# Gemini 3.5 Flash API pricing

The official API price of Gemini 3.5 Flash is $1.5 per 1M input tokens and $9 per 1M output tokens (as of 2026-11-12). Context window: 1.05M tokens, up to 65.5K output tokens per request. 37 providers sell it. The lowest is UnoRouter: $0.1857 input, $1.1142 output.

- Type: Text
- Context: 1.05M
- Max output: 65.5K
- Released: 2026-05-19
- Open weights: No

## Price by provider (USD per 1M tokens)

| Provider | Model id | Input | Output | Cached | Notes |
| --- | --- | --- | --- | --- | --- |
| [Google](https://ai.google.dev/gemini-api/docs/models) | gemini-3.5-flash | $1.5 | $9 | $0.15 | Official |
| [UnoRouter](https://unorouter.com/models) | gemini-3.5-flash | $0.1857 | $1.1142 | — | Lowest |
| [Kilo Gateway](https://kilo.ai) | google/gemini-3.5-flash | $0.75 | $4.5 | $0.075 |  |
| [302.AI](https://doc.302.ai) | gemini-3.5-flash | $1.5 | $9 | — |  |
| [302.AI](https://doc.302.ai) | gemini-3.5-flash-thinking | $1.5 | $9 | — |  |
| [Abacus](https://abacus.ai/help/api) | gemini-3.5-flash | $1.5 | $9 | $0.15 |  |
| [Cloudflare AI Gateway](https://developers.cloudflare.com/ai-gateway/) | google/gemini-3.5-flash | $1.5 | $9 | $0.15 |  |
| [CommandCode](https://commandcode.ai/docs/provider) | google/gemini-3.5-flash | $1.5 | $9 | $0.15 |  |
| [CrossModel](https://www.crossmodel.ai/docs) | gemini/gemini-3.5-flash | $1.5 | $9 | $0.15 |  |
| [Databricks](https://docs.databricks.com/aws/en/machine-learning/foundation-models/) | databricks-gemini-3-5-flash | $1.5 | $9 | $0.15 |  |
| [Eden AI](https://docs.edenai.co) | google/gemini-3.5-flash | $1.5 | $9 | $0.15 |  |
| [Eden AI](https://docs.edenai.co) | vertex/gemini-3.5-flash | $1.5 | $9 | $0.15 |  |
| [Eden AI](https://docs.edenai.co) | vertex/gemini-3.5-flash@eu | $1.5 | $9 | $0.15 |  |
| [Eden AI](https://docs.edenai.co) | vertex/gemini-3.5-flash@us | $1.5 | $9 | $0.15 |  |
| [FastRouter](https://fastrouter.ai/models) | google/gemini-3.5-flash | $1.5 | $9 | $0.15 |  |
| [Vertex](https://cloud.google.com/vertex-ai/generative-ai/docs/models) | gemini-3.5-flash | $1.5 | $9 | $0.15 |  |
| [Impossibl](https://impossibl.com/docs/models) | google/gemini-3.5-flash | $1.5 | $9 | $0.15 |  |
| [DevPass (LLM Gateway)](https://llmgateway.io/docs) | gemini-3.5-flash | $1.5 | $9 | $0.15 |  |
| [LLM Gateway](https://llmgateway.io/docs) | google-vertex/gemini-3.5-flash | $1.5 | $9 | $0.15 |  |
| [Merge Gateway](https://docs.merge.dev/merge-gateway) | google/gemini-3.5-flash | $1.5 | $9 | $0.15 |  |
| [NanoGPT](https://docs.nano-gpt.com) | google/gemini-3.5-flash | $1.5 | $9 | $0.15 |  |
| [NanoGPT](https://docs.nano-gpt.com) | google/gemini-3.5-flash-thinking | $1.5 | $9 | $0.15 |  |
| [NEAR AI Cloud](https://docs.near.ai/) | google/gemini-3.5-flash | $1.5 | $9 | $0.15 |  |
| [Neon](https://neon.com/docs) | gemini-3-5-flash | $1.5 | $9 | $0.15 |  |
| [Ofox](https://ofox.ai/docs) | google/gemini-3.5-flash | $1.5 | $9 | $0.15 |  |
| [OpenCode](https://opencode.ai/v2/docs/console/models/) | gemini-3.5-flash | $1.5 | $9 | $0.15 |  |
| [OpenRouter](https://openrouter.ai/models) | google/gemini-3.5-flash | $1.5 | $9 | $0.15 |  |
| [Opper](https://opper.ai/models) | gemini-3.5-flash | $1.5 | $9 | $0.15 |  |
| [OrcaRouter](https://docs.orcarouter.ai) | google/gemini-3.5-flash | $1.5 | $9 | $0.15 |  |
| [Prime Inference](https://docs.primeintellect.ai/inference/overview) | google/gemini-3.5-flash | $1.5 | $9 | — |  |
| [Requesty](https://requesty.ai/solution/llm-routing/models) | gemini-3.5-flash | $1.5 | $9 | $0.15 |  |
| [SAP AI Core](https://help.sap.com/docs/sap-ai-core) | gemini-3.5-flash | $1.5 | $9 | $0.15 |  |
| [Tempr Gateway](https://temprhq.io/docs/gateway-reference.html) | google/gemini-3.5-flash | $1.5 | $9 | $0.15 |  |
| [Vercel AI Gateway](https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway) | google/gemini-3.5-flash | $1.5 | $9 | $0.15 |  |
| [ZenMux](https://docs.zenmux.ai) | google/gemini-3.5-flash | $1.5 | $9 | $0.15 |  |
| [Poe](https://creator.poe.com/docs/external-applications/openai-compatible-api) | google/gemini-3.5-flash | $1.5152 | $9.0909 | $0.1515 |  |
| [Venice AI](https://docs.venice.ai) | gemini-3-5-flash | $1.55 | $9.45 | $0.155 |  |
| [Cortecs](https://api.cortecs.ai/v1/models) | gemini-3.5-flash | $1.649 | $9.899 | $0.165 |  |
| [Requesty](https://requesty.ai/solution/llm-routing/models) | gemini-3.5-flash@eu | $1.65 | $9.9 | $0.165 |  |
| [Xpersona](https://www.xpersona.co/docs) | gemini-3.5-flash | $1.55 | $12.2 | $0.155 |  |
| [AIHubMix](https://docs.aihubmix.com) | gemini-3.5-flash | $0.75 | $3.75 | $0.075 | Deprecated |
| [GitHub Copilot](https://docs.github.com/en/copilot) | gemini-3.5-flash | $1.5 | $9 | $0.15 | Deprecated |
| [Kenari](https://kenari.id/docs) | gemini-3-5-flash | — | — | — | Deprecated |

Providers are those listed by models.dev. This site has not vetted them one by one; each provider's own page has the binding price.

Prices and specs come from models.dev (MIT licence), updated 2026-11-12. Each provider's name links to its official docs. A provider priced at 0 usually includes the model in a subscription; it is not necessarily a free API.

https://apibook.ai/models/google/gemini-3.5-flash/