Gemma 2B Instruct on Together AI

Gemma · Google DeepMind

ServerlessOpen Weights

Last refreshed 2026-06-15. Next refresh: weekly.

Why use Gemma 2B Instruct on Together AI?

Together AI offers Gemma 2B Instruct with pay-as-you-go pricing at $0.10/1M input tokens. Together AI is a platform for running open-source and proprietary LLMs with fast serverless and dedicated endpoints at competitive inference pricing.

Compare Gemma 2B Instruct across 7 providers to find the best fit for your use case
Input / 1M
$0.10
Output / 1M
$0.10
Cache
Not sourced
Batch
Not sourced

Setup recipe

Python + curl
Install
pip install together
Auth
export TOGETHER_API_KEY=...
Call
from together import Together
client = Together()  # reads TOGETHER_API_KEY from env
response = client.chat.completions.create(
    model="gemma-2b-it",
Model ID
gemma-2b-it

Request example

from together import Together

client = Together()  # reads TOGETHER_API_KEY from env
response = client.chat.completions.create(
    model="gemma-2b-it",
    messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)

Gotchas

  • Together uses "organization/model-name" format, e.g. "meta-llama/Llama-4-Scout-17B-16E-Instruct" or "Qwen/QwQ-32B". See the Together model catalog for the exact ID.
  • The examples expect TOGETHER_API_KEY; rename it only if your application config maps the new variable.

Compare Gemma 2B Instruct Across Providers

ProviderInput (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——
View all 7 providers →

Pricing

TypePrice (per 1M)
Input tokens$0.10
Output tokens$0.10

Capabilities

Structured Outputs

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.

Get Started