Gemini 2.5 Flash Image (Nano Banana)
gemini The API that serves this model and sets the prices shown here. gemini-2.5-flash-image The model identifier to send in API requests. LLM Generates text from a prompt, so it can be compared with other LLMs on price and capability. Small The fast, low-latency tier of a model family, suited to high-volume or simple tasks. Retired Oct 02, 2026 This model has been retired and can no longer be relied on.Provider: google
Knowledge cutoff: June 2024
Gemini 2.5 Flash Image (gemini-2.5-flash-image) is deprecated and will be shut down on October 2, 2026; migrate to Gemini 3.1 Flash Image or Gemini 3.1 Flash Lite Image to avoid service disruption.
Sticker prices & cost-per-token
List rates as published by google, before any volume or enterprise discounts.
$0.30
$0.039
32,768 tokens
32,768
tokens per response (includes reasoning tokens)
Closed weights
$0.03
Get this data free
Want to stay updated on price changes on this model? Pull this data free (no API key required) here:
curl "https://coolhandlabs.com/api/v2/inference_apis?q%5Bmodel_eq%5D=gemini-2.5-flash-image&q%5Bsource_api_eq%5D=gemini"Pricing History
| Effective | Price |
|---|---|
| Oct 5, 2026 – present | Input cost: $0.30 / 1M, Output cost: $0.039 / 1M, Cached input cost: $0.03 / 1M, Cache creation cost: $0.00 / 1M, 5-minute cache write cost: $0.00 / 1M, 1-hour cache write cost: $0.00 / 1M, Reasoning output cost: $0.00 / 1M, Cache storage cost: $0.00 / 1M/hr |
| Aug 16, 2026 – Oct 5, 2026 | Input cost: $0.30 / 1M, Output cost: $30.00 / 1M, Cached input cost: $0.03 / 1M, Cache creation cost: $0.00 / 1M, 5-minute cache write cost: $0.00 / 1M, 1-hour cache write cost: $0.00 / 1M, Reasoning output cost: $0.00 / 1M, Cache storage cost: $0.00 / 1M/hr |
History
Last change detected October 5, 2026 (3 days ago) by an automated scan.
| Date | Changed by | What changed |
|---|---|---|
| Aug 16, 2026 | Unknown | Initial record created |
Source
https://ai.google.dev/pricingComparable models
No comparable models identified yet.
Reliability
No reliability incidents recorded in the last 90 days.
Frequently asked questions
Gemini 2.5 Flash Image (Nano Banana) (google) costs $0.30 per 1M input tokens and $0.039 per 1M output tokens, as last published by google.
Gemini 2.5 Flash Image (Nano Banana) has a context window of 32,768 tokens (the maximum combined input and output it can handle in a single request).
Gemini 2.5 Flash Image (Nano Banana) sits in the small size tier. Size tiers run from micro (small enough to run on a device) through small, medium and large to extra large (frontier flagships), and are assigned from the model's family, naming and limits rather than its price.
Gemini 2.5 Flash Image (Nano Banana) can generate up to 32,768 tokens in a single response. Reasoning (thinking) tokens count toward this limit.
Gemini 2.5 Flash Image (Nano Banana)'s training data runs through June 2024, so it may not know about later events. Coolhand records the cutoff at month precision, since providers often publish only the month.
Gemini 2.5 Flash Image (Nano Banana) accepts image and text as input and produces image and text as output, as recorded in the Coolhand catalog.
No — the weights of Gemini 2.5 Flash Image (Nano Banana) have not been released, so it is only available through hosted APIs.
Yes — google deprecated Gemini 2.5 Flash Image (Nano Banana) on October 2, 2026. Gemini 2.5 Flash Image (gemini-2.5-flash-image) is deprecated and will be shut down on October 2, 2026; migrate to Gemini 3.1 Flash Image or Gemini 3.1 Flash Lite Image to avoid service disruption.
google retired Gemini 2.5 Flash Image (Nano Banana) on October 2, 2026.
Since Gemini 2.5 Flash Image (Nano Banana) is deprecated, google customers are moving to Google Gemma 3 12B, Gemma 3 4B IT, and Deep Research Max Preview (Apr-21-2026).
Call GET https://coolhandlabs.com/api/v2/inference_apis?q[source_api_eq]=gemini&q[model_eq]=gemini-2.5-flash-image — free, no API key required, and scoped to just this model since source_api and model together are unique. See https://coolhandlabs.com/docs for the full REST API reference.
Coolhand also tracks Gemini 3.1 Flash Lite Preview, Google Gemma 3 12B, Gemma 3 4B IT, Deep Research Max Preview (Apr-21-2026), Deep Research Preview (Apr-21-2026), and Gemini 2.5 Flash from google. Some may already be deprecated, so check each model's status alongside its current pricing.
| Model | Input cost | Output cost | Context window | Max output tokens | Status |
|---|---|---|---|---|---|
| Gemini 3.1 Flash Lite Preview | $0.25/1M $0.0000002500 | $1.50/1M $0.0000015000 | 1,048,576 | 65,536 |
Deprecated Aug 13, 2026
|
| Google Gemma 3 12B via Bedrock | $0.09/1M $0.0000000900 | $0.29/1M $0.0000002900 | 131,072 | 8,192 | Active |
| Gemma 3 4B IT via Bedrock | $0.04/1M $0.0000000400 | $0.08/1M $0.0000000800 | 131,072 | 4,096 | Active |
| Deep Research Max Preview (Apr-21-2026) | $2.00/1M $0.0000020000 | $12.00/1M $0.0000120000 | — | 65,536 | Active |
| Deep Research Preview (Apr-21-2026) | $2.00/1M $0.0000020000 | $12.00/1M $0.0000120000 | — | 65,536 | Active |
| Gemini 2.5 Flash | $0.30/1M $0.0000003000 | $2.50/1M $0.0000025000 | 1,048,576 | 65,536 | Active |
Track LLM pricing and deprecations automatically.
Start free