← 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

At a glance
Official price$0.10 / $0.40 per 1M
Cache read $0.01 · Vertex
Lowest paid$0.10 / $0.10
LLMTR Gateway · 1.4× spread
1 more $0 channels
Context1,048,576
⚠ Providers report 1,000,000–1,048,756; the table below is authoritative
Output limit65,536
Capabilities
ReasoningTool useStructured outputTemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
TextImageAudioVideoPDF
Knowledge cutoff2025-01
Released / updated2025-06-17 / 2025-06-17

Quality & performanceArtificial Analysis · Intelligence Index v4.1 · rep. tier Reasoning

Intelligence11.4
Value114
Coding
Agentic
Output speed312 tok/s
TTFT24.64 s
Value formulaIQ 11.4 ÷ min blended $0.100 = 114
Reasoning tier → intelligence / speed (higher tier = stronger but slower)
Non-reasoningIQ 6.7 · 232 tok/s
ReasoningIQ 11.4 · 312 tok/s

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

Available at 21 providers18 with public prices · 1 free

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Kenari
gemini-2-5-flash-lite
GatewayFree1,048,57665,536
LLMTRGateway$0.10$0.101,048,57665,536
PoeGateway$0.07$0.281,024,00064,000
Jiekou.AIGateway$0.09$0.361,048,57665,535
OrcaRouterGateway$0.10$0.40$0.011,048,57665,536
NanoGPTGateway$0.10$0.40$0.011,048,75665,536
VertexOfficialFirst-party$0.10$0.40$0.011,048,57665,536
GoogleOfficialFirst-party$0.10$0.40$0.011,048,57665,536
ImpossiblGateway$0.10$0.40$0.011,048,57665,536
OpenRouterGateway$0.10$0.40$0.01$0.0831,048,57665,535

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.

Your usage cost

1LLMTR$25.00
2Poe$28.00
3OrcaRouter$29.20
4NanoGPT$29.20
5Vertex · Official$29.20
6Google · Official$29.20

1 more channels offer $0 (Kenari); free tiers usually have rate limits and no SLA, excluded from ranking.

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.

Benchmark3 items

NameConditionsScoreMetricSource
Artificial Analysis Coding Index9.5indexSource ↗
SciCode19.3percent correctSource ↗
Terminal-Bench Hard4.5success rateSource ↗

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

Reasoning control

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

5 / 21 providers expose no reasoning control (reasoning_options: []).

Related models

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$0.40$02026-08-052026-08-172026-08-05 · Input list $0.102026-08-06 · Input list $0.102026-08-07 · Input list $0.102026-08-08 · Input list $0.102026-08-09 · Input list $0.102026-08-10 · Input list $0.102026-08-11 · Input list $0.102026-08-12 · Input list $0.102026-08-13 · Input list $0.102026-08-17 · Input list $0.102026-08-05 · Output list $0.402026-08-06 · Output list $0.402026-08-07 · Output list $0.402026-08-08 · Output list $0.402026-08-09 · Output list $0.402026-08-10 · Output list $0.402026-08-11 · Output list $0.402026-08-12 · Output list $0.402026-08-13 · Output list $0.402026-08-17 · Output list $0.402026-08-05 · Min blended $0.1222026-08-06 · Min blended $0.1222026-08-07 · Min blended $0.1222026-08-08 · Min blended $0.1222026-08-09 · Min blended $0.1222026-08-10 · Min blended $0.1222026-08-11 · Min blended $0.1222026-08-12 · Min blended $0.1222026-08-13 · Min blended $0.1222026-08-17 · Min blended $0.10