Last refreshed 2026-04-19. Next refresh: weekly.
Why use Gemma 2B Instruct on Replicate API?
Replicate API offers Gemma 2B Instruct with pay-as-you-go pricing at $0.05/1M input tokens. Replicate is a cloud-based platform that enables users to run machine learning models easily and efficiently.
Compare Gemma 2B Instruct across 7 providers to find the best fit for your use caseSetup recipe
Python + curlpip install replicateexport REPLICATE_API_TOKEN=...import replicate
output = replicate.run(
"google-deepmind/gemma-2b-it",
input={"prompt": "Hello"}google-deepmind/gemma-2b-itRequest example
import replicate
# reads REPLICATE_API_TOKEN from env
# google-deepmind/gemma-2b-it format: "owner/model-name" (latest version) or "owner/model-name:version-hash"
output = replicate.run(
"google-deepmind/gemma-2b-it",
input={"prompt": "Hello"}
)
# Output is a list or generator depending on the model
print("".join(output))Gotchas
- Use provider model ID "google-deepmind/gemma-2b-it", not the LLMReference slug "gemma-2b-it".
- Replicate uses "owner/model-name" format (e.g. "meta/meta-llama-3-8b-instruct") for the latest version, or "owner/model-name:version-sha" to pin to a specific version. The REST endpoint splits owner and model-name into the path: /v1/models/{owner}/{model-name}/predictions.
- The examples expect REPLICATE_API_TOKEN; rename it only if your application config maps the new variable.
Compare Gemma 2B Instruct Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| Together AI | $0.10 | $0.10 |
| GCP Vertex AI | $0.04 | $0.12 |
| Cloudflare Workers AI | — | — |
| NVIDIA NIM | — | — |
| Alibaba Cloud PAI-EAS | — | — |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.05 |
| Output tokens | $0.25 |
Capabilities
About Gemma 2B Instruct
Gemma 2B Instruct is a large language model developed by Google, designed to balance performance and accessibility with its 2 billion parameters. Derived from the Gemini family, it excels in tasks such as text generation, code interpretation, and mathematical problem-solving. Built on a transformer decoder architecture, it features multi-query attention, RoPE, GeGLU activations, and RMSNorm. Trained on approximately 6 trillion tokens, including web documents, code, and mathematical content, it uses SFT and RLHF for instruction-tuning. Notable for its lightweight design permitting deployment on consumer-grade hardware, it's open-source and optimized for dialogue applications.