Last refreshed 2026-05-22. Next refresh: weekly.
Why use Gemma 3 27B on NVIDIA NIM?
NVIDIA NIM offers Gemma 3 27B with competitive pricing. NVIDIA NIM is NVIDIA's deployment platform for GPU-accelerated inference microservices.
Compare Gemma 3 27B across 5 providers to find the best fit for your use caseSetup recipe
Docs fallbackUse the provider REST API or SDKCreate a provider API keymodel: google/gemma-3-27b-itgoogle/gemma-3-27b-itRequest example
google/gemma-3-27b-it.Gotchas
- Use provider model ID "google/gemma-3-27b-it", not the LLMReference slug "gemma-3-27b-it".
Compare Gemma 3 27B Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| NVIDIA NIM | — | — |
| Novita AI | $0.12 | $0.20 |
| OpenRouter | $0.08 | $0.16 |
| AWS Bedrock | $0.50 | $0.50 |
| GCP Vertex AI | $0.08 | $0.16 |
Pricing
| Type | Rate |
|---|---|
| GPU Hour Rate | $1.00/GPU·hr |
| GPU Config | 1xH100 |
Capabilities
About Gemma 3 27B
Gemma 3 27B is Google DeepMind's Gemma 3 instruction-tuned model with openly available weights and a 131K-token context window.
FAQ
What is the context window for Gemma 3 27B on NVIDIA NIM?
Gemma 3 27B supports a 131k token context window on NVIDIA NIM.
How does NVIDIA NIM compare to other Gemma 3 27B providers?
Gemma 3 27B is available from 5 providers. The cheapest input pricing is $0.08/1M tokens from OpenRouter.
What API model ID do I use for Gemma 3 27B on NVIDIA NIM?
Use the model ID google/gemma-3-27b-it when calling NVIDIA NIM's API.
Who created Gemma 3 27B?
Gemma 3 27B was created by Google DeepMind as part of the Gemma 3 model family.
Is Gemma 3 27B open source?
Gemma 3 27B has open weights under Gemma according to the seed data, but that does not necessarily mean an OSI-approved open-source license.