# Gemma 4 31B IT API pricing

No price from the maker itself is on record for Gemma 4 31B IT. The lowest of 46 providers is DevPass (LLM Gateway): $0.1 per 1M input tokens and $0.25 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-4-31b-it | — | — | — | Official |
| [DevPass (LLM Gateway)](https://llmgateway.io/docs) | gemma-4-31b-it | $0.1 | $0.25 | $0.01 | Lowest |
| [LLM Gateway](https://llmgateway.io/docs) | consensusprotocol/gemma-4-31b-it | $0.1 | $0.25 | $0.01 |  |
| [LLM Gateway](https://llmgateway.io/docs) | runware/gemma-4-31b-it | $0.102 | $0.297 | $0.012 |  |
| [FastRouter](https://fastrouter.ai/models) | google/gemma-4-31b-it | $0.1 | $0.3 | — |  |
| [Kilo Gateway](https://kilo.ai) | google/gemma-4-31b-it | $0.1 | $0.34 | $0.1 |  |
| [NanoGPT](https://docs.nano-gpt.com) | google/gemma-4-31b-it:thinking | $0.1 | $0.34 | $0.1 |  |
| [CoreWeave](https://docs.wandb.ai/inference) | google/gemma-4-31B-it | $0.1 | $0.34 | $0.1 |  |
| [Venice AI](https://docs.venice.ai) | google-gemma-4-31b-it | $0.12 | $0.36 | $0.09 |  |
| [Chutes](https://llm.chutes.ai/v1/models) | google/gemma-4-31B-turbo-TEE | $0.12 | $0.37 | $0.012 |  |
| [NanoGPT](https://docs.nano-gpt.com) | TEE/gemma4-31b | $0.12 | $0.37 | $0.012 |  |
| [NanoGPT](https://docs.nano-gpt.com) | TEE/gemma4-31b:thinking | $0.12 | $0.37 | $0.012 |  |
| [Kenari](https://kenari.id/docs) | gemma-4-31b-it | $0.102857 | $0.405714 | $0.041143 |  |
| [OrcaRouter](https://docs.orcarouter.ai) | google/gemma-4-31b-it | $0.13 | $0.38 | $0.02 |  |
| [Abacus](https://abacus.ai/help/api) | google/gemma-4-31b-it | $0.14 | $0.4 | — |  |
| [Amazon Bedrock](https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html) | google.gemma-4-31b | $0.14 | $0.4 | — |  |
| [Crusoe](https://docs.crusoecloud.com/managed-inference/overview) | google/gemma-4-31b-it | $0.14 | $0.4 | $0.14 |  |
| [Friendli](https://friendli.ai/docs/guides/serverless_endpoints/introduction) | google/gemma-4-31B-it | $0.14 | $0.4 | — |  |
| [Hugging Face](https://huggingface.co/docs/inference-providers) | google/gemma-4-31B-it | $0.14 | $0.4 | — |  |
| [LLM Gateway](https://llmgateway.io/docs) | novita/gemma-4-31b-it | $0.14 | $0.4 | — |  |
| [Merge Gateway](https://docs.merge.dev/merge-gateway) | google/gemma-4-31b-it | $0.14 | $0.4 | — |  |
| [NanoGPT](https://docs.nano-gpt.com) | google/gemma-4-31b-it | $0.14 | $0.4 | $0.05 |  |
| [Novita AI](https://novita.ai/docs/guides/introduction) | google/gemma-4-31b-it | $0.14 | $0.4 | — |  |
| [Ollama Cloud](https://docs.ollama.com/cloud) | gemma4:31b | $0.14 | $0.4 | $0.05 |  |
| [Vercel AI Gateway](https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway) | google/gemma-4-31b-it | $0.14 | $0.4 | — |  |
| [Neuralwatt](https://portal.neuralwatt.com/docs) | gemma-4-31b | $0.144 | $0.42 | $0.0144 |  |
| [Deep Infra](https://deepinfra.com/models) | google/gemma-4-31B-it | $0.2 | $0.4 | — |  |
| [LLM Gateway](https://llmgateway.io/docs) | deepinfra/gemma-4-31b-it | $0.2 | $0.4 | — |  |
| [OpenRouter](https://openrouter.ai/models) | google/gemma-4-31b-it | $0.2 | $0.4 | — |  |
| [NanoGPT](https://docs.nano-gpt.com) | TEE/gemma-4-31b-it | $0.15 | $0.46 | $0.075 |  |
| [Cortecs](https://api.cortecs.ai/v1/models) | gemma-4-31b-it | $0.223 | $0.39 | — |  |
| [DigitalOcean](https://docs.digitalocean.com/products/gradient-ai-platform/details/models/) | gemma-4-31B-it | $0.18 | $0.5 | $0.036 |  |
| [ai&](https://docs.aiand.com/) | google/gemma-4-31b-it | $0.2 | $0.5 | $0.05 |  |
| [Infomaniak](https://www.infomaniak.com/en/hosting/ai-services/open-source-models) | google/gemma-4-31B-it | $0.25 | $0.5 | — |  |
| [Berget.AI](https://api.berget.ai) | google/gemma-4-31B-it | $0.280375 | $0.56075 | — |  |
| [Modular](https://docs.modular.com/models) | google/gemma-4-31b-it | $0.25 | $0.65 | $0.08 |  |
| [Tinfoil](https://docs.tinfoil.sh) | gemma4-31b | $0.4 | $1 | — |  |
| [SambaNova](https://docs.sambanova.ai/cloud/docs/get-started/supported-models) | gemma-4-31B-it | $0.38 | $1.15 | — |  |
| [SiliconFlow](https://cloud.siliconflow.com/models) | google/gemma-4-31B-it | $0.75 | $1 | $0.25 |  |
| [AI/ML API](https://docs.aimlapi.com) | google/gemma-4-31b-it | $1.04742 | $1.57642 | $1.04742 |  |
| [Regolo AI](https://docs.regolo.ai/) | gemma4-31b | $0.46 | $2.42 | — |  |
| [Opper](https://opper.ai/models) | gemma-4-31b-it | $0.46488 | $2.44062 | — |  |
| [LLMTR](https://llmtr.com/docs) | gemma-4 | $2 | $5 | $0.5 |  |
| [Lilac](https://docs.getlilac.com/inference/models) | google/gemma-4-31b-it | $0.11 | $0.35 | — | Deprecated |
| [AMD](https://developer.amd.com.cn/radeon/tokenfactory) | Gemma-4-31B-IT | $0 | $0 | $0 |  |
| [Bothub](https://bothub.ru/models) | gemma-4-31b-it:free | $0 | $0 | — |  |
| [InferX](https://model.inferx.net/endpoints) | gemma-4-31B-it-fp8 | $0 | $0 | — |  |
| [Nvidia](https://docs.api.nvidia.com/nim/) | google/gemma-4-31b-it | $0 | $0 | — |  |
| [OpenRouter](https://openrouter.ai/models) | google/gemma-4-31b-it:free | $0 | $0 | — |  |
| [Poe](https://creator.poe.com/docs/external-applications/openai-compatible-api) | google/gemma-4-31b | $0 | $0 | — |  |
| [QVAC](https://www.npmjs.com/package/@qvac/ai-sdk-provider) | gemma4-31b | $0 | $0 | — |  |
| [Requesty](https://requesty.ai/solution/llm-routing/models) | gemma-4-31b-it | $0 | $0 | — |  |
| [UnoRouter](https://unorouter.com/models) | gemma-4-31b-it:free | $0 | $0 | — |  |
| [Tempr Gateway](https://temprhq.io/docs/gateway-reference.html) | google/gemma-4-31b-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-4-31b-it/