Calculate the cost of using gemma4 from Sarvam for your AI applications
Pricing data last updated:
Mode: Chat
Max: 262,144 tokens
Max: 262,144 tokens
Built for enterprise-grade reliability, governance, and scale. Deploy in seconds.
gemma4 is a chat model from Sarvam, one of 7 chat models they offer. It is priced at $0.37 per 1M input tokens and $0.96 per 1M output tokens, ranking 2561 out of 5562 chat models by cost and cheaper than 54% of models in this category. gemma4 supports vision, function calling, reasoning, prompt caching, structured output. Its 262K-token context window is in the top 49% among chat models.
Note: Use the interactive calculator above to estimate costs for your specific usage patterns.
Use the maximum token limits shown above to understand the model's capacity. This model can handle up to 262,144 input tokens. The maximum output length is 262,144 tokens.
At $0.37 per 1M input tokens and $0.96 per 1M output tokens, gemma4 ranks 2561 out of 5562 chat models by input cost. It is more affordable compared to the median of $0.47 for chat models, and is cheaper than 54% of models in this category.
gemma4 is one of 7 Sarvam chat models, with support for vision, function calling, reasoning, prompt caching, structured output. its 262K-token context window places it in the top 49% of chat models.
| Model | Provider | Input / 1M tokens | Output / 1M tokens | vs gemma4 |
|---|---|---|---|---|
| amazon.nova-2-lite-v1:0 | AWS Bedrock | $0.30 | $2.50 | -19% |
| apac.amazon.nova-2-lite-v1:0 | AWS Bedrock | $0.40 | $3.31 | +6% |
| eu.amazon.nova-2-lite-v1:0 | AWS Bedrock | $0.43 | $3.60 | +15% |
Similar chat models from other providers
No. gemma4 costs $0.37 per 1M input tokens while amazon.nova-2-lite-v1:0 costs $0.30 per 1M input tokens, making amazon.nova-2-lite-v1:0 19% more affordable for input. However, gemma4 may offer different capabilities or performance characteristics that justify the price difference.
gemma4 input pricing is $0.37 per 1M tokens, which is 21% below the median of $0.47 for chat models. It ranks 2561 out of 5562 chat models by input cost, making it cheaper than 54% of models in this category. For output, it costs $0.96 per 1M tokens compared to the median of $1.56.
Among Sarvam's 7 chat models, gemma4 ranks 6 by input cost.
The most comparable chat models to gemma4 are: amazon.nova-2-lite-v1:0 from AWS Bedrock ($0.30/1M input tokens); apac.amazon.nova-2-lite-v1:0 from AWS Bedrock ($0.40/1M input tokens); eu.amazon.nova-2-lite-v1:0 from AWS Bedrock ($0.43/1M input tokens); us.amazon.nova-2-lite-v1:0 from AWS Bedrock ($0.33/1M input tokens). These alternatives were selected based on similar capabilities, pricing, and provider diversity. You can compare any of these models in detail using the Bifrost Model Library.
gemma4 is priced based on input and output tokens. Use the interactive calculator at the top of this page to estimate costs for your specific workload. Enter your expected input and output tokens volume and the calculator will show the total cost breakdown. For reference, processing 1M input tokens costs $0.37 and generating 1M output tokens costs $0.96.