LLM prices / Google / Gemini 2.5 Flash
Google API · prices checked Oct 23, 2026
Gemini 2.5 Flash API pricing
Short answerGemini 2.5 Flash costs $0.3 per 1M input tokens and $2.5 per 1M output tokens on the Google API (standard price, checked Oct 23, 2026). A typical chatbot reply (1,500 tokens in, 400 out) costs $0.0014, so 1,000 replies a day is about $43.50 a month and 1M replies is $1,450. Google's own model page marks it limited access, so it is left out of our picks.
Limited access. Google lists Gemini 2.5 Flash as limited access on its model page. Prices stay here for old bills and migrations. The cheapest current Google model for a chatbot reply is Gemini 3.1 Flash-Lite.
Best for
- Long repeated prompts (agents, RAG with a fixed prefix): cached input bills at 10% of the normal input price.
- Bulk jobs that can wait: the batch API bills input at 50% of the standard price.
- Whole codebases or contracts in one prompt: 1.05M tokens of context.
- Reading more than text: takes image, video, audio input.
Skip if
- You are starting something new: Google marks it limited access. The cheapest current Google model for a chatbot reply is Gemini 3.1 Flash-Lite.
Rules: Best for = cheapest quarter of current models for a chatbot reply, top 3 on one of our 8 jobs, cache reads at 15% or less of input, batch at 60% or less, 1M+ context, non-text inputs. Skip if = not current on the provider's page, priciest quarter, text only, no cache or batch price, a long-prompt surcharge, preview, under 200K context, no tool calling. Price and spec facts only; we don't score answer quality.
What your volume costs
Pick a job and a monthly volume. Same prices as everything on this page; caching and batch applied where they make it cheaper.
Cost per task, 8 jobs
Per 1,000 requests and per month at a typical volume, billed the cheapest way the price list allows. The rank is among current models that fit the job.
| Job (links to the cheapest model for it) | Per 1,000 | A month | Rank among fits |
|---|---|---|---|
| Chatbota 1,500-token prompt (system prompt plus the conversation so far) and a 400-token reply | $1.45standard price | $43.50at 30,000 a month | does not fit |
| RAG (answer from your docs)6,000 tokens of retrieved passages plus the question, and a 500-token answer | $3.05standard price | $91.50at 30,000 a month | does not fit |
| Coding agent40,000 tokens of repo context and history, 30,000 of them repeated from the last step and billed at the cache-read price, 2,000 tokens out, tool calling required | $8.90with the repeated 30,000 tokens billed at the cache-read price | $26.70at 3,000 a month | does not fit |
| Tool-using agent12,000 tokens of instructions, tool definitions and history, 10,000 of them repeated from the last step and cached, 600 tokens out, tool calling required | $2.40with the repeated 10,000 tokens billed at the cache-read price | $24.00at 10,000 a month | does not fit |
| Vision (read an image)one image counted as 1,000 input tokens plus a 300-token question, and a 300-token answer. Providers count image tokens differently, so treat vision costs as a rough guide | $1.14standard price | $11.40at 10,000 a month | does not fit |
| Translationa 1,000-token passage in and about 1,100 tokens out (translations run a little longer than the source) | $3.05standard price | $30.50at 10,000 a month | does not fit |
| Batch extraction2,000 tokens per record in and 300 tokens of JSON out, through the batch API where there is one (results within 24 hours) | $0.68through the batch API | $67.50at 100,000 a month | does not fit |
| Summarize long documentsa 20,000-token document in and an 800-token summary out | $8.00standard price | $8.00at 1,000 a month | does not fit |
Cheaper and pricier alternatives
The current models just below and just above Gemini 2.5 Flash on the cost of 1,000 chatbot replies, with what differs. Price only, not quality.
Cheaper
- Gemini 3.1 Flash-Lite $0.970.67x the cost of a chatbot reply, same provider, takes image, video, audio, pdf too.
- DeepSeek Flash $0.930.64x the cost of a chatbot reply, DeepSeek, 1M context vs 1.05M, takes image too.
- GPT-5.6 Luna $0.780.54x the cost of a chatbot reply, OpenAI, 1.05M context vs 1.05M, takes image too.
Pricier
- Gemini 3.5 Flash-Lite $1.451.00x the cost of a chatbot reply, same provider, takes image, video, audio, pdf too.
- Gemini 3 Flash Preview $1.951.34x the cost of a chatbot reply, same provider, takes image, video, audio, pdf too.
- Gemini 3.8 Flash $2.621.81x the cost of a chatbot reply, same provider, takes image, video, audio, pdf too.
Every price tier
| Input | $0.3 per 1M tokens |
| Output | $2.5 per 1M tokens |
| Cache read (hit) | $0.03 (10% of the input price) |
| Batch API | $0.15 input / $1.25 output |
| Flex tier | $0.15 input / $1.25 output |
| Priority tier | $0.54 input / $4.5 output |
| API model id | gemini-2.5-flash |
| Status on the pricing page | listed |
Provider notes: prices are the Paid Tier text-token prices; explicit cache storage 1 USD per 1M tokens per hour; audio input is priced higher; see page
Model facts from Google
| Context window | 1,048,576 tokens |
| Max output | 65,536 tokens |
| Input types | text, image, video, audio |
| Tool calling | yes |
| Lifecycle | limited access |
| Provider note | Per ai.google.dev/gemini-api/docs/models: access limited to users who have used 2.5 models before; not deprecated. |
Source: https://ai.google.dev/gemini-api/docs/models/gemini-2.5-flash, checked Oct 24, 2026.
The 6 classic workloads
Per 1,000 requests at the standard price. "With caching" bills the repeated part of the prompt at the cache-read price (cache writes not counted); "via batch" uses the batch API price. Run your own token counts in the LLM API cost calculator.
| Workload | Gemini 2.5 Flashper 1,000 requests |
|---|---|
| Chatbot replya 1,500-token prompt (1,000 of it a fixed system prompt) and a 400-token answer | $1.45$1.18 with caching |
| Answer from your docs (RAG)6,000 tokens of retrieved context plus the question, a 500-token answer | $3.05$2.78 with caching |
| Summarize a long documenta 20,000-token document in, an 800-token summary out | $8.00$7.73 with caching |
| Coding agent step40,000 tokens of repo context and history (30,000 of it repeated from the last step), 2,000 out | $17.00$8.90 with caching |
| Batch extraction2,000 tokens per record in, 300 tokens of JSON out, sent through the batch API where there is one | $1.35$0.68 via batch |
| Long-document Q&Aa 150,000-token contract or codebase in one prompt, a 1,000-token answer | $47.50 |
What the numbers say
- Output costs 8.33333x input on Gemini 2.5 Flash, so for answer-heavy jobs the output price drives the bill; for document-heavy jobs (RAG, summaries, agents) input does.
- Caching matters: a coding-agent step that rereads 30,000 cached tokens costs 48% less than the same step uncached ($8.90 vs $17.00 per 1,000 steps, cache writes not counted). How to stop paying twice for repeated prompts: LLM semantic cache.
- Among 10 listed Google models it is the #4 cheapest for a chat reply.
- Same standard input/output price as Gemini 3.5 Flash-Lite; the differences are in caching, batch and long-prompt tiers.
Every listed Google model, cheapest first
Same chatbot workload, 1,000 replies.
| Model | Input / 1M | Output / 1M | 1,000 chat replies |
|---|---|---|---|
| Gemini 2.5 Flash-Litelimited access | $0.1 | $0.4 | $0.31 |
| Gemini 3.1 Flash-Lite | $0.25 | $1.5 | $0.97 |
| Gemini 3.5 Flash-Lite | $0.3 | $2.5 | $1.45 |
| Gemini 2.5 Flashlimited access | $0.3 | $2.5 | $1.45 |
| Gemini 3 Flash Preview | $0.5 | $3 | $1.95 |
| Gemini 3.8 Flash | $0.75 | $3.75 | $2.62 |
| Gemini 3.6 Flash | $0.75 | $3.75 | $2.62 |
| Gemini 2.5 Prolimited access | $1.25 | $10 | $5.88 |
| Gemini 4 Argon | $2 | $10 | $7.00 |
| Gemini 3.1 Pro Preview | $2 | $12 | $7.80 |
Closest price from other providers
The current model from each other provider whose chatbot-reply cost is nearest. Price only: we do not rank quality here.
| Model | Input / 1M | Output / 1M | 1,000 chat replies | vs Gemini 2.5 Flash |
|---|---|---|---|---|
| Claude Haiku 5.5Anthropic | $0.1 | $0.5 | $0.35 | 0.24x |
| GPT-5.6 LunaOpenAI | $0.2 | $1.2 | $0.78 | 0.54x |
| DeepSeek FlashDeepSeek | $0.3 | $1.2 | $0.93 | 0.64x |
Head-to-head
Price history
- Oct 17, 2026: Gemini 2.5 Flash first recorded: $0.3 input / $2.5 output per 1M tokens.
- Checked against the provider page on 2 dates: Oct 17, 2026, Oct 23, 2026.
Every change we record is on the LLM price changelog.
Sources
- Google API pricing: https://ai.google.dev/gemini-api/docs/pricing, checked Oct 23, 2026.
- Context, inputs and lifecycle: https://ai.google.dev/gemini-api/docs/models/gemini-2.5-flash, checked Oct 24, 2026.
- Dataset: llm-prices (every row names its page and check date) and /llm/prices.csv.
Prices change often. If one is out of date, email matt@tensorust.com and we will fix it.