This model is deprecated. We only continue performance benchmarking for the default 10k input token workload. Results for other workloads are historical and no longer updated.
Google has launched a newer model, Gemma 4 26B A4B. We suggest considering it instead.
For more information, see comparison of Gemma 4 26B A4B to other models and API provider benchmarks for Gemma 4 26B A4B.
Gemma 3 12B Instruct API Provider Benchmarking & Analysis
This analysis is intended to support you in choosing the best API provider of Gemma 3 12B Instruct for your use-case.
Fastest
Amazon
DeepInfraOutput speed
Total 3 providers
Lowest Latency
DeepInfraAmazonTime to first token
Total 3 providers
Lowest Price
Google (AI Studio)DeepInfraAmazonBlended price (per 1M tokens)
Total 3 providers
Gemma 3 12B is available through 3 API providers, each offering different performance characteristics and pricing. Below is a comparison of the key metrics across providers.
- For output speed, the top providers are Amazon (90.1 t/s) and DeepInfra (48.0 t/s).
- For latency, DeepInfra (0.99s) and Amazon (1.32s) offer the lowest time to first token.
- For pricing, Google (AI Studio) (0.00), DeepInfra (0.06), and Amazon (0.11) offer the lowest blended prices per 1M tokens.
Highlights
Pricing
Pricing: Cache Hit, Input, and Output
Pricing: Blended Price
Output Speed vs. Price
Speed
Measured by Output Speed (tokens per second)
Output Speed: Gemma 3 12B Instruct
Latency vs. Output Speed
Latency
Measured by Time (seconds) to First Token
Time to First Token
End-to-End Response Time
Seconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed
End-to-End Response Time
Key Comparison Metrics & API Features
Frequently Asked Questions
Common questions about Gemma 3 12B Instruct providers
Gemma 3 12B Instruct is available through 3 API providers: DeepInfra, Amazon, and Google (AI Studio). Each provider offers different performance characteristics and pricing.
Gemma 3 12B Instruct is currently available through 3 API providers that we benchmark and track.
The most affordable providers for Gemma 3 12B Instruct by blended price are Google (AI Studio) ($0.00 per 1M tokens), DeepInfra ($0.06 per 1M tokens), and Amazon ($0.11 per 1M tokens). Blended price uses a 7:2:1 cache hit/input/output token ratio.
The providers with the lowest input token pricing for Gemma 3 12B Instruct are Google (AI Studio) ($0.00 per 1M input tokens), DeepInfra ($0.05 per 1M input tokens), and Amazon ($0.09 per 1M input tokens).
The providers with the lowest output token pricing for Gemma 3 12B Instruct are Google (AI Studio) ($0.00 per 1M output tokens), DeepInfra ($0.15 per 1M output tokens), and Amazon ($0.29 per 1M output tokens).
1 of 3 providers support JSON mode for Gemma 3 12B Instruct: DeepInfra.
The best provider for Gemma 3 12B Instruct depends on your priorities: Amazon offers the highest output speed, DeepInfra has the lowest latency, and Google (AI Studio) provides the most competitive pricing.
When choosing a provider for Gemma 3 12B Instruct, consider: output speed (for throughput-intensive tasks), latency (for interactive applications requiring quick first responses), pricing (for cost-sensitive workloads), and API features like JSON mode or function calling.
Yes, provider performance can vary over time due to infrastructure changes, load balancing, and updates. We continuously benchmark all providers and display historical performance trends in the "Over Time" charts.
For information about Gemma 3 12B Instruct's intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview