BroadRouter

Gemini API API pricing

Updated

Gemini API lists standard per-token prices for 12 models. The cheapest is Gemini 2.5 Flash-Lite at USD 0.10 input and USD 0.40 output per 1M tokens; the dearest is Gemini 3.1 Pro Preview at USD 2 / USD 12. It publishes cached-input prices for all of them, plus batch, flex / spot and priority tiers. Checked 2026-11-14.

Gemini API is a model maker: 12 of the 12 models here are its own. By maker: Google 12. 48 prices, each read from Gemini API's own pricing page or one of 11 linked model pages, checked 2026-11-14. BroadRouter is BroadNet's own site and does not sell Gemini API's services. Automated re-check 2026-11-16: 48 of 48 prices still matched the provider's page.

Models with a standard price
12
Median input / output
USD 0.75 / USD 3.75
Cached-input prices
12 of 12
Cheapest host for
11 of 11 shared models

Which models is Gemini API the cheapest provider for?

Of the 11 models that Gemini API and at least one other provider both price at the standard tier, Gemini API has the lowest price for 11, ranked on a blend of 3 input tokens to 1 output token (all of them tied with another provider at the same price; the maker's own API is listed first on a tie). Another 1 model has a standard price from Gemini API only.

Models where Gemini API is the cheapest provider
ModelGemini API input / outputNext cheapestSaving on 3:1 blendProviders
Gemini 4 Argon (promo)USD 2 / USD 10GMI Cloud USD 2 / USD 10tie4
Gemini 4 Carbon (promo)USD 2 / USD 10GMI Cloud USD 2 / USD 10tie4
Gemini 2.5 FlashUSD 0.30 / USD 2.50DeepInfra USD 0.30 / USD 2.50tie3
Gemini 2.5 ProUSD 1.25 / USD 10DeepInfra USD 1.25 / USD 10tie3
Gemini 3.1 Flash-Lite (gemini-3.1-flash-lite)USD 0.25 / USD 1.50DeepInfra USD 0.25 / USD 1.50tie3
Gemini 3.1 Pro PreviewUSD 2 / USD 12GMI Cloud USD 2 / USD 12tie3
Gemini 3.5 Flash-LiteUSD 0.30 / USD 2.50GMI Cloud USD 0.30 / USD 2.50tie3
Gemini 3.6 Flash (promo)USD 0.75 / USD 3.75Google Vertex AI USD 0.75 / USD 3.75tie3
Gemini 3.8 Flash (promo)USD 0.75 / USD 3.75GMI Cloud USD 0.75 / USD 3.75tie3
Gemini 4 HydrogenUSD 1.50 / USD 7.50Google Vertex AI USD 1.50 / USD 7.50tie3
Gemini 2.5 Flash-LiteUSD 0.10 / USD 0.40Google Vertex AI USD 0.10 / USD 0.40tie2

The 6 models Gemini API sells that the most other providers also sell, with Gemini API's rank among them on the 3:1 blend.

Gemini API on the most widely hosted models
ModelGemini APIRankCheapest
Gemini 4 ArgonUSD 2 / USD 101 of 4Gemini API (this page)
Gemini 4 CarbonUSD 2 / USD 101 of 4Gemini API (this page)
Gemini 2.5 FlashUSD 0.30 / USD 2.501 of 3Gemini API (this page)
Gemini 2.5 ProUSD 1.25 / USD 101 of 3Gemini API (this page)
Gemini 3.1 Flash-Lite (gemini-3.1-flash-lite)USD 0.25 / USD 1.501 of 3Gemini API (this page)
Gemini 3.1 Pro PreviewUSD 2 / USD 121 of 3Gemini API (this page)

Gemini API price list

USD per 1M tokens: 48 prices for 12 models, one row per model with any other service tiers stacked under the standard price. Sources checked 2026-11-14 unless a row says otherwise. "vs maker" compares a standard price with the model maker's own API on the 3:1 blend; a minus means Gemini API is cheaper. Gemini API is the maker of every model here, so there is no maker price to compare with.

Gemini API API prices by model
ModelTierInputCachedOutputContextvs makerSource
Gemini 2.5 Flashstandard
batch
flex / spot
priority
USD 0.30
USD 0.15
USD 0.15
USD 0.54
USD 0.03
USD 0.03
USD 0.03
USD 0.054
USD 2.50
USD 1.25
USD 1.25
USD 4.50
not statedown modelsource
Gemini 2.5 Flash-Litestandard
batch
flex / spot
priority
USD 0.10
USD 0.05
USD 0.05
USD 0.18
USD 0.01
USD 0.01
USD 0.01
USD 0.018
USD 0.40
USD 0.20
USD 0.20
USD 0.72
not statedown modelsource
Gemini 2.5 Prostandard
batch
flex / spot
priority
USD 1.25
USD 0.625
USD 0.625
USD 2.25
USD 0.125
USD 0.125
USD 0.125
USD 0.225
USD 10
USD 5
USD 5
USD 18
not statedown modelsource
Gemini 3 Flash Previewstandard
batch
flex / spot
priority
USD 0.50
USD 0.25
USD 0.25
USD 0.90
USD 0.05
USD 0.05
USD 0.05
USD 0.09
USD 3
USD 1.50
USD 1.50
USD 5.40
not statedown modelsource
Gemini 3.1 Flash-Lite (gemini-3.1-flash-lite)standard
batch
flex / spot
priority
USD 0.25
USD 0.125
USD 0.125
USD 0.45
USD 0.025
USD 0.0125
USD 0.0125
USD 0.045
USD 1.50
USD 0.75
USD 0.75
USD 2.70
not statedown modelsource
Gemini 3.1 Pro Previewstandard
batch
flex / spot
priority
USD 2
USD 1
USD 1
USD 3.60
USD 0.20
USD 0.20
USD 0.20
USD 0.36
USD 12
USD 6
USD 6
USD 21.60
not statedown modelsource
Gemini 3.5 Flash-Litestandard
batch
flex / spot
priority
USD 0.30
USD 0.15
USD 0.15
USD 0.54
USD 0.03
USD 0.015
USD 0.02
USD 0.05
USD 2.50
USD 1.25
USD 1.25
USD 4.50
not statedown modelsource
Gemini 3.6 Flashpromostandard
batch
flex / spot
priority
USD 0.75
USD 0.375
USD 0.375
USD 1.35
USD 0.075
USD 0.0375
USD 0.0375
USD 0.135
USD 3.75
USD 1.875
USD 1.875
USD 6.75
not statedown modelsource
Gemini 3.8 Flashpromostandard
batch
flex / spot
priority
USD 0.75
USD 0.375
USD 0.375
USD 1.35
USD 0.075
USD 0.0375
USD 0.0375
USD 0.135
USD 3.75
USD 1.875
USD 1.875
USD 6.75
not statedown modelsource
Gemini 4 Argonpromostandard
batch
flex / spot
priority
USD 2
USD 1
USD 1
USD 3.60
USD 0.10
USD 0.05
USD 0.05
USD 0.18
USD 10
USD 5
USD 5
USD 18
not statedown modelsource
Gemini 4 Carbonpromostandard
batch
flex / spot
priority
USD 2
USD 1
USD 1
USD 3.60
USD 0.10
USD 0.05
USD 0.05
USD 0.18
USD 10
USD 5
USD 5
USD 18
not statedown modelsource
Gemini 4 Hydrogenstandard
batch
flex / spot
priority
USD 1.50
USD 0.75
USD 0.75
USD 2.70
USD 0.075
USD 0.0375
USD 0.0375
USD 0.135
USD 7.50
USD 3.75
USD 3.75
USD 13.50
not statedown modelsource
  • Cached "—" means Gemini API's page shows no cache price for that row; budget cached tokens at the input price.
  • Context "not stated": Gemini API's pricing page does not give context windows.
  • Promo: Gemini API's page describes 4 prices as promotional or discounted; they can end without notice. Each model page has the list price where the source gives one.

Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).

What service tiers does Gemini API publish?

  • batch (12 rows). Across 12 models with both prices, the median batch price is 50% below standard. Gemini API row note: “Paid tier. Text, image and video input; audio input costs more. Cache storage is billed separately per hour.”
  • flex / spot (12 rows). Across 12 models with both prices, the median flex / spot price is 50% below standard. Gemini API row note: “Paid tier. Text, image and video input; audio input costs more. Cache storage is billed separately per hour.”
  • priority (12 rows). Across 12 models with both prices, the median priority price is 1.8× standard. Gemini API row note: “Paid tier. Text, image and video input; audio input costs more. Cache storage is billed separately per hour.”

Cached input: 12 of 12 standard prices include a cache-read price, a median 10% of the input price. What cached input means.

What we recorded about Gemini API's pricing page: Gemini Developer API paid tier, per 1M tokens in USD (ai.google.dev/gemini-api/docs/pricing redirects here). Gemma 4 has no paid tier on the Gemini API (free tier only), so it is not listed. The invite-only Contributor tier is not listed. Context windows are not stated on the pricing page.

BroadNet Inference and Gemini API

BroadRouter is BroadNet's own site, so BroadNet is never ranked on this page. BroadNet Inference serves none of the models Gemini API prices. BroadNet Inference pricing.

More on Gemini API

Quick answers

Is Gemini API OpenAI-compatible?

Yes, in beta. Google's OpenAI compatibility docs list chat completions, embeddings, image generation, models and batch, and say OpenAI library support is "still in beta". No Responses API is listed (Google, Gemini OpenAI compatibility, checked 2026-11-15).

What is Gemini API's API base URL?

https://generativelanguage.googleapis.com/v1beta/openai/, as Gemini API documents it. It ends in /v1beta/openai/, not /v1 (Google, Gemini OpenAI compatibility, checked 2026-11-15).

Does Gemini API keep API prompts and outputs?

On paid services, Google "logs prompts and responses for a limited period of time, solely for detecting and preventing violations"; no number of days is given. On unpaid services the terms do not give a retention period, and human reviewers may read API input and output (Gemini API Additional Terms of Service, checked 2026-11-14).

Does Gemini API train on API data?

Not on paid services: Google says it "doesn't use your prompts ... or responses to improve our products". On unpaid services it uses content "to provide, improve, and develop" its products. In the EEA, UK and Switzerland the paid-services data terms apply to all services (Gemini API Additional Terms of Service, checked 2026-11-14).

Does Gemini API have a free tier?

Free tier: many models show "Free of charge" on the pricing page, including Gemini 4 Hydrogen, Gemini 3.8 Flash and Gemini 3.5 Flash-Lite (Gemini API pricing, checked 2026-11-14). Per-model free-tier limits are shown only in Google AI Studio: "Rate limits depend on a variety of factors (such as your usage tier) and can be viewed in Google AI Studio." The one model with published free-tier numbers is Gemini Decision 1 (200 RPM, 50,000 TPM, 10,000 RPD) (Gemini API rate limits, checked 2026-11-14).

Does Gemini API have a batch API?

Yes. Google's Gemini OpenAI compatibility docs list batch among the supported endpoints (Google, Gemini OpenAI compatibility, checked 2026-11-15).

Questions

How much does the Gemini API API cost per token?

Gemini API's standard prices run from USD 0.10 input and USD 0.40 output per 1M tokens (Gemini 2.5 Flash-Lite) to USD 2 / USD 12 (Gemini 3.1 Pro Preview). The median across 12 standard prices is USD 0.75 input and USD 3.75 output per 1M, which is USD 0.00000075 per input token. Input, cached input and output are billed separately.

What is the cheapest model on Gemini API?

Gemini 2.5 Flash-Lite, at USD 0.10 input and USD 0.40 output per 1M tokens (USD 0.175 on a 3:1 input-to-output blend).

Is Gemini API cheaper than other providers?

It depends on the model. Of 11 models that other providers also price, Gemini API is the cheapest standard price for 11 (all of them tied with another provider), for example Gemini 4 Argon, Gemini 4 Carbon and Gemini 2.5 Flash; another provider is cheaper for none; and it is the dearest for none. Its median rank is 1 of a median 3 providers, on a 3:1 input-to-output blend.

Does Gemini API have batch, cached or priority pricing?

Cached input: yes, for 12 of 12 standard prices, at a median 10% of the input price. Other tiers: batch on 12 rows (median input 50% below standard); flex / spot on 12 rows (median input 50% below standard); priority on 12 rows (median input 1.8× standard).

How much does a chatbot cost per month on Gemini API?

For 2,000 requests a day, 1,500 input tokens (60% cached), 300 output, over 30 days: USD 11.34 on Gemini 2.5 Flash-Lite, USD 98.55 on Gemini 3.6 Flash (the middle of Gemini API's list) and USD 298.80 on Gemini 3.1 Pro Preview. Try your own numbers.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity