API PRICES

Google · gemini-2.5-flash-lite

Provider prices, cheapest first

Google · gemini-2.5-flash-lite official price: input 0.10, output 0.40 USD per million tokens (Google, observed 2026-10-16). Cheapest inference provider: OpenRouter, input 0.1, output 0.4 USD per million tokens. Relays have only older quotes; the lowest is api.guaiyun.cc, group "gemini" 0.04375 USD_CREDIT per million total tokens (credit price, not cash, observed 2026-10-10). 150 sites have comparable prices; 277 sites list this model.Relay blended price uses 75% input and 25% output.

Official price

Provider	Input	Output	Cache read	Cache write	Unit	Observed	Conditions and source
Google	0.10	0.40	0.01	—	USD / 1M tokens	2026-10-16	Official source

Official prices are the vendor's cash prices. Inference providers also list cash prices and can be compared directly. Relays list prices in site credit; what you actually pay depends on each site's top-up rate, so they cannot be compared with official prices directly.

Inference providers

Provider	Input	Output	Cache read	Cache write	Unit	Observed	Conditions and source	vs official
OpenRouter · Aggregator	0.1	0.4	0.01	0.0833333333333333	USD / 1M tokens	2026-10-16	Official source	Input 0% · Output 0%

Unit: USD credits per 1M tokens. These are site-credit prices; actual cost depends on each site’s top-up rate.

Find a provider by name or address

Filtering by provider: api.guaiyun.cc

Searching…

Browse all providers

Blended price = input × 75% + output × 25%, without cache.

sites have comparable prices150277 sites list this model; approximately 1 operators

Older lowest input price (reference)0.025USD credits / 1M

Median of each provider’s lowest price0.025USD credits / 1M

Relays

Prices below are in site credit, not cash.

#	Provider	Plan / conditions	Input ↑USD credits / 1M	Output USD credits / 1M	Cache readUSD credits / 1M	BlendedUSD credits / 1M	Details
Older price
01	api.guaiyun.ccAsk or discussCollected: 10 Oct 2026, 07:18 UTC View 4 plans	gemini Usable with Gemini CLI, low cache, use with caution [machine translation]Original: 可用于Gemini CLI，缓存低慎重	0.025	0.1	0.0025	0.04375	Full prices and sources
01	api.guaiyun.ccAsk or discussCollected: 10 Oct 2026, 07:18 UTC View 4 plans	gemini-cli - Antigravity [machine translation]Group on site: gemini-cli-反重力	0.025	0.1	0.0025	0.04375	Full prices and sources
03	api.guaiyun.ccAsk or discussCollected: 10 Oct 2026, 07:18 UTC View 4 plans	gemini stable text [machine translation]Group on site: gemini稳定文字 [Fidelity direct connection] official models, aistudio and vertex mixed resources [machine translation]Original: [保真直连】官方模型aistudio和vertex混合资源	0.15	0.6	0.015	0.2625	Full prices and sources
03	api.guaiyun.ccAsk or discussCollected: 10 Oct 2026, 07:18 UTC View 4 plans	gemini stable image generation [machine translation]Group on site: gemini稳定生图 [Fidelity direct connection] official models, aistudio and vertex mixed resources [machine translation]Original: [保真直连】官方模型aistudio和vertex混合资源	0.15	0.6	0.015	0.2625	Full prices and sources

Special groups · 4 rows · not ranked

These plans are marked as test, internal, disabled, gated by top-up or membership, or have a near-zero ratio. They may not be purchasable or stable, so they are listed separately and left out of the ranking and statistics.

test or debug group: 4 rows

api.tenzen.ai · Test group [machine translation]Group on site: 测试分组 · gemini-2.5-flash-lite · Input 0.1 / Output 0.4 USD credits / 1M
tenzen.ai · Test group [machine translation]Group on site: 测试分组 · gemini-2.5-flash-lite · Input 0.1 / Output 0.4 USD credits / 1M
www.amutes.com · vertex-test · gemini-2.5-flash-lite · Input 0.17 / Output 0.68 USD credits / 1M
hk.apitoken.ai · sandbox · gemini-2.5-flash-lite · Input 0.3 / Output 1.2 USD credits / 1M

View all 4 rows →

Related variants · 25 rows · not ranked

These are special editions of the model (thinking, max, search, batch, long context, free, etc.). They are priced differently from the base model, so they are listed separately and not ranked. Names that only add an effort level such as low, high or nothinking are compared with the base model.

gemini-2.5-flash-lite-thinking (-thinking · thinking edition): 23 rows
[OO]gemini-2.5-flash-lite-search (-search · search or tool): 1 rows
[OO]gemini-2.5-flash-lite-thinking (-thinking · thinking edition): 1 rows

api.xhuoai.com · default · gemini-2.5-flash-lite-thinking · Input 0.1 / Output 0.4 USD credits / 1M
api.xistree.hk · default · gemini-2.5-flash-lite-thinking · Input 0.1 / Output 0.4 USD credits / 1M
sg.uiuiapi.com · default · gemini-2.5-flash-lite-thinking · Input 0.1 / Output 0.4 USD credits / 1M
hohoapi.com · default · gemini-2.5-flash-lite-thinking · Input 0.13 / Output 0.52 USD credits / 1M
yinli.one · Gemini-low price-90% stability [machine translation]Group on site: Gemini-低价-90%稳定性 · gemini-2.5-flash-lite-thinking · Input 0.15 / Output 0.6 USD credits / 1M
hohoapi.com · gemini · gemini-2.5-flash-lite-thinking · Input 0.195 / Output 0.78 USD credits / 1M
api.nekoapi.com · gemini-vip · gemini-2.5-flash-lite-thinking · Input 0.25 / Output 1 USD credits / 1M
nekoapi.com · gemini-vip · gemini-2.5-flash-lite-thinking · Input 0.25 / Output 1 USD credits / 1M
yinli.one · Gemini-mid price-95% stability [machine translation]Group on site: Gemini-中价-95%稳定性 · gemini-2.5-flash-lite-thinking · Input 0.3 / Output 1.2 USD credits / 1M
api.xhuoai.com · Enterprise channel [machine translation]Group on site: 企业渠道 · gemini-2.5-flash-lite-thinking · Input 0.4 / Output 1.6 USD credits / 1M

View all 25 rows →

How this ranking works

All per-token prices: 96,427 prices from 839 sites (about 733 companies). 88,950 are ranked, from 826 sites (about 720 companies); 7,477 more are listed separately and not ranked. Prices collected up to 2026-10-10.

This model has 873 recorded prices; 351 can be compared directly (310 ranked, 41 listed separately). Not comparable yet: price not parsed yet 202, new price under review; showing the previous one 173, ratio looks unset 57, tiered by rules (see Tiered prices) 37, display unit not confirmed 30, scope of the official doc price not confirmed 12, billed per request or another unit 11

0 recent · 4 stale (older than 7 days, or not updated by this refresh) · 0 unverified timestamps. Only older prices are available, so the statistics are for reference only. 0 zero-valued pairs are separately unverified, without proof of free eligibility. Timing does not verify payment, upstream identity or quality.

Prices are converted to site credits using each site’s published ratio. What you actually pay depends on its top-up rate. Input, output and cache prices in each row come from the same plan. Several sites run by the same company take one place in the ranking: its cheapest plan, with the other sites listed under it. We judge “same company” by identical prices, status pages or homepage code; this is not a legal finding. To see every site’s prices, choose “All plans” or filter by provider.

“Self-declared unofficial channel” means the plan name itself says “reverse-engineered” or similar. We have not verified their source or quality. Minimum and median only count regular plans.

Full methodology →

Switch model

Search modelsModel528 matches; choose and submit to view prices.