Last refreshed 2026-04-19. Next refresh: weekly.
Why use Gemma 2 9B Instruct on Replicate API?
Replicate API offers Gemma 2 9B Instruct with pay-as-you-go pricing at $0.10/1M input tokens. Replicate is a cloud-based platform that enables users to run machine learning models easily and efficiently.
Compare Gemma 2 9B Instruct across 6 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/gemma2-9b-it",
input={"prompt": "Hello"}google-deepmind/gemma2-9b-itRequest example
import replicate
# reads REPLICATE_API_TOKEN from env
# google-deepmind/gemma2-9b-it format: "owner/model-name" (latest version) or "owner/model-name:version-hash"
output = replicate.run(
"google-deepmind/gemma2-9b-it",
input={"prompt": "Hello"}
)
# Output is a list or generator depending on the model
print("".join(output))Gotchas
- Use provider model ID "google-deepmind/gemma2-9b-it", not the LLMReference slug "gemma-2-9b-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 2 9B Instruct Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| Fireworks AI | $0.20 | $0.20 |
| NVIDIA NIM | — | — |
| OpenRouter | — | — |
| Chutes AI | $0.10 | $0.30 |
| Replicate API | $0.10 | $0.10 |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.10 |
| Output tokens | $0.10 |
Capabilities
About Gemma 2 9B Instruct
Gemma 2 9B Instruct, developed by Google, is a state-of-the-art large language model based on the advanced Gemini framework. It is a decoder-only transformer model with 9 billion parameters, offering a balance between size and performance. The model is trained on an expansive dataset comprising 8 trillion tokens, including web documents, code, and mathematical text, a notable 30% increase from its predecessor, Gemma 1.1. This allows it to adeptly handle diverse tasks such as question answering, creative writing, coding, and mathematical problem-solving.