---
title: "Gemini 3.5 Flash vs Gemini 2.5 Flash API pricing compared"
description: "Gemini 3.5 Flash vs Gemini 2.5 Flash API price per 1M tokens: USD 1.50 / USD 9 vs USD 0.30 / USD 2.50 input/output, from providers' own pricing pages."
url: https://broadrouter.com/llm-api-pricing/compare/gemini-3.5-flash-vs-gemini-2.5-flash/
lang: en
updated: 2026-11-15
publisher: BroadRouter (a BroadNet site); API by BroadNet Inference, https://inference.broadnet.ai
---

# Gemini 3.5 Flash vs Gemini 2.5 Flash API pricing

Updated 2026-11-15

Gemini 3.5 Flash: USD 1.50 input, USD 9 output per 1M tokens (DeepInfra and 2 others). Gemini 2.5 Flash: USD 0.30 input, USD 2.50 output per 1M tokens (Google Gemini API and 2 others). At 3 input tokens per output token, Gemini 3.5 Flash costs 4× as much as Gemini 2.5 Flash (USD 3.375 vs USD 0.85 per 1M).

Gemini 2.5 Flash is the release before Gemini 3.5 Flash in the same Google line (by version in the name), so this page shows what the newer release costs. **Price only**: every number is computed from prices read from each provider's own pricing page (linked per cell, newest check 2026-11-15), with no claim about quality, speed or accuracy.

## How do Gemini 3.5 Flash and Gemini 2.5 Flash differ on price?

-   Cheapest input price: Gemini 2.5 Flash USD 0.30 against USD 1.50 per 1M tokens, so Gemini 3.5 Flash costs 5× as much.
-   Cheapest output price: Gemini 2.5 Flash USD 2.50 against USD 9 per 1M tokens, so Gemini 3.5 Flash costs 3.6× as much.
-   Among the 201 indexed models, Gemini 3.5 Flash ranks 164th cheapest and Gemini 2.5 Flash 121st on the 3:1 blend.
-   No input:output mix changes the answer: Gemini 2.5 Flash is cheaper at every mix before cache discounts.
-   Both list cached-input discounts: Gemini 3.5 Flash at 2 standard prices of 3, from USD 0.15 (GMI Cloud, 90% below that provider's input price); Gemini 2.5 Flash at 2 standard prices of 3, from USD 0.03 (Google Gemini API, 90% below that provider's input price).
-   Gemini 3.5 Flash states up to 1,048,576 tokens of context and Gemini 2.5 Flash 1,000,000, within 10% of each other.
-   Both have 3 providers with a standard price; 2 providers sell both (DeepInfra and Google Vertex AI).
-   On one account, DeepInfra charges USD 3.375 for Gemini 3.5 Flash (its cheapest price) and USD 0.85 for Gemini 2.5 Flash (its cheapest price) at 3:1, tied with 1 other provider for the lowest combined price among the providers that sell both.
-   Shopping around matters equally: on both, the dearest standard price is 1× the cheapest.
-   Google's own API is one of 3 providers tied for the lowest standard price we found for Gemini 2.5 Flash, USD 0.85 at 3:1.
-   Gemini 3.5 Flash has a batch price at 1 provider, from USD 1.688 at 3:1 (Google Vertex AI); Gemini 2.5 Flash has a batch price at 2 providers, from USD 0.425 at 3:1 (Google Gemini API).
-   For the one-developer coding agent preset, the gap is USD 13,111 a year in Gemini 2.5 Flash's favour (Gemini 3.5 Flash USD 1,444 a month, Gemini 2.5 Flash USD 351.90).

## Gemini 3.5 Flash and Gemini 2.5 Flash prices side by side

USD per 1M tokens, standard tier. "Cheapest" is the lowest price at 3 input tokens to 1 output token; each line can come from a different provider.

Gemini 3.5 Flash and Gemini 2.5 Flash API prices compared
| Price | Gemini 3.5 Flash | Gemini 2.5 Flash |
| --- | --- | --- |
| Model page | [Gemini 3.5 Flash](https://broadrouter.com/llm-api-pricing/gemini-3.5-flash/) · Google · 3 providers | [Gemini 2.5 Flash](https://broadrouter.com/llm-api-pricing/gemini-2.5-flash/) · Google · 3 providers |
| Cheapest standard price, blended 3:1 | USD 3.375 · USD 1.50 in / USD 9 out at DeepInfra and 2 others · [DeepInfra page](https://deepinfra.com/google/gemini-3.5-flash) checked 2026-11-14 | USD 0.85 lower · USD 0.30 in / USD 2.50 out at Google Gemini API and 2 others · [Google Gemini API page](https://aistudio.google.com/docs/pricing#gemini-2.5-flash) checked 2026-11-14 |
| Cheapest input | USD 1.50 · DeepInfra [source](https://deepinfra.com/google/gemini-3.5-flash) | USD 0.30 lower · Google Gemini API [source](https://aistudio.google.com/docs/pricing#gemini-2.5-flash) |
| Cheapest cached input | USD 0.15 · GMI Cloud [source](https://console.gmicloud.ai/model/llm/gemini-3-5-flash/88943704-646d-47f6-868c-408ed6f78e08) | USD 0.03 lower · Google Gemini API [source](https://aistudio.google.com/docs/pricing#gemini-2.5-flash) |
| Cheapest output | USD 9 · DeepInfra [source](https://deepinfra.com/google/gemini-3.5-flash) | USD 2.50 lower · Google Gemini API [source](https://aistudio.google.com/docs/pricing#gemini-2.5-flash) |
| Maker's own API | Google publishes no paid standard price on its own API that we found. | USD 0.30 / USD 2.50 · Google Gemini API [source](https://aistudio.google.com/docs/pricing#gemini-2.5-flash) |
| Median standard price | USD 1.50 / USD 9 · input / output, 3 prices | USD 0.30 / USD 2.50 · input / output, 3 prices |
| Context window | 1,048,576 tokens, largest stated; from 1,000,000 at some providers | 1,000,000 tokens, largest stated |
| Providers with a standard price | 3 | 3 |

-   **Lower** marks the lower price on a line; **tie**, equal prices. Other tiers and free rows are on the model pages.

[Report a wrong price or number](mailto:info@broadnet.ai?subject=Wrong%20price%20or%20number%20on%20Gemini%203.5%20Flash%20vs%20Gemini%202.5%20Flash%20API%20pricing&body=Page%3A%20https%3A%2F%2Fbroadrouter.com%2Fllm-api-pricing%2Fcompare%2Fgemini-3.5-flash-vs-gemini-2.5-flash%2F%0A%0AWhat%20looks%20wrong%20(model%2C%20figure%20shown%2C%20correct%20figure%20and%20a%20source%20link%20if%20you%20have%20one)%3A%0A) (email to info@broadnet.ai, with this page's link filled in).

## What do Gemini 3.5 Flash and Gemini 2.5 Flash cost for a real workload?

30 days at each model's cheapest standard price for the workload (presets of the [cost calculator](https://broadrouter.com/tools/llm-api-cost-calculator/?model=gemini-3.5-flash,gemini-2.5-flash); cached input at the cached price where listed).

Monthly cost of three workloads on Gemini 3.5 Flash and Gemini 2.5 Flash
| Workload | Gemini 3.5 Flash | Gemini 2.5 Flash | Difference |
| --- | --- | --- | --- |
| **Support chatbot** · 2,000 requests a day, 1,500 input tokens (60% cached), 300 output | USD 224.10 · GMI Cloud | USD 57.42 · Google Gemini API | USD 166.68 · Gemini 2.5 Flash lower |
| **RAG over documents** · 1,000 requests a day, 8,000 input tokens (30% cached), 500 output | USD 397.80 · GMI Cloud | USD 90.06 · Google Gemini API | USD 307.74 · Gemini 2.5 Flash lower |
| **Coding agent (one developer)** · 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning | USD 1,444 · GMI Cloud | USD 351.90 · Google Gemini API | USD 1,093 · Gemini 2.5 Flash lower |

Gemini 2.5 Flash is cheaper on all three workloads. The widest gap is on RAG over documents: the dearer model costs 4.4× as much as the cheaper one.

## Does the cheaper model change with your input:output ratio?

Gemini 2.5 Flash is cheaper at every mix of input and output tokens, before cache discounts: its cheapest input price and its cheapest output price are both at or below Gemini 3.5 Flash's, so the input:output ratio never changes the answer.

Price per 1M tokens of Gemini 3.5 Flash and Gemini 2.5 Flash at different input:output mixes
| Input : output tokens | Gemini 3.5 Flash | Gemini 2.5 Flash |
| --- | --- | --- |
| **1 : 3** (long answers) | USD 7.125 · DeepInfra | USD 1.95 lower · Google Gemini API |
| **1 : 1** | USD 5.25 · DeepInfra | USD 1.40 lower · Google Gemini API |
| **3 : 1** (the site’s blend) | USD 3.375 · DeepInfra | USD 0.85 lower · Google Gemini API |
| **10 : 1** (retrieval, long prompts) | USD 2.182 · DeepInfra | USD 0.50 lower · Google Gemini API |
| **30 : 1** (agents, big contexts) | USD 1.742 · DeepInfra | USD 0.371 lower · Google Gemini API |

USD per 1M tokens at the cheapest standard provider for each mix, before cache discounts. Thinking tokens bill as output.

## What do Gemini 3.5 Flash and Gemini 2.5 Flash cost per character in other languages?

Not measured: the [real cost by language dataset](https://broadrouter.com/data/real-cost-by-language/) covers only tokenizers we could measure from published files, and Gemini 3.5 Flash and Gemini 2.5 Flash are not among them. Count tokens on your own text with the counters below.

## Check it on your own traffic

-   [Gemini 3.5 Flash API pricing](https://broadrouter.com/llm-api-pricing/gemini-3.5-flash/): all 3 providers and other tiers.
-   [Gemini 2.5 Flash API pricing](https://broadrouter.com/llm-api-pricing/gemini-2.5-flash/): all 3 providers and other tiers.
-   [Cost calculator with Gemini 3.5 Flash and Gemini 2.5 Flash preloaded](https://broadrouter.com/tools/llm-api-cost-calculator/?model=gemini-3.5-flash,gemini-2.5-flash)
-   [Token counter](https://broadrouter.com/tools/token-counter/)
-   [Prompt caching calculator](https://broadrouter.com/tools/prompt-caching-calculator/)

More comparisons: [Gemini 3.6 Flash vs Gemini 3.5 Flash](https://broadrouter.com/llm-api-pricing/compare/gemini-3.6-flash-vs-gemini-3.5-flash/) · [Gemini 2.5 Pro vs Gemini 2.5 Flash](https://broadrouter.com/llm-api-pricing/compare/gemini-2.5-pro-vs-gemini-2.5-flash/) · [every Gemini 3.5 Flash comparison](https://broadrouter.com/llm-api-pricing/compare/#m-gemini-3.5-flash) · [every Gemini 2.5 Flash comparison](https://broadrouter.com/llm-api-pricing/compare/#m-gemini-2.5-flash) · [all 662 price comparisons](https://broadrouter.com/llm-api-pricing/compare/)

## Questions

### Is Gemini 3.5 Flash cheaper than Gemini 2.5 Flash?

No. On a blend of 3 input tokens to 1 output token, Gemini 2.5 Flash costs USD 0.85 per 1M tokens and Gemini 3.5 Flash USD 3.375, at each model's cheapest standard price. For input alone, Gemini 2.5 Flash is cheaper (USD 0.30 against USD 1.50 per 1M); for output alone, Gemini 2.5 Flash is (USD 2.50 against USD 9). This compares price only, not quality.

### What do Gemini 3.5 Flash and Gemini 2.5 Flash cost per 1M tokens?

Gemini 3.5 Flash: from USD 1.50 input and USD 9 output at DeepInfra and 2 others; median of 3 standard prices USD 1.50 / USD 9. Gemini 2.5 Flash: from USD 0.30 input and USD 2.50 output at Google Gemini API and 2 others; Google Gemini API's own API charges USD 0.30 / USD 2.50; median of 3 standard prices USD 0.30 / USD 2.50. Each price is read from the provider's own pricing page; the source is linked in the table.

### Which providers sell both Gemini 3.5 Flash and Gemini 2.5 Flash?

2 providers have a standard price for both: DeepInfra (USD 3.375 and USD 0.85 at 3:1), Google Vertex AI (USD 3.375 and USD 0.85 at 3:1). The first 2 tie for the lowest combined price. Buying each model from its own cheapest provider costs USD 3.375 and USD 0.85.

### Which is cheaper for a coding agent or a chatbot, Gemini 3.5 Flash or Gemini 2.5 Flash?

For a coding agent (1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning): USD 1,444 a month on Gemini 3.5 Flash (GMI Cloud) against USD 351.90 on Gemini 2.5 Flash (Google Gemini API), a difference of USD 1,093. For a support chatbot (2,000 requests a day, 1,500 input tokens (60% cached), 300 output): USD 224.10 a month on Gemini 3.5 Flash (GMI Cloud) against USD 57.42 on Gemini 2.5 Flash (Google Gemini API), a difference of USD 166.68. Each uses the cheapest standard price for that workload, cached input included. [Try your own numbers](https://broadrouter.com/tools/llm-api-cost-calculator/?model=gemini-3.5-flash,gemini-2.5-flash).

### At what input:output ratio does the cheaper of Gemini 3.5 Flash and Gemini 2.5 Flash change?

Gemini 2.5 Flash is cheaper at every mix of input and output tokens, before cache discounts: its cheapest input price and its cheapest output price are both at or below Gemini 3.5 Flash's, so the input:output ratio never changes the answer.

### Do Gemini 3.5 Flash and Gemini 2.5 Flash have cached input pricing?

Gemini 3.5 Flash from USD 0.15 per 1M cached input tokens (GMI Cloud; 2 of 3 standard prices list a discount). Gemini 2.5 Flash from USD 0.03 per 1M cached input tokens (Google Gemini API; 2 of 3 standard prices list a discount). Cached tokens are billed at the input price where no cache price is published.

### Which has the larger context window, Gemini 3.5 Flash or Gemini 2.5 Flash?

Gemini 3.5 Flash: up to 1,048,576 tokens, against 1,000,000 for Gemini 2.5 Flash, as stated on providers' pricing pages. Some providers offer less than the maximum; check the model pages before you pick the cheapest row for long prompts.

Try it on your real workload. New accounts start with $5 of credit for Gemma and transcription. DeepSeek, GLM and Qwen3.8 need a top-up.

[Get started](https://inference.broadnet.ai/account/?utm_source=broadrouter&utm_medium=referral&utm_campaign=llm-api-pricing-compare-gemini-3.5-flash-vs-gemini-2.5-flash&utm_content=page-cta) ·

**Sources**

-   [DeepInfra: pricing (checked 2026-11-14)](https://deepinfra.com/google/gemini-3.5-flash)
-   [GMI Cloud: pricing (checked 2026-11-15)](https://console.gmicloud.ai/model/llm/gemini-3-5-flash/88943704-646d-47f6-868c-408ed6f78e08)
-   [Google Vertex AI: pricing (checked 2026-11-14)](https://cloud.google.com/model-garden/pricing)
-   [Google Gemini API: own API pricing (checked 2026-11-14)](https://aistudio.google.com/docs/pricing#gemini-2.5-flash)
-   [DeepInfra: pricing (checked 2026-11-14)](https://deepinfra.com/google/gemini-2.5-flash)
