API pricing and cost
Nano Banana 2.1 pricing
Nano Banana 2.1 official API pricing is $1.50 per million input tokens and $7.50 per million output tokens. Third-party provider prices are compared below.
Covers the 2026-10-06 Nano Banana 2.1 release.
$1.50
Official input / 1M
Standard tier
$7.50
Official output / 1M
Standard tier
$2.70
Blended / 1M
4:1 input/output
$270.00
Example monthly cost
10K requests, 8K input + 2K output/request
Token charges only; tool calls, taxes, and other non-token fees are excluded.
Official API pricing
USD / 1M text tokens · Standard · Effective from 2026-10-06 · Last verified 2026-10-06
- InputStandard text tier, per million tokens
- $1.50
- OutputStandard text tier, per million tokens
- $7.50
Service tiers
USD per million text tokens for additional published service tiers.
| Tier | Input | Output | Cache read |
|---|---|---|---|
| Batch | $0.75 | $3.75 | — |
- Source: https://ai.google.dev/gemini-api/docs/pricing Source: https://ai.google.dev/gemini-api/docs/pricing; includes thinking tokens.
Other modalities
- image input: $1.50 / 1M tokens
Source: https://ai.google.dev/gemini-api/docs/pricing
- image output: $30.00 / 1M tokens
Source: https://ai.google.dev/gemini-api/docs/pricing; image output only: 1K=1120, 2K=1680, 4K=2520 tokens; input/text/search billed separately.
- image input: $0.75 / 1M tokens
batch · Source: https://ai.google.dev/gemini-api/docs/pricing
- image output: $15.00 / 1M tokens
batch · Source: https://ai.google.dev/gemini-api/docs/pricing; image output only: 1K=1120, 2K=1680, 4K=2520 tokens; input/text/search billed separately.
API providers (2)
Published USD text API rates across hosting providers for Nano Banana 2.1. Compare listed rates, effective dates, and service-tier notes for the same model.
On the example assistant workload above (10K requests, 8K input + 2K output/request; missing cache rates billed at full input), Google Cloud Vertex AI lists the lowest flat-rate total at $172.80/month.
| Provider | Input / 1M | Cached / 1M | Output / 1M | Additional tiers & notes |
|---|---|---|---|---|
| Google Cloud Vertex AIEffective from 2026-11-14 | $1.50 | $0.15 | $7.50 | Batch: $0.75/$3.75, $0.075 cached; Flex: $0.75/$3.75, $0.075 cached; Priority: $2.7/$13.5, $0.27 cached per 1M tokens. |
| Google Deep MindOfficialEffective from 2026-10-06 | $1.50 | — | $7.50 | Batch: $0.75/$3.75 per 1M tokens. |
What Nano Banana 2.1 costs to run
Four workloads costed at official standard rates. Cached-input share is an estimation assumption, not a provider guarantee; when no cached rate is published, all input is billed at the uncached rate. Non-token fees are excluded.
| Workload | Per request | Monthly tokens | Input | Output | Per month |
|---|---|---|---|---|---|
| Chatbotshort turns | 1,500 in · 500 out× 100,000 requests | 150M in · 50M out | $225.00 | $375.00 | $600.00$0.0060 / request |
| Assistant8K context · 90% cached | 8,000 in · 2,000 out× 10,000 requests | 80M in · 20M out | $120.00 | $150.00 | $270.00$0.03 / request |
| RAGlong input, cached · 50% cached | 24,000 in · 800 out× 20,000 requests | 480M in · 16M out | $720.00 | $120.00 | $840.00$0.04 / request |
| Coding agentlong output · 70% cached | 15,000 in · 4,000 out× 20,000 requests | 300M in · 80M out | $450.00 | $600.00 | $1,050.00$0.05 / request |
Monthly cost
$270.00
on Nano Banana 2.1
Per request
$0.03
80M in · 20M out a month
Split
$120.00 + $150.00
input + output
The same workload costs $100.00 on Gemini 3.1 Flash Image, the cheapest of the comparable models below.
- Gemini 3.1 Flash ImageGoogle Deep Mind · $1.00 / 1M blended$100.00
- Mistral Medium 3.5MistralAI · $2.70 / 1M blended$270.00
- GPT-5.6 TerraOpenAI · $2.70 / 1M blended$270.40
- Qwen3.5-Omni-PlusAlibaba · $2.78 / 1M blended$278.00
- Llama3-70B-InstructFacebook AI Research Lab · $2.82 / 1M blended$282.00
- Gemini 3 Pro ImageGoogle Deep Mind · $4.00 / 1M blended$400.00
Nano Banana 2.1 against comparable models
Benchmark-overlap peers and price-comparable same-type models, costed on the assistant workload above. All figures use the same workload and caching rule; lower price does not imply equivalent capability or service terms.
| Model | Basis | Blended / 1M | Per month | vs Nano Banana 2.1 |
|---|---|---|---|---|
| Gemini 3.1 Flash ImageGoogle Deep Mind | Lower-cost option | $1.00 | $100.00 | 63%cheaper · 2.7× |
| Mistral Medium 3.5MistralAI | Similar price | $2.70 | $270.00 | Same |
| Nano Banana 2.1Google Deep Mind · this model | This model | $2.70 | $270.00 | — |
| GPT-5.6 TerraOpenAI | Similar price | $2.70 | $270.40 | Same |
| Qwen3.5-Omni-PlusAlibaba | Similar price | $2.78 | $278.00 | 3%dearer |
| Llama3-70B-InstructFacebook AI Research Lab | Similar price | $2.82 | $282.00 | 4.4%dearer |
| Gemini 3 Pro ImageGoogle Deep Mind | Similar price | $4.00 | $400.00 | 48%dearer |
Catalog price position: #211 cheapest of 269 active priced models in the LLMLearner catalog (cheaper than 21% at the 4:1 mix; official headline rates).
Nano Banana 2.1 pricing questions
- How much does Nano Banana 2.1 cost per million tokens?
- Nano Banana 2.1 official API pricing is $1.50 per million input tokens and $7.50 per million output tokens. At the default 4:1 input-to-output mix, that is $2.70 per million blended tokens.
- Which API provider offers a lower price for Nano Banana 2.1?
- Among the 2 hosting providers listed on this page, Google Cloud Vertex AI lists lower flat text rates at $1.50 input and $7.50 output per million tokens ($172.80/month on the example Assistant workload, vs $270.00/month at Google Deep Mind's listed rate).
- What does Nano Banana 2.1 cost per month, and what is included?
- On the example Assistant workload (10,000 requests/month, 8,000 input and 2,000 output tokens/request), Nano Banana 2.1 costs about $270.00/month ($0.03/request). This includes token charges at the official rate only; tool calls, off-peak or batch tiers, and taxes are excluded.
- Is there a cheaper alternative to Nano Banana 2.1?
- Among the comparable models shown on this page, Gemini 3.1 Flash Image is cheaper at $1.00 per million blended tokens vs $2.70 for Nano Banana 2.1. Compare benchmarks before switching, as a lower rate does not guarantee equivalent quality or service terms. Across all 269 active priced models in the LLMLearner catalog, Nano Banana 2.1 ranks 211th cheapest (cheaper than 21% at the default 4:1 mix).
- Does Nano Banana 2.1 charge for cached input?
- Google Deep Mind publishes no cached-input rate for Nano Banana 2.1 here, so every input token is estimated at the full $1.50 per million.