API PRICES

Google · gemini-3.8-flash

Provider prices, cheapest first

Browse all models

Google · gemini-3.8-flash official price: input 0.75, output 3.75 USD per million tokens (Google, observed 2026-10-17). Cheapest inference provider: OpenRouter, input 0.825, output 4.125 USD per million tokens. 297 sites have comparable prices; 583 sites list this model.

Price ranges per million tokens

Official cash prices · Lowest 1.5 · median 1.5 · highest 1.5 · 1 quotes USD / per million tokens

Official price

ProviderInputOutputCache readCache writeUnitObservedConditions and source
Google0.753.750.075—USD / 1M tokens
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 provider prices at least 10% above official (1)

Inference providers

ProviderInputOutputCache readCache writeUnitObservedConditions and sourcevs official
OpenRouter · Aggregator0.8254.1250.08250.0416666666667USD / 1M tokens
Official source
Input 10% higher · Output 10% higher

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

Showing: Related variants。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. Back to the default ranking

Searching…

Browse all providers

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

Price range: lowest — · median — · highest — (0 quotes, USD credits per million total tokens)

sites have comparable prices297583 sites list this model; approximately 6 operators
Lowest input price—USD credits / 1M
Median of each provider’s lowest price—USD credits / 1M

Relays

Prices below are in site credit, not cash.

#ProviderPlan / conditionsInput ↑USD credits / 1MOutput USD credits / 1MCache readUSD credits / 1MBlendedUSD credits / 1MDetails
Related variants · not ranked · Recent price
—deepkey.topAsk or discussCollected:
Collected this cycle
View 3 plans
gemini
Name on site: gemini-3.8-flash-tiered
gemini - mixed group [machine translation]Original: gemini-混合分组

Related variant: gemini-3.8-flash-tiered (-tiered · tiered or extended pricing)

Operator pending verification
0.2251.1250.02250.45Full prices and sources
—deepkey.topAsk or discussCollected:
Collected this cycle
View 3 plans
gemini-anti
Name on site: gemini-3.8-flash-tiered
gemini - Antigravity group [machine translation]Original: gemini-反重力分组

Related variant: gemini-3.8-flash-tiered (-tiered · tiered or extended pricing)

Operator pending verification
0.2251.1250.02250.45Full prices and sources
—api.cloudpass.spaceAsk or discussCollected:
Collected this cycle
View 1 plans
Gemini
Name on site: gemini-3.8-flash-tiered
gemini

Related variant: gemini-3.8-flash-tiered (-tiered · tiered or extended pricing)

Operator pending verification
0.26251.31250.026250.525Full prices and sources
—newaicxy.xyzAsk or discussCollected:
Collected this cycle
View 1 plans
Antigravity [machine translation]Group on site: 反重力
Name on site: gemini-3.8-flash-tiered
Usage-based, low cache [machine translation]Original: 按量低缓

Related variant: gemini-3.8-flash-tiered (-tiered · tiered or extended pricing)

Operator pending verification
0.26251.31250.026250.525Full prices and sources
—onenode.spaceAsk or discussCollected:
Collected this cycle
View 2 plans
default
Name on site: gemini-3.8-flash-tiered
Default group [machine translation]Original: 默认分组

Related variant: gemini-3.8-flash-tiered (-tiered · tiered or extended pricing)

Operator pending verification
0.31.2—0.525Full prices and sources
—onenode.spaceAsk or discussCollected:
Collected this cycle
View 2 plans
vip
Name on site: gemini-3.8-flash-tiered
vip group [machine translation]Original: vip分组

Related variant: gemini-3.8-flash-tiered (-tiered · tiered or extended pricing)

Operator pending verification
0.31.2—0.525Full prices and sources
—api.manbeihu.topAsk or discussCollected:
Collected this cycle
View 1 plans
gemini
Name on site: gemini-3.8-flash-tiered
gemini

Related variant: gemini-3.8-flash-tiered (-tiered · tiered or extended pricing)

Operator pending verification
0.31.5—0.6Full prices and sources
—deepkey.topAsk or discussCollected:
Collected this cycle
View 3 plans
gemini-cli
Name on site: gemini-3.8-flash-tiered
gemini-cli group-anti+cli mixed to maintain stability [machine translation]Original: gemini-cli分组-由anti+cli混保持稳定性

Related variant: gemini-3.8-flash-tiered (-tiered · tiered or extended pricing)

Operator pending verification
0.33751.68750.033750.675Full prices and sources
—sg.uiuiapi.comAsk or discussCollected:
Collected this cycle
View 4 plans
default
Name on site: gemini-3.8-flash-maxthinking
⭐ Default (mixed channels) | Azure + official models [machine translation]Original: ⭐ 默认(混渠道)| Azure + 官模型

Related variant: gemini-3.8-flash-maxthinking (-maxthinking · thinking edition)

Operator pending verification
0.753.75—1.5Full prices and sources
—sg.uiuiapi.comAsk or discussCollected:
Collected this cycle
View 4 plans
default
Name on site: gemini-3.8-flash-thinking
⭐ Default (mixed channels) | Azure + official models [machine translation]Original: ⭐ 默认(混渠道)| Azure + 官模型

Related variant: gemini-3.8-flash-thinking (-thinking · thinking edition)

Operator pending verification
0.753.75—1.5Full prices and sources
—sg.uiuiapi.comAsk or discussCollected:
Collected this cycle
View 4 plans
🔥Gemini-SVIP
Name on site: gemini-3.8-flash-maxthinking
Gemini-premium-quality channel | *3 [machine translation]Original: Gemini-优质通道 | *3

Related variant: gemini-3.8-flash-maxthinking (-maxthinking · thinking edition)

Operator pending verification
2.2511.25—4.5Full prices and sources
—sg.uiuiapi.comAsk or discussCollected:
Collected this cycle
View 4 plans
🔥Gemini-SVIP
Name on site: gemini-3.8-flash-thinking
Gemini-premium-quality channel | *3 [machine translation]Original: Gemini-优质通道 | *3

Related variant: gemini-3.8-flash-thinking (-thinking · thinking edition)

Operator pending verification
2.2511.25—4.5Full prices and sources
How this ranking works

All per-token prices: 97,455 prices from 871 sites (about 765 companies). 89,631 are ranked, from 861 sites (about 755 companies); 7,824 more are listed separately and not ranked. Prices collected up to 2026-10-17.

This model has 2304 recorded prices; 758 can be compared directly (717 ranked, 41 listed separately). Not comparable yet: price not parsed yet 742, tiered by rules (see Tiered prices) 329, billed per request or another unit 200, ratio looks unset 128, display unit not confirmed 86, scope of the official doc price not confirmed 48

12 recent · 0 stale (older than 10 days, or not updated by this refresh) · 0 unverified timestamps. No recent prices to summarize in this group. 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

Sources not accepted this cycle and reasons

FAQ

Which API is cheapest for Google · gemini-3.8-flash?

No valid quotes within 10 days. Older quotes are listed as reference prices.

What is the official price for Google · gemini-3.8-flash?

Input 0.75, output 3.75 USD per million tokens, checked 2026-10-17. Lowest inference provider: OpenRouter, input 0.825, output 4.125 USD per million tokens. Input 10% higher than official.

How do I use Google · gemini-3.8-flash in Claude Code or Codex?

Install Grandet Skill, then say "Connect the cheapest Google · gemini-3.8-flash API to Claude Code for me". Install Skill →