Try Bifrost Enterprise free for 14 days.
Request access

gemma-4-31b Cost Calculator - Cerebras

Calculate the cost of using gemma-4-31b from Cerebras for your AI applications

Pricing data last updated:

gemma-4-31b Cost Calculator

Mode: Chat

Max: 131,072 tokens

Max: 40,960 tokens

Cost Breakdown

Input Cost$0.00099000
Output Cost$0.001490
Total Cost$0.002480

Pricing Details

Input: $0.0000009900 per token
Output: $0.00000149 per token
[ WE'RE OPEN SOURCE ]

Scale with the Fastest LLM Gateway

Built for enterprise-grade reliability, governance, and scale. Deploy in seconds.

Model Specifications

Capabilities

Function Calling
Vision
Reasoning

Limits

Max Input Tokens131,072
Max Output Tokens40,960
Max Tokens40,960

About gemma-4-31b

gemma-4-31b is a chat model from Cerebras, one of 9 chat models they offer. It is priced at $0.99 per 1M input tokens and $1.49 per 1M output tokens, ranking 2085 out of 3254 chat models by cost and cheaper than 36% of models in this category. gemma-4-31b supports vision, function calling, reasoning, structured output. It accepts up to 131K input tokens.

Pricing Information

Input Cost$0.99 per 1M tokens
Output Cost$1.49 per 1M tokens

Note: Use the interactive calculator above to estimate costs for your specific usage patterns.

Technical Specifications

Maximum Input Tokens131,072
Maximum Output Tokens40,960
Maximum Total Tokens40,960

Pro Tip

Use the maximum token limits shown above to understand the model's capacity. This model can handle up to 131,072 input tokens. The maximum output length is 40,960 tokens.

Model Capabilities

Function Calling - Execute custom functions and tools
Vision - Process and understand images
Advanced Reasoning - Complex problem-solving capabilities
Parallel Function Calling - Execute multiple functions simultaneously
Response Schema - Structured output formatting

How gemma-4-31b Pricing Compares

At $0.99 per 1M input tokens and $1.49 per 1M output tokens, gemma-4-31b ranks 2085 out of 3254 chat models by input cost. It is more expensive compared to the median of $0.52 for chat models, and is cheaper than 36% of models in this category.

gemma-4-31b is one of 9 Cerebras chat models, with support for vision, function calling, reasoning, structured output.

ModelProviderInput / 1M tokensOutput / 1M tokensvs gemma-4-31b
anthropic.claude-haiku-4-5-20251001-v1:0AWS Bedrock$1.00$5.00+1%
anthropic.claude-haiku-4-5@20251001AWS Bedrock$1.00$5.00+1%
apac.anthropic.claude-haiku-4-5-20251001-v1:0AWS Bedrock$1.10$5.50+11%

Alternatives to gemma-4-31b

Similar chat models from other providers

AWS Bedrock
anthropic.claude-haiku-4-5-20251001-v1:0
$1.00/1M input
+1% vs gemma-4-31b
AWS Bedrock
anthropic.claude-haiku-4-5@20251001
$1.00/1M input
+1% vs gemma-4-31b
AWS Bedrock
apac.anthropic.claude-haiku-4-5-20251001-v1:0
$1.10/1M input
+11% vs gemma-4-31b
Azure
claude-haiku-4-5
$1.00/1M input
+1% vs gemma-4-31b
Azure
o4-mini
$1.10/1M input
+11% vs gemma-4-31b

Frequently Asked Questions

Is gemma-4-31b cheaper than anthropic.claude-haiku-4-5-20251001-v1:0?

Yes. gemma-4-31b costs $0.99 per 1M input tokens compared to anthropic.claude-haiku-4-5-20251001-v1:0's $1.00 per 1M input tokens, making it 1% more affordable. Both are chat models and share support for vision, function calling, reasoning, web search, prompt caching, structured output.

How does gemma-4-31b pricing compare to the average chat model?

gemma-4-31b input pricing is $0.99 per 1M tokens, which is 92% above the median of $0.52 for chat models. It ranks 2085 out of 3254 chat models by input cost, making it cheaper than 36% of models in this category. For output, it costs $1.49 per 1M tokens compared to the median of $1.50.

What makes gemma-4-31b different from other Cerebras models?

Among Cerebras's 9 chat models, gemma-4-31b ranks 7 by input cost.

What are the best alternatives to gemma-4-31b?

The most comparable chat models to gemma-4-31b are: anthropic.claude-haiku-4-5-20251001-v1:0 from AWS Bedrock ($1.00/1M input tokens); anthropic.claude-haiku-4-5@20251001 from AWS Bedrock ($1.00/1M input tokens); apac.anthropic.claude-haiku-4-5-20251001-v1:0 from AWS Bedrock ($1.10/1M input tokens); claude-haiku-4-5 from Azure ($1.00/1M 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.

How do I check if Cerebras is down?

You can monitor Cerebras service health in real time on the Bifrost Cerebras Status page. It tracks current component status, active incidents, and historical reliability data pulled from the official status page every 60 seconds.

How do I calculate gemma-4-31b costs?

gemma-4-31b 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 $0.99 and generating 1M output tokens costs $1.49.