# Gemma 4 26B A4B IT API pricing

No price from the maker itself is on record for Gemma 4 26B A4B IT. The lowest of 29 providers is NanoGPT: $0.01 per 1M input tokens and $0.031 per 1M output tokens (as of 2026-11-12). Context window: 262K tokens, up to 32.8K output tokens per request.

- Type: Text
- Context: 262K
- Max output: 32.8K
- Released: 2026-04-02
- Open weights: Yes

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

| Provider | Model id | Input | Output | Cached | Notes |
| --- | --- | --- | --- | --- | --- |
| [Google](https://ai.google.dev/gemini-api/docs/models) | gemma-4-26b-a4b-it | — | — | — | Official |
| [NanoGPT](https://docs.nano-gpt.com) | google/gemma-4-26b-a4b-it | $0.01 | $0.031 | $0.005 | Lowest |
| [NanoGPT](https://docs.nano-gpt.com) | google/gemma-4-26b-a4b-it:thinking | $0.01 | $0.031 | $0.005 |  |
| [Kilo Gateway](https://kilo.ai) | google/gemma-4-26b-a4b-it | $0.013 | $0.04 | $0.007 |  |
| [OpenRouter](https://openrouter.ai/models) | google/gemma-4-26b-a4b-it | $0.08 | $0.1 | $0.046 |  |
| [EmpirioLabs AI](https://docs.empiriolabs.ai) | gemma-4-26b-a4b | $0.05 | $0.29 | $0.025 |  |
| [OrcaRouter](https://docs.orcarouter.ai) | google/gemma-4-26b-a4b-it | $0.06 | $0.33 | $0.0075 |  |
| [Cloudflare Workers AI](https://developers.cloudflare.com/workers-ai/models/) | @cf/google/gemma-4-26b-a4b-it | $0.1 | $0.3 | $0.05 |  |
| [CoreWeave](https://docs.wandb.ai/inference) | google/gemma-4-26B-A4B-it | $0.1 | $0.3 | $0.05 |  |
| [Deep Infra](https://deepinfra.com/models) | google/gemma-4-26B-A4B-it | $0.07 | $0.34 | — |  |
| [DevPass (LLM Gateway)](https://llmgateway.io/docs) | gemma-4-26b-a4b-it | $0.07 | $0.34 | — |  |
| [LLM Gateway](https://llmgateway.io/docs) | deepinfra/gemma-4-26b-a4b-it | $0.07 | $0.34 | — |  |
| [Requesty](https://requesty.ai/solution/llm-routing/models) | gemma-4-26b-a4b-it | $0.07 | $0.34 | $0.07 |  |
| [Charm Hyper](https://hyper.charm.land) | gemma-4-26b-a4b-it | $0.098 | $0.334 | $0.049 |  |
| [Amazon Bedrock](https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html) | google.gemma-4-26b-a4b | $0.13 | $0.4 | — |  |
| [Hugging Face](https://huggingface.co/docs/inference-providers) | google/gemma-4-26B-A4B-it | $0.13 | $0.4 | — |  |
| [LLM Gateway](https://llmgateway.io/docs) | novita/gemma-4-26b-a4b-it | $0.13 | $0.4 | — |  |
| [Merge Gateway](https://docs.merge.dev/merge-gateway) | google/gemma-4-26b-a4b-it | $0.13 | $0.4 | — |  |
| [Novita AI](https://novita.ai/docs/guides/introduction) | google/gemma-4-26b-a4b-it | $0.13 | $0.4 | — |  |
| [Venice AI](https://docs.venice.ai) | google-gemma-4-26b-a4b-it | $0.13 | $0.4 | $0.05 |  |
| [SiliconFlow](https://cloud.siliconflow.com/models) | google/gemma-4-26B-A4B-it | $0.14 | $0.4 | $0.05 |  |
| [Cortecs](https://api.cortecs.ai/v1/models) | gemma-4-26b-a4b-it | $0.111 | $0.557 | — |  |
| [AKI.IO](https://aki.io/docs/) | gemma4-26b | $0.11215 | $0.56075 | — |  |
| [evroc](https://docs.evroc.com/products/think/overview.html) | google/gemma-4-26B-A4B-it | $0.144 | $0.575 | — |  |
| [Vertex](https://cloud.google.com/vertex-ai/generative-ai/docs/models) | google/gemma-4-26b-a4b-it-maas | $0.15 | $0.6 | $0.015 |  |
| [Vercel AI Gateway](https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway) | google/gemma-4-26b-a4b-it | $0.15 | $0.6 | $0.015 |  |
| [AI/ML API](https://docs.aimlapi.com) | google/gemma-4-26b-a4b-it | $0.1587 | $0.6348 | $0.1587 |  |
| [Scaleway](https://www.scaleway.com/en/docs/generative-apis/) | gemma-4-26b-a4b-it | $0.280375 | $0.56075 | — | Beta |
| [GreenPT](https://docs.greenpt.ai) | gemma4 | $0.57 | $1.71 | — |  |
| [NaN](https://nan.builders/docs/models) | gemma4 | $0 | $0 | — |  |
| [OpenRouter](https://openrouter.ai/models) | google/gemma-4-26b-a4b-it:free | $0 | $0 | — |  |
| [Tempr Gateway](https://temprhq.io/docs/gateway-reference.html) | google/gemma-4-26b-a4b-it | — | — | — |  |

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/gemma-4-26b-a4b-it/