpenRouter$0.303.0×—
SAP AI Core$0.303.0×—
AIHubMix$0.303.0×—
ZenMux$0.303.0×—
Ofox$0.303.0×—
OrcaRouter$0.303.0×—
Impossibl$0.303.0×—

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
1LLMTR$25.00
2Jiekou.AI$27.74
3Poe$28.00
4Vertex · Official$29.20
5Google · Official$29.20
6CrossModel$29.20
Switch to LLMTR to save $4.20/mo (14%). The gap is small, so staying on the official channel is fine.
Note: this is a gateway; verify availability and rate limits yourself.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$0.40$02026-08-052026-11-18
2026-11-18Input list $0.10Output list $0.40Min blended $0.10

Benchmark3 items

NameConditionsScoreMetricSource
Artificial Analysis Coding Index—9.5indexSource ↗
SciCode—19.3percent correctSource ↗
Terminal-Bench Hard—4.5success rateSource ↗

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

Artificial Analysis arenas1 arenas

Text to speech1082±11#57 of 106

Elo from human preference matchups run by Artificial Analysis. Each arena is anchored separately, so Elo is only comparable within one arena, against the other models on that board, and the 95% confidence interval (shown as ±) indicates how much of a gap is noise. Rank is over the whole arena, including models not listed here.

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 / $2.50Nemotron 3 Ultra 550B A55Bcheaper alternative$0 / $0Nemotron 3.5 Super VL 120B A12Bcheaper alternative$0 / $0reBeam 1.0 501B A23Bcheaper alternative$0 / $0Qwen3.7 Flashcheaper alternative$0.03 / $0.13Nano Bananasame lab$0.30 / $2.50Gemini 2.5 Prosame lab$1.25 / $10.00
Data partly from models.dev (MIT) · Google official docs ↗