Gemma4 API Pricing
- Input / output
- $0.3723 / $0.9574 per 1M tokens
- Cache read
- $0.1064 / 1M
- Context
- 256K tokens
- Max output
- 256K tokens
As of November 21, 2026, Gemma4 costs $0.3723 per 1M input tokens and $0.9574 per 1M output tokens on Sarvam, with cache reads at $0.1064 per 1M tokens. It has a 262,144-token context window and returns up to 262,144 tokens per response.
Gemma4 pricing by provider
1 listing across 1 provider. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.
| Provider | Model name in LiteLLM | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| Sarvam | sarvam/gemma4 | $0.3723 | $0.9574 | $0.1064 | 256K |
What Gemma4 costs in practice
1,000 requests with 2,000 input and 500 output tokens each
| Sarvam | $1.223 |
100 long-document requests with 100,000 input and 2,000 output tokens each
| Sarvam | $3.915 |
Gemma4 cost calculator
At Sarvam's price ($0.3723 input, $0.9574 output per 1M tokens), 10,000 requests a day with 1,000 input and 500 output tokens each cost $8.51 a day, about $255 a month. Change the numbers for your workload, or compare it with other models.
- Per request
- $0.0008511
- Per day
- $8.51
- Per month (30 days)
- $255
Gemma4 features
Input: text, image. Output: text.
- Function calling
- Parallel tool calls
- Structured output
- Image input
- Audio input
- Video input
- Reasoning
- Prompt caching
Use Gemma4 with LiteLLM
Call Gemma4 through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.
from litellm import completion
response = completion(
model="sarvam/gemma4",
messages=[{"role": "user", "content": "Hello!"}],
)model_list:
- model_name: gemma4
litellm_params:
model: sarvam/gemma4
# credentials: see the provider's LiteLLM docs pagecurl http://0.0.0.0:4000/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $LITELLM_API_KEY" \
-d '{
"model": "gemma4",
"messages": [{"role": "user", "content": "Hello!"}]
}'Gemma4 FAQ
How much does Gemma4 cost?
Gemma4 costs $0.3723 per 1M input tokens and $0.9574 per 1M output tokens on Sarvam, with cache reads at $0.1064 per 1M tokens.
What is the context window of Gemma4?
Gemma4 has a 262,144-token context window and returns up to 262,144 tokens per response.
Which providers offer Gemma4?
Gemma4 is available from Sarvam through LiteLLM, using the model name sarvam/gemma4.
How do I call Gemma4 with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="sarvam/gemma4", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.
What features does Gemma4 support?
Gemma4 supports function calling, parallel tool calls, structured output, image input, reasoning and prompt caching. It does not support audio input and video input.
When did LiteLLM add Gemma4?
Gemma4 was added to LiteLLM's model price file on November 18, 2026.
Sources
Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Maintainers update it from each provider's published pricing, and this page is usually rebuilt within 20 minutes of every change. Provider pricing pages:
LiteLLM docs: Sarvam.
Provider pages: Sarvam.