CodeGemma Models by Google DeepMind
6 models2024Up to 8k ctxFrom $0.05/1M input
Details
ResearcherGoogle DeepMind
LicenseGemma
Commercial useCommercial use with conditions
Models6
Released2024
Max context8k
Capabilities
Structured Outputs2 of 6 models
About
CodeGemma is a family of 6 AI models by Google DeepMind, released in 2024.
Current Variants
Use-when guidance is derived from seed capabilities, context, release, and replacement fields.
4 in view2 retired
CodeGemma 1.1 2BCurrent
Use when the workload needs 8k context and 2B parameters.
2024-058k context2B parameters
Use when the workload needs 8k context, 7B parameters, and structured outputs.
2024-058k context7B parametersstructured outputs
CodeGemma 2BCurrent
Use when the workload needs 8k context and 2B parameters.
2024-048k context2B parameters
CodeGemma 7BCurrent
Use when the workload needs 8k context and 7B parameters.
2024-048k context7B parameters
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| CodeGemma 1.1 2B | Use when the workload needs 8k context and 2B parameters. | 2024-05 | 8k context2B parameters | Current |
| CodeGemma on Google Vertex AI | Use when the workload needs 8k context, 7B parameters, and structured outputs. | 2024-05 | 8k context7B parametersstructured outputs | Current |
| CodeGemma 2B | Use when the workload needs 8k context and 2B parameters. | 2024-04 | 8k context2B parameters | Current |
| CodeGemma 7B | Use when the workload needs 8k context and 7B parameters. | 2024-04 | 8k context7B parameters | Current |
Release Timeline
2 release groups2024-05
2 current · 1 retired
CodeGemma 1.1 2B
Current8k context2B parameters
CodeGemma 1.1 7B
Archived8k context7B parametersstructured outputs
CodeGemma on Google Vertex AI
Current8k context7B parametersstructured outputs
2024-04
2 current · 1 retired
CodeGemma 2B
Current8k context2B parameters
CodeGemma 7B
Current8k context7B parameters
CodeGemma 7B Instruct
Archived8k context7B parameters
Specifications(6 models)
| Model | Released | Context | Parameters | Structured Outputs |
|---|---|---|---|---|
| CodeGemma 1.1 2B | 2024-05 | 8k | 2B | No |
| CodeGemma on Google Vertex AI | 2024-05 | 8k | 7B | Yes |
| CodeGemma 2B | 2024-04 | 8k | 2B | No |
| CodeGemma 7B | 2024-04 | 8k | 7B | No |
Available From(4 providers)
Pricing
| Model | Provider | Input / 1M | Output / 1M | Type |
|---|---|---|---|---|
| CodeGemma 2B | Fireworks AI | $0.1 | $0.1 | Provisioned |
| CodeGemma on Google Vertex AI | GCP Vertex AI | $0.125 | $0.375 | Serverless |
| CodeGemma 7B | Fireworks AI | $0.2 | $0.2 | Serverless |
Frequently Asked Questions
- What is CodeGemma used for?
- CodeGemma is used for coding and structured outputs. The family description and listed model capabilities point to those workloads as the best fit.
- How does CodeGemma compare to Gemma 4?
- CodeGemma by Google DeepMind is strongest where you need coding, while Gemma 4 by Google DeepMind is the closest related family to check for multimodal. CodeGemma has 6 listed variants and reaches up to 8k context, while Gemma 4 reaches up to 256k context, so compare the specs and pricing tables before choosing a production model.
- Which CodeGemma model should I use?
- For the lowest listed input price, start with CodeGemma 1.1 7B through DeepInfra at $0.05/1M input tokens. For the most capable/latest local choice, evaluate CodeGemma on Google Vertex AI with 8k context and structured outputs.
