Google Models API Cost Calculator & Comparison

Every Google model, side by side — current API rates, context window, benchmarks, and a live calculator that ranks them at your exact workload. 31 active models, 31 with public pricing. Prices refreshed daily.

Models tracked

31

Active

31

With public pricing

31

Cheapest input

$0.00/1M

Calculate your Google API cost at your workload.

Set your workload — every priced model ranks in real time.

Adjust the workload

Every model below updates in real time.

1,00010,00050,000250,0001M10M

Ranked by your monthly bill

No models with public pricing available to compare right now.

Pricing at a glance

Blended $/1M tokens across the lineup.

Blended price uses a 3-to-1 input/output ratio. Green bar = cheapest.

Quick picks

Best Google model for your use case.

As of April 2026, Google offers 31 active models via API, ranging from $0/1M to $2.00/1M input tokens. The most context-rich model handles up to 1M tokens. Models support vision, deep reasoning, tool use. All prices are USD per 1 million tokens.

Lowest cost

Gemma 4 26B A4B

$0/1M input

Largest context

Gemini 3.1 Flash Lite Preview

1.0M tokens

Deep reasoning

Gemini 3.1 Pro Preview

Reasoning mode

Vision / multimodal

Gemma 4 26B A4B

Image input

Tool use / agents

Gemma 4 31B

Function calling

Quality vs price

Google benchmarks at a glance.

Each point is one model — X is blended $/1M tokens, Y is the average of available quality benchmarks. Larger bubbles mean larger context windows.

Per-model benchmark scores

ModelAvgScores
Gemma 3 12B86.7
HumanEval85.4IFEval88.9BBH85.7
Gemma 3 12B86.7
HumanEval85.4IFEval88.9BBH85.7
Gemini 2.5 Pro Preview 05-0684.0
GPQA Diamond84
Gemma 4 31B76.0
MMLU Pro85.2LiveCodeBench80AA Intelligence Index39Chatbot Arena Elo1452
Gemma 3 27B75.3
MMLU Pro67.5GPQA Diamond42.4HumanEval87.8MATH89Chatbot Arena Elo1338
Gemini 2.0 Flash Lite71.6
MMLU Pro71.6
Gemma 4 26B A4B69.9
MMLU Pro82.6AIME 202589LiveCodeBench77.1AA Intelligence Index31
Gemma 3n 4B69.4
MMLU Pro69.4
Gemma 4 31B62.1
MMLU Pro85.2AA Intelligence Index39
Gemma 2 27B61.8
MMLU75.2HumanEval51.8MATH42.3BBH74.9Chatbot Arena Elo1220IFEval79.8MMLU Pro38.4
Gemini 2.5 Pro61.0
MMLU Pro86.2GPQA Diamond84SWE-Bench Verified63.8AIME 202492AIME 202586.7AA Intelligence Index60Chatbot Arena Elo1451FrontierMath Tier-42.1SciPredict17.0Humanity's Last Exam18.2
Gemma 3 27B59.4
MMLU Pro67.5GPQA Diamond42.4HumanEval87.8MATH89LiveCodeBench29.7AA Intelligence Index10Chatbot Arena Elo1338
Gemini 3.1 Pro Preview58.2
SWE-Bench Verified75.6GPQA Diamond94.1FrontierMath Tier-416.7Humanity's Last Exam46.4
Gemini 3.1 Pro Preview Custom Tools58.2
SWE-Bench Verified75.6GPQA Diamond94.1FrontierMath Tier-416.7Humanity's Last Exam46.4
Gemma 4 26B A4B56.8
MMLU Pro82.6AA Intelligence Index31
Gemini 2.0 Flash51.4
MMLU Pro77GPQA Diamond62SWE-Bench Verified51AA Intelligence Index19Chatbot Arena Elo1356Humanity's Last Exam6.6
Gemma 3 4B51.3
HellaSwag77.2BBH50.9DROP60.1MMLU59.6MATH24.2HumanEval36
Gemma 3 4B51.3
HellaSwag77.2BBH50.9DROP60.1MMLU59.6MATH24.2HumanEval36
Gemini 2.5 Flash51.0
GPQA Diamond82.8AIME 202488AA Intelligence Index21Humanity's Last Exam12.1
Gemma 3n 4B44.2
MMLU Pro69.4AA Intelligence Index19
Gemini 2.5 Pro Preview 06-0542.7
MMLU Pro86.2GPQA Diamond86.4FrontierMath Tier-42.1SciPredict17.0Humanity's Last Exam21.6
Gemini 2.5 Flash Lite39.0
GPQA Diamond65AA Intelligence Index13
Gemma 3n 2B37.5
MMLU Pro60AA Intelligence Index15
Gemini 3 Flash Preview34.1
AA Intelligence Index46SciPredict22.2
Gemini 3.1 Flash Lite Preview8.6
Humanity's Last Exam8.6

Open weights

Open Models from Google

Google ships 14 open-source or open-weights models you can self-host or fine-tune. Each links to its Hugging Face card.

Every model

Every Google model — pricing, context & capabilities.

ModelContextInput /1MOutput /1M
Gemma 4 26B A4B262K$0.08$0.35
Gemma 4 26B A4B262K$0.0$0.0
Gemma 4 31B262K$0.13$0.38
Gemma 4 31B262K$0.0$0.0
Gemini 3.1 Flash Lite Preview1.0M$0.25$1.50
Gemini 3.1 Pro Preview1.0M$2.00$12.00
Gemini 3.1 Pro Preview Custom Tools1.0M$2.00$12.00
Lyria 3 Pro Preview1.0M$0.0$0.0
Nano Banana 2 (Gemini 3.1 Flash Image Preview)66K$0.5$3.00
Lyria 3 Clip Preview1.0M$0.0$0.0
Gemini 3 Flash Preview1.0M$0.5$3.00
Nano Banana Pro (Gemini 3 Pro Image Preview)66K$2.00$12.00
Gemini 2.5 Flash Lite Preview 09-20251.0M$0.1$0.4
Gemma 3n 2B8K$0.0$0.0
Gemma 3n 4B33K$0.06$0.12
Gemma 3n 4B8K$0.0$0.0
Gemini 2.5 Flash Lite1.0M$0.1$0.4
Nano Banana (Gemini 2.5 Flash Image)33K$0.3$2.50
Gemini 2.5 Pro Preview 06-051.0M$1.25$10.00
Gemini 2.5 Flash1.0M$0.3$2.50
Gemini 2.5 Pro Preview 05-061.0M$1.25$10.00
Gemini 2.5 Pro1.0M$1.25$10.00
Gemma 3 12B131K$0.04$0.13
Gemma 3 12B33K$0.0$0.0
Gemma 3 27B131K$0.08$0.16
Gemma 3 27B131K$0.0$0.0
Gemma 3 4B131K$0.04$0.08
Gemma 3 4B33K$0.0$0.0
Gemini 2.0 Flash Lite1.0M$0.075$0.3
Gemini 2.0 Flash1M$0.1$0.4
Gemma 2 27B8K$0.65$0.65

FAQ

Preguntas frecuentes

Pricing patterns, best-known use cases, and how this provider stacks up.

Get instant answers from our AI agent

Google API pricing ranges from $0 to $2.00 per 1M input tokens. Output tokens cost more than input on every model. Prices are per 1 million tokens (1M ≈ 750,000 words). Use the calculator above to estimate your monthly spend at your actual workload.
Gemma 4 26B A4B is the lowest-priced Google model with public pricing at $0/1M input tokens. It suits high-volume tasks where cost matters most — classification, extraction, summarization, and similar workloads that don't need frontier reasoning.
Gemini 3.1 Pro Preview is Google's highest-tier model at $2.00/1M input. It delivers the most sophisticated reasoning, instruction-following, and nuance. For workloads that don't require frontier performance, a mid-tier model typically cuts inference costs substantially.
Gemini 3.1 Flash Lite Preview, Gemini 3.1 Pro Preview, Gemini 3.1 Pro Preview Custom Tools and 9 more support deep reasoning mode, which improves performance on multi-step coding, debugging, and code review. For simpler autocomplete or snippet generation, a faster, cheaper model often delivers acceptable quality at a fraction of the cost.
Gemma 4 26B A4B, Gemma 4 26B A4B, Gemma 4 31B and 23 more support function calling (tool use), required for agentic workflows. Agents need a model that reliably follows structured output schemas — test with your specific tool definitions before committing to production volumes.
Yes — Gemma 4 26B A4B, Gemma 4 26B A4B, Gemma 4 31B, Gemma 4 31B and 26 more accept image input alongside text. You can pass screenshots, photos, charts, and documents for analysis. Vision adds no separate line-item on most Google models — you're billed for the token equivalent of the image.
Yes — Google supports prompt caching (discounts for repeated context) and batch processing (accept a delay, cut costs ~50%). These rates appear in the table above under "Cached /1M" and "Batch /1M." Caching pays off quickly if your prompts share a long system prompt or document prefix across many calls.
Google has historically adjusted prices when launching new model generations, often cutting rates to stay competitive. Buzzi.ai snapshots pricing daily — you can subscribe to price-drop alerts on any Google model using the "Alert me" button on its detail page.
Use the main comparison wizard to run the same calculator across Google, Anthropic, Google, Meta, Mistral, and 20+ other providers. Set your exact workload and get a ranked cost chart in under a minute.
Gemini 3.1 Flash Lite Preview, Gemini 3.1 Pro Preview, Gemini 3.1 Pro Preview Custom Tools, Gemini 3 Flash Preview and 8 more offer an extended thinking or reasoning mode. The model spends extra compute "thinking" before answering — slower and more expensive, but meaningfully better on complex, multi-step problems. Standard mode is faster and cheaper for routine tasks.

Look wider

Compare Google against other providers.

Open the full wizard — pick a use case, set your usage, and cross-compare against OpenAI, Anthropic, Google, and 20+ more.

Open the comparison wizard