API PRICES
Google · gemini-2.5-pro
Provider prices, cheapest first
Price comparison
- Official (cash)
- Input 1.25 / output 10 USD/million tokensGoogle ·
- Lowest inference provider (cash)
- Input 1.25 / output 10 USD/million tokensDeepInfra ·
- Lowest relay (credit)
- 1.65 USD credit/million total tokensgo.sbgpt.site "无审核az-0.4倍率" ·
Official and inference-provider prices are cash; relay prices are site credit (USD credit or CNY credit), a different unit, compared separately. Relay prices are per million total tokens at 75% input and 25% output.
Google · gemini-2.5-pro official price: input 1.25, output 10 USD per million tokens (Google, observed 2026-10-17). Cheapest inference provider: DeepInfra, input 1.25, output 10 USD per million tokens. Cheapest relay: go.sbgpt.site, group "No moderation az-0.4x rate multiplier [machine translation] (on site: 无审核az-0.4倍率)" 1.65 USD_CREDIT per million total tokens (credit price, not cash, observed 2026-10-16). 155 sites have comparable prices; 329 sites list this model.Relay blended price uses 75% input and 25% output.
Price ranges per million tokens
Official cash prices · Lowest 3.4375 · median 4.5313 · highest 5.625 · 2 quotes USD / per million tokens
Inference provider cash prices · Lowest 3.4375 · median 3.4375 · highest 3.4375 · 2 quotes USD / per million tokens
Relay USD credit prices · Lowest 1.65 · median 2.0625 · highest 15.469 · 9 quotes USD / per million tokens, site credit
Official price
| Provider | Input | Output | Cache read | Cache write | Unit | Observed | Conditions and source |
|---|---|---|---|---|---|---|---|
| 1.25 | 10 | 0.125 | — | USD / 1M tokens | Official source | ||
| 2.5 | 15 | 0.25 | — | 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 providers
| Provider | Input | Output | Cache read | Cache write | Unit | Observed | Conditions and source | vs official |
|---|---|---|---|---|---|---|---|---|
| DeepInfra | 1.25 | 10 | — | — | USD / 1M tokens | Official source | ||
| OpenRouter · Aggregator | 1.25 | 10 | 0.125 | 0.375 | USD / 1M tokens | Official source |
Unit: USD credits per 1M tokens. These are site-credit prices; actual cost depends on each site’s top-up rate.
Price range: lowest 1.65 · median 2.0625 · highest 15.469 (9 quotes, USD credits per million total tokens)
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 |
|---|---|---|---|---|---|---|---|
| Recent price | |||||||
| 01 | go.sbgpt.siteAsk or discussCollected: Collected this cycle View 9 plans | az-3 az no moderation all models-0.48x rate multiplier [machine translation]Original: az无审核全模型-0.48倍率 Operator pending verification | 0.6 | 4.8 | — | 1.65Median price ÷ this price: 1.3× | Full prices and sources |
| 01 | go.sbgpt.siteAsk or discussCollected: Collected this cycle View 9 plans | No moderation az-0.4x rate multiplier [machine translation]Group on site: 无审核az-0.4倍率 No moderation AZ, no o1-0.48x rate multiplier [machine translation]Original: 无审核AZ无o1-0.48倍率 Operator pending verification | 0.6 | 4.8 | — | 1.65Median price ÷ this price: 1.3× | Full prices and sources |
| 03 | go.sbgpt.siteAsk or discussCollected: Collected this cycle View 9 plans | No moderation az-2 [machine translation]Group on site: 无审核az-2 No-moderation AZ, moderated o1-0.58x rate multiplier [machine translation]Original: 无审核AZ有审核o1-0.58倍率 Operator pending verification | 0.725 | 5.8 | — | 1.9938Median price ÷ this price: 1× | Full prices and sources |
| 04 | go.sbgpt.siteAsk or discussCollected: Collected this cycle View 9 plans | gemini all models [machine translation]Group on site: gemini全模型 Official gemini all models-0.6x rate multiplier [machine translation]Original: 官gemini全模型-0.6倍率 Operator pending verification | 0.75 | 6 | — | 2.0625Median price ÷ this price: 1× | Full prices and sources |
| 04 | go.sbgpt.siteAsk or discussCollected: Collected this cycle View 9 plans | No moderation AZ [machine translation]Group on site: 无审核AZ No moderation AZ-0.6x rate multiplier [machine translation]Original: 无审核AZ-0.6倍率 Operator pending verification | 0.75 | 6 | — | 2.0625Median price ÷ this price: 1× | Full prices and sources |
| 06 | go.sbgpt.siteAsk or discussCollected: Collected this cycle View 9 plans | default default-1 rate multiplier [machine translation]Original: default-1倍率 Operator pending verification | 1.25 | 10 | — | 3.4375Median price ÷ this price: 0.6× | Full prices and sources |
| 07 | go.sbgpt.siteAsk or discussCollected: Collected this cycle View 9 plans | az-12 az-12-1.2x rate multiplier [machine translation]Original: az-12-1.2倍率 Operator pending verification | 1.5 | 12 | — | 4.125Median price ÷ this price: 0.5× | Full prices and sources |
| 08 | go.sbgpt.siteAsk or discussCollected: Collected this cycle View 9 plans | openai-official [machine translation]Group on site: openai-官 openai-official-2x rate multiplier [machine translation]Original: openai-官-2倍率 Operator pending verification | 2.5 | 20 | — | 6.875Median price ÷ this price: 0.3× | Full prices and sources |
| 09 | go.sbgpt.siteAsk or discussCollected: Collected this cycle View 9 plans | Official openai [machine translation]Group on site: 官openai Official openai-4.5x rate multiplier [machine translation]Original: 官openai-4.5倍率 Operator pending verification | 5.625 | 45 | — | 15.469Median price ÷ this price: 0.1× | Full prices and sources |
Special groups · 8 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.
- top-up or membership gated: 6 rows
- test or debug group: 2 rows
- test-api.apiqik.online · vertex/sp/gemini · gemini-2.5-pro · Input 0.425 / Output 3.4 USD credits / 1M
- test-api.apiqik.online · gemini · gemini-2.5-pro · Input 0.625 / Output 5 USD credits / 1M
- poloai.top · Gemini-1 · gemini-2.5-pro · Input 1.25 / Output 10 USD credits / 1M
- poloai.top · Gemini-1 · gemini-2.5-pro-thinking-128 · Input 1.25 / Output 10 USD credits / 1M
- poloapi.top · Gemini-1 · gemini-2.5-pro-thinking-128 · Input 1.25 / Output 10 USD credits / 1M
- poloapi.top · Gemini-1 · gemini-2.5-pro · Input 1.25 / Output 10 USD credits / 1M
- xy.poloapi.com · Gemini-1 · gemini-2.5-pro · Input 1.25 / Output 10 USD credits / 1M
- xy.poloapi.com · Gemini-1 · gemini-2.5-pro-thinking-128 · Input 1.25 / Output 10 USD credits / 1M
Related variants · 109 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-pro-thinking (-thinking · thinking edition): 55 rows
- gemini-2.5-pro-thinking-128 (-thinking-128 · thinking edition): 23 rows
- gemini-2.5-pro-thinking-512 (-thinking-512 · thinking edition): 10 rows
- gemini-2.5-pro-deepsearch (-deepsearch · search or tool): 7 rows
- gemini-2.5-pro-search (-search · search or tool): 3 rows
- [夜雨]gemini-2.5-pro-thinking (-thinking · thinking edition): 2 rows
- gemini-2.5-pro-thinking-1024 (-thinking-1024 · thinking edition): 2 rows
- gemini-2.5-pro-thinking-3000 (-thinking-3000 · thinking edition): 2 rows
- [OO]gemini-2.5-pro-search (-search · search or tool): 1 rows
- [OO]gemini-2.5-pro-thinking (-thinking · thinking edition): 1 rows
- gemini-2.5-pro-thinking-16384 (-thinking-16384 · thinking edition): 1 rows
- gemini-2.5-pro-thinking-32768 (-thinking-32768 · thinking edition): 1 rows
- gemini-2.5-pro-thinking-8096 (-thinking-8096 · thinking edition): 1 rows
- go.sbgpt.site · No moderation az-0.4x rate multiplier [machine translation]Group on site: 无审核az-0.4倍率 · gemini-2.5-pro-thinking · Input 0.6 / Output 4.8 USD credits / 1M
- go.sbgpt.site · az-3 · gemini-2.5-pro-thinking · Input 0.6 / Output 4.8 USD credits / 1M
- apijing.com · gemini usage-based [machine translation]Group on site: gemini按量 · gemini-2.5-pro-thinking-128 · Input 0.625 / Output 5 USD credits / 1M
- go.sbgpt.site · No moderation az-2 [machine translation]Group on site: 无审核az-2 · gemini-2.5-pro-thinking · Input 0.725 / Output 5.8 USD credits / 1M
- go.sbgpt.site · gemini all models [machine translation]Group on site: gemini全模型 · gemini-2.5-pro-thinking · Input 0.75 / Output 6 USD credits / 1M
- go.sbgpt.site · No moderation AZ [machine translation]Group on site: 无审核AZ · gemini-2.5-pro-thinking · Input 0.75 / Output 6 USD credits / 1M
- apijing.com · gemini special offer all models [machine translation]Group on site: gemini特惠全模型 · gemini-2.5-pro-thinking-128 · Input 1 / Output 8 USD credits / 1M
- aiapi.world · default · gemini-2.5-pro-thinking · Input 1.2456 / Output 9.9647 USD credits / 1M
- api.101aix.com · Gemini · gemini-2.5-pro-thinking · Input 1.25 / Output 0.78125 USD credits / 1M
- api.101aix.com · Gemini · gemini-2.5-pro-thinking-512 · Input 1.25 / Output 0.78125 USD credits / 1M
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 1707 recorded prices; 570 can be compared directly (398 ranked, 172 listed separately). Not comparable yet: price not parsed yet 611, billed per request or another unit 233, tiered by rules (see Tiered prices) 170, ratio looks unset 68, display unit not confirmed 25, scope of the official doc price not confirmed 24
9 recent · 0 stale (older than 10 days, or not updated by this refresh) · 0 unverified timestamps. Minimum and median only count recent paid prices; older prices stay in the table. 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.
Sources not accepted this cycle and reasons
FAQ
Which API is cheapest for Google · gemini-2.5-pro?
go.sbgpt.site, group "无审核az-0.4倍率 (No moderation az-0.4x rate multiplier)", 1.65 USD credit per million total tokens, observed 2026-10-16. 155 sites have comparable prices.
What is the official price for Google · gemini-2.5-pro?
Input 1.25, output 10 USD per million tokens, checked 2026-10-17. Lowest inference provider: DeepInfra, input 1.25, output 10 USD per million tokens.
How do I use Google · gemini-2.5-pro in Claude Code or Codex?
Install Grandet Skill, then say "Connect the cheapest Google · gemini-2.5-pro API to Claude Code for me". Install Skill →