Compare prices for the same model
USD per 1 million uncached text tokens. Each cell lists input / output. Short-context Standard rates; cache, tools, regional fees, taxes and funding fees are excluded.
| Exact model | Official provider | OpenRouter | API429 |
|---|---|---|---|
Gemini 2.5 Flashgemini-2.5-flash | $0.3 / $2.5Standard; text; earlier generationSource | $0.3 / $2.5Public catalog rateSource | $0.09 / $0.75Base rate; full conditions below |
Gemini 2.5 Flash Litegemini-2.5-flash-lite | $0.1 / $0.4Standard; textSource | $0.1 / $0.4Public catalog rateSource | $0.03 / $0.12Base rate; full conditions below |
Gemini 2.5 Progemini-2.5-pro | $1.25 / $10Standard; text; input ≤200,000 tokensSource | $1.25 / $10Base tier; context overrides applySource | $0.375 / $3Base rate; full conditions below |
Gemini 3 Flashgemini-3-flash | Not verified in this review | No verified exact match | $0.15 / $0.9Base rate; full conditions below |
Gemini 3.1 Pro Lowgemini-3.1-pro-low | Not verified in this review | No verified exact match | $0.6 / $3.6Base rate; full conditions below |
Gemini 3.1 Pro Previewgemini-3.1-pro-preview | $2 / $12Standard; text; input ≤200,000 tokensSource | $2 / $12Base tier; context overrides applySource | $0.6 / $3.6Base rate; full conditions below |
Gemini 3.5 Flashgemini-3.5-flash | $1.5 / $9Standard; textSource | $1.5 / $9Public catalog rateSource | $0.45 / $2.7Base rate; full conditions below |
Gemini 3.5 Flash Litegemini-3.5-flash-lite | $0.3 / $2.5Standard; textSource | $0.3 / $2.5Public catalog rateSource | $0.09 / $0.75Base rate; full conditions below |
Gemini 3.6 Flashgemini-3.6-flash | $0.75 / $3.75Standard; text; introductory rates through 2026-12-31Source | $0.75 / $3.75Public catalog rateSource | $0.225 / $1.13Base rate; full conditions below |
Gemini 3.7 Flashgemini-3.7-flash | $0.75 / $3.75Standard; text; introductory rates through 2026-12-31Source | $0.75 / $3.75Public catalog rateSource | $0.225 / $1.13Base rate; full conditions below |
Gemini 3.8 Flashgemini-3.8-flash | $0.75 / $3.75Standard; text; introductory rates through 2026-12-31Source | $0.75 / $3.75Public catalog rateSource | $0.225 / $1.13Base rate; full conditions below |
OpenRouter amounts are model-list rates, excluding its separately listed platform fees. A missing quote means it was not verified for this comparison; it does not establish that the provider has no such model. Unverified reference figures are not filled with older or inferred prices.
The same workload, three budgets
Example: gemini-3.8-flash, 10 million input and 2 million output tokens across many short-context requests. No cache, tools or extra operations; this is not one 10-million-token prompt.
A changed token mix or context tier changes the result. For actual budgets, add billable reasoning, cache writes and tool use from your usage records.
Standard, free access and Batch
Google’s free tier has its own limits and conditions. It does not establish the price of an arbitrary production workload. Batch and Flex differ from Standard processing; use their own rates and limits if the job can wait.
Google publishes introductory rates for Gemini 3.8, 3.7 and 3.6 Flash through December 31, 2026. Do not treat them as permanent costs. This table compares the current Standard rates rather than the rates scheduled for January.
Text, thinking, caching and Google Cloud
Output pricing includes billable thinking tokens; audio, images, search and cache storage can have separate rates. Pro pricing also depends on prompt length. The short-context table is not a complete multimodal estimate.
Gemini Developer API pricing does not establish the same price or contract for Vertex AI / Google Cloud. If an integration requires a native Google format, region or agent feature, check API429’s compatibility matrix for the specific method.
All published Google / Gemini rates in API429
These rows come from the live public API429 catalog, including conditional rates. Publication is separate from access under your key. GET /v1/models confirms your permitted models.
| Model | Rate and condition |
|---|---|
Gemini 2.5 Flashgemini-2.5-flash | $0.09 / 1,000,000 cache-write input tokens $0.09 / 1,000,000 cached input tokens $0.09 / 1,000,000 input tokens $0.75 / 1,000,000 output tokens |
Gemini 2.5 Flash Litegemini-2.5-flash-lite | $0.03 / 1,000,000 cache-write input tokens $0.03 / 1,000,000 cached input tokens $0.03 / 1,000,000 input tokens $0.12 / 1,000,000 output tokens |
Gemini 2.5 Progemini-2.5-pro | $0.375 / 1,000,000 cache-write input tokens $0.375 / 1,000,000 cached input tokens $0.375 / 1,000,000 input tokens $3 / 1,000,000 output tokens |
Gemini 3 Flashgemini-3-flash | $0.15 / 1,000,000 cache-write input tokens $0.15 / 1,000,000 cached input tokens $0.15 / 1,000,000 input tokens $0.9 / 1,000,000 output tokens |
Gemini 3.1 Pro Lowgemini-3.1-pro-low | $0.6 / 1,000,000 cache-write input tokens $0.6 / 1,000,000 cached input tokens $0.6 / 1,000,000 input tokens $3.6 / 1,000,000 output tokens |
Gemini 3.1 Pro Previewgemini-3.1-pro-preview | $0.6 / 1,000,000 cache-write input tokens $0.6 / 1,000,000 cached input tokens $0.6 / 1,000,000 input tokens $3.6 / 1,000,000 output tokens |
Gemini 3.5 Flashgemini-3.5-flash | $0.45 / 1,000,000 cache-write input tokens $0.45 / 1,000,000 cached input tokens $0.45 / 1,000,000 input tokens $2.7 / 1,000,000 output tokens |
Gemini 3.5 Flash Litegemini-3.5-flash-lite | $0.09 / 1,000,000 cache-write input tokens $0.009 / 1,000,000 cached input tokens $0.09 / 1,000,000 input tokens $0.75 / 1,000,000 output tokens |
Gemini 3.6 Flashgemini-3.6-flash | $0.225 / 1,000,000 cache-write input tokens $0.0225 / 1,000,000 cached input tokens $0.225 / 1,000,000 input tokens $1.125 / 1,000,000 output tokens |
Gemini 3.7 Flashgemini-3.7-flash | $0.225 / 1,000,000 cache-write input tokens $0.0225 / 1,000,000 cached input tokens $0.225 / 1,000,000 input tokens $1.125 / 1,000,000 output tokens |
Gemini 3.8 Flashgemini-3.8-flash | $0.225 / 1,000,000 cache-write input tokens $0.0225 / 1,000,000 cached input tokens $0.225 / 1,000,000 input tokens $1.125 / 1,000,000 output tokens |
API429 catalog generated: . Public source.
Connect the model and check the result
Create an API429 key and check the permitted model IDs before migrating a workload. Keep the key on your server. Review the request contract and inspect actual usage and charges on a small representative job before increasing volume.
Sources and comparison method
Reference rates checked October 2, 2026. Recheck after a model release, promotion or pricing change. Reference figures are hidden after their review deadline; current API429 prices load from the public catalog. Neither individual contracts nor discounts are inferred.