Gemini 2.5 Pro API pricing
Updated
Among the 3 providers we checked (prices read 2026-11-14), 3 tie for the lowest blended standard price for Gemini 2.5 Pro; Google Gemini API charges USD 1.25 per 1M input tokens and USD 10 per 1M output tokens. The median across 3 standard prices is USD 1.25 / USD 10. That is Google Gemini API's own API.
What does Google Gemini API charge for Gemini 2.5 Pro?
- Input
- USD 1.25
- Cached input
- USD 0.125
- Output
- USD 10
- Blended 3:1
- USD 3.438
USD per 1M tokens on Google (Gemini API), model gemini-2.5-pro, standard tier. Source, checked 2026-11-14.
Other Google Gemini API tiers: batch USD 0.625 / USD 5 · flex / spot USD 0.625 / USD 5 · priority USD 2.25 / USD 18.
Is a host cheaper than Google Gemini API? They tie. DeepInfra and Google Gemini API's own API both work out at USD 3.438 per 1M tokens on the 3:1 blend.
Gemini 2.5 Pro price per provider
USD per 1M tokens. Standard prices are ranked on a blend of 3 input tokens to 1 output token, cheapest first; the dearest standard price is 0% above the cheapest. Free rows, the maker's serving version and other service tiers follow, tagged and unranked.
| # | Provider | Input | Cached input | Output | Blended 3:1 | Context | Precision | Source |
|---|---|---|---|---|---|---|---|---|
| 1 | Google Gemini API tied cheapest makergemini-2.5-proNotes and source quotePaid tier. Prompts up to 200K tokens. Deprecated: from December 1, 2026 requests route to gemini-3.8-flash and bill at its rates. Cache storage is billed separately per hour. “Gemini 2.5 Pro Standard: Input price $1.25, prompts <= 200k tokens $2.50, prompts > 200k tokens … Output price (including thinking tokens) $10.00, prompts <= 200k tokens $15.00, prompts > 200k … Context caching price $0.125, prompts <= 200k tokens $0.25, prompts > 200k $4.50 / 1,000,000 tokens per hour (storage price)” | USD 1.25 | USD 0.125 | USD 10 | USD 3.438 | not stated | not stated | Google Gemini API page checked 2026-11-14 re-checked 2026-11-16 |
| 2 | DeepInfra tied cheapestgoogle/gemini-2.5-proNotes and source quote“$1.25 in $10.00 out / 1M tokens” | USD 1.25 | not published | USD 10 | USD 3.438 | 1,000,000 | not stated | DeepInfra page checked 2026-11-14 re-checked 2026-11-16 |
| 3 | Google Vertex AI tied cheapestgemini-2.5-proNotes and source quotePrompts up to 200K tokens; longer prompts bill at higher rates. “Gemini 2.5 Pro Input (text, image, video, audio) $1.25 … Text output (response and reasoning) $10.00 … cached $0.125” | USD 1.25 | USD 0.125 | USD 10 | USD 3.438 | not stated | not stated | Google Vertex AI page checked 2026-11-14 re-checked 2026-11-16 |
| — | Google Gemini API maker batchgemini-2.5-proNotes and source quotePaid tier. Prompts up to 200K tokens. Deprecated: from December 1, 2026 requests route to gemini-3.8-flash and bill at its rates. Cache storage is billed separately per hour. “Gemini 2.5 Pro Batch: Input price $0.625, prompts <= 200k tokens $1.25, prompts > 200k tokens … Output price (including thinking tokens) $5.00, prompts <= 200k tokens $7.50, prompts > 200k … Context caching price $0.125, prompts <= 200k tokens $0.25, prompts > 200k $4.50 / 1,000,000 tokens per hour (storage price)” | USD 0.625 | USD 0.125 | USD 5 | USD 1.719 | not stated | not stated | Google Gemini API page checked 2026-11-14 re-checked 2026-11-16 |
| — | Google Vertex AI batchgemini-2.5-proNotes and source quotePrompts up to 200K tokens; longer prompts bill at higher rates. Google lists one price for Flex and Batch. “Gemini 2.5 Pro Input (text, image, video, audio) $0.625 … Text output (response and reasoning) $5.00” | USD 0.625 | not published | USD 5 | USD 1.719 | not stated | not stated | Google Vertex AI page checked 2026-11-14 re-checked 2026-11-16 |
| — | Google Gemini API maker flex / spotgemini-2.5-proNotes and source quotePaid tier. Prompts up to 200K tokens. Deprecated: from December 1, 2026 requests route to gemini-3.8-flash and bill at its rates. Cache storage is billed separately per hour. “Gemini 2.5 Pro Flex: Input price $0.625, prompts <= 200k tokens $1.25, prompts > 200k tokens … Output price (including thinking tokens) $5.00, prompts <= 200k tokens $7.50, prompts > 200k … Context caching price $0.125, prompts <= 200k tokens $0.25, prompts > 200k $4.50 / 1,000,000 tokens per hour (storage price)” | USD 0.625 | USD 0.125 | USD 5 | USD 1.719 | not stated | not stated | Google Gemini API page checked 2026-11-14 re-checked 2026-11-16 |
| — | Google Gemini API maker prioritygemini-2.5-proNotes and source quotePaid tier. Prompts up to 200K tokens. Deprecated: from December 1, 2026 requests route to gemini-3.8-flash and bill at its rates. Cache storage is billed separately per hour. “Gemini 2.5 Pro Priority: Input price $2.25, prompts <= 200k tokens $4.50, prompts > 200k tokens … Output price (including thinking tokens) $18.00, prompts <= 200k tokens $27.00, prompts > 200k … Context caching price $0.225, prompts <= 200k tokens $0.45, prompts > 200k $8.10 / 1,000,000 tokens per hour (storage price)” | USD 2.25 | USD 0.225 | USD 18 | USD 6.188 | not stated | not stated | Google Gemini API page checked 2026-11-14 re-checked 2026-11-16 |
| — | Google Vertex AI prioritygemini-2.5-proNotes and source quotePrompts up to 200K tokens; longer prompts bill at higher rates. “Gemini 2.5 Pro Input (text, image, video, audio) $2.25 … Text output (response and reasoning) $18.00 … cached $0.225” | USD 2.25 | USD 0.225 | USD 18 | USD 6.188 | not stated | not stated | Google Vertex AI page checked 2026-11-14 re-checked 2026-11-16 |
- Ranked: standard-tier prices only, on (3 × input + output) ÷ 4. "Cached input: not published" means the provider's page shows no cache price; budget cached tokens at the input price.
- Other tiers (batch, flex / spot and priority): batch runs asynchronously within hours; flex and spot are best-effort and can be slow or refused at capacity; priority and fast cost more for reliability or speed. Shown, not ranked.
- Automated re-check 2026-11-16: a weekly job re-fetches each source page and looks for the recorded quote or prices. It is not a human review. "Re-checked" means it still found them. Rows with no re-check note show only the date the price was read.
- Precision is shown only where the provider states it; "not stated" is unknown, not full precision.
Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).
What does Gemini 2.5 Pro cost for a real workload?
Monthly cost over 30 days at each standard price, using the presets of the LLM API cost calculator. Providers without a cached price bill cached input at the input price.
- Support chatbot: 2,000 requests a day, 1,500 input tokens (60% cached), 300 output.
- RAG over documents: 1,000 requests a day, 8,000 input tokens (30% cached), 500 output.
- Coding agent (one developer): 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning.
| Provider | Support chatbot | RAG over documents | Coding agent (one developer) |
|---|---|---|---|
| Google Gemini API (maker) | USD 231.75 | USD 369.00 | USD 1,429 |
| DeepInfra | USD 292.50 | USD 450.00 | USD 3,150 |
| Google Vertex AI | USD 231.75 | USD 369.00 | USD 1,429 |
For the support chatbot, the cheapest price (Google Gemini API and 1 other, tied, USD 231.75 a month) saves USD 0 against the median (USD 231.75). For the coding agent the gap is USD 0 a month.
Which Gemini 2.5 Pro provider is cheapest for your traffic?
All 3 providers charge the same standard price, USD 1.25 input and USD 10 output per 1M tokens, so the per-token price does not decide between them: compare the cache and context lines below.
| Provider | No cache hits | 50% cached | 90% cached |
|---|---|---|---|
| Google Gemini API (maker) | USD 3.438 cheapest | USD 3.016 cheapest | USD 2.678 cheapest |
| DeepInfra (no cache price) | USD 3.438 cheapest | USD 3.438 | USD 3.438 |
| Google Vertex AI | USD 3.438 cheapest | USD 3.016 cheapest | USD 2.678 cheapest |
USD per 1M tokens, 3 input tokens to 1 output token, each provider's cheapest standard row. A provider without a cached price bills cached input at the input price. Any charge for writing to the cache, which some providers add, is not included.
2 of 3 providers publish a cached-input price below the input price: Google Gemini API (90% off), Google Vertex AI (90% off). DeepInfra publishes none, so cached tokens there bill at the input price.
DeepInfra states a context window of 1,000,000 tokens; Google Gemini API and Google Vertex AI do not state one.
Estimate your own bill
- LLM API cost calculator with Gemini 2.5 Pro preloaded: your traffic and cache rate, against any of 428 models.
- Token counter: count the tokens in your real prompts. Tokenizers differ, so the same text costs a different number of tokens on different models.
- Prompt caching calculator: what a higher cache-hit rate saves.
How does Gemini 2.5 Pro compare with other Google models?
The Google models whose cheapest standard price is closest to Gemini 2.5 Pro's (USD 3.438 blended):
| Model | Cheapest input | Cheapest output | Max context | Providers |
|---|---|---|---|---|
| Gemini 3.5 Flash | USD 1.50 | USD 9 | 1,048,576 | 3 |
| Gemini 4 Hydrogen | USD 1.50 | USD 7.50 | — | 3 |
| Gemini 4 Argon | USD 2 | USD 10 | 1,048,576 | 4 |
| Gemini 4 Carbon | USD 2 | USD 10 | 1,048,576 | 4 |
| Gemini 3.1 Pro Preview | USD 2 | USD 12 | 1,048,576 | 3 |
| Gemini 3.6 Flash | USD 0.75 | USD 3.75 | 1,048,576 | 3 |
Priced closest from other makers: GPT-5 (2025-08-07) (OpenAI, USD 3.438) · GPT-5.1 (OpenAI, USD 3.438) · GPT-4.1 (2025-04-14) (OpenAI, USD 3.50).
Compare Gemini 2.5 Pro with
- Gemini 3.1 Pro Preview vs Gemini 2.5 Pro: API price side by side
- Gemini 2.5 Pro vs Gemini 2.5 Flash: API price side by side
Also compared: vs Gemini 3.1 Pro Preview · vs Gemini 2.5 Flash.
Every Gemini 2.5 Pro price comparison · All model-vs-model price comparisons
All 428 models: API prices compared · Cheapest LLM APIs right now · LLM API price index (open data) · Download all prices (CSV, JSON) · Price change log
Questions
How much does the Gemini 2.5 Pro API cost per token?
From USD 1.25 per 1M input tokens (USD 0.00000125 per token) and USD 10 per 1M output tokens (USD 0.00001 per token) at the lowest standard prices we found. The median of 3 standard prices is USD 1.25 input and USD 10 output. Each price was read from the provider's own pricing page; the source is linked in its row.
Which provider is cheapest for Gemini 2.5 Pro?
Among the 3 providers we checked (prices read 2026-11-14), 3 are tied for the lowest price: Google Gemini API, DeepInfra and Google Vertex AI, each USD 3.438 per 1M on a blend of 3 input tokens to 1 output token. For input alone the lowest price is USD 1.25 (Google Gemini API and 2 others, tied); for output alone, USD 10 (Google Gemini API and 2 others, tied). Batch, flex, priority and fast tiers are shown in the table but not ranked.
Is Gemini 2.5 Pro cheaper from a host than from Google Gemini API?
They tie. DeepInfra and Google Gemini API's own API both work out at USD 3.438 per 1M tokens on the 3:1 blend.
Does Gemini 2.5 Pro have cached input pricing?
2 of 3 standard prices include one. The lowest is USD 0.125 per 1M at Google Gemini API; the median is USD 0.125. Providers without one bill cached input at the input price. What cached input means.
What is the Gemini 2.5 Pro context window?
1,000,000 tokens on every provider that states it.
How much does a coding agent cost per month on Gemini 2.5 Pro?
For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 1,429 a month at Google Gemini API, USD 1,429 at the median price and USD 3,150 at DeepInfra. Try your own numbers.
Is there a batch, flex or priority price for Gemini 2.5 Pro?
Yes: batch from Google Gemini API at USD 0.625 / USD 5; flex / spot from Google Gemini API at USD 0.625 / USD 5; priority from Google Gemini API at USD 2.25 / USD 18 per 1M input / output tokens. These tiers trade speed or availability for price (batch runs within hours, flex and spot can be slow or refused at capacity, priority and fast cost more for speed or reliability), so they are shown but not ranked.
Is Gemini 2.5 Pro free to use through an API?
No provider in our data lists a free price for Gemini 2.5 Pro as of 2026-11-14. Free tiers and credits by provider (checked 2026-11-14) lists general offers that do not name a model; all free LLM API models are on one page.