Last refreshed 2026-05-19. Next refresh: weekly.
Why use CodeGemma 1.1 7B on NVIDIA NIM?
NVIDIA NIM offers CodeGemma 1.1 7B with competitive pricing. NVIDIA NIM is NVIDIA's deployment platform for GPU-accelerated inference microservices.
Compare CodeGemma 1.1 7B across 2 providers to find the best fit for your use caseSetup recipe
Docs fallbackUse the provider REST API or SDKCreate a provider API keymodel: codegemma-1.1-7bcodegemma-1.1-7bRequest example
codegemma-1.1-7b.Gotchas
No curated gotchas have been sourced for this exact provider/model route yet.
Compare CodeGemma 1.1 7B Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| NVIDIA NIM | — | — |
| DeepInfra | $0.05 | $0.15 |
Pricing
| Type | Rate |
|---|---|
| GPU Hour Rate | $1.00/GPU·hr |
| GPU Config | 1xH100 |
Capabilities
About CodeGemma 1.1 7B
CodeGemma 1.1 7B is Google DeepMind's CodeGemma model. It is deprecated (originally released 2024-05-03); use it only for reproducing earlier results or evaluating drift over time.
FAQ
What is the context window for CodeGemma 1.1 7B on NVIDIA NIM?
CodeGemma 1.1 7B supports a 8k token context window on NVIDIA NIM.
How does NVIDIA NIM compare to other CodeGemma 1.1 7B providers?
CodeGemma 1.1 7B is available from 2 providers. The cheapest input pricing is $0.05/1M tokens from DeepInfra.
Who created CodeGemma 1.1 7B?
CodeGemma 1.1 7B was created by Google DeepMind as part of the CodeGemma model family.
Is CodeGemma 1.1 7B open source?
CodeGemma 1.1 7B has open weights under Gemma according to the seed data, but that does not necessarily mean an OSI-approved open-source license.