Gemma 3 4B
Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling.
- Input / output price
- $0.04 / $0.08 per 1M
- Context
- 131K tokens
- Released
- Mar 12, 2025
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
5 providers, cheapest first, OpenRouter last, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
Bedrock bedrock/gemma-3-4b-it | $0.04/M | $0.08/M |
Concentrate concentrate/gemma-3-4b | $0.04/M | $0.08/M |
DeepInfra deepinfra/gemma-3-4b-it | $0.05/M | $0.10/M |
Inference.net inference_net/gemma-3-4b-it | $0.05/M | $0.10/M |
OpenRouter openrouter/gemma-3-4b-it | $0.05/M | $0.10/M |
Is a provider down? AWS Bedrock status, OpenRouter status
Pricing
Averaged across 5 providers, in USD per 1M tokens after gateway discounts.
- Average input
- $0.05 per 1M
- Average output
- $0.09 per 1M
Cost by volume
Total cost from 0 to 1T tokens on the cheapest and most expensive provider.
Throughput and latency
30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.
Output speed
Higher is better6.0tokens/sacross providers
Response latency
Lower is better0.8sacross providers
Benchmarks
5 published scores from 1 source, each linked to where it was published.
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LiveCodeBenchGoogle | 12.6% | Mar 12, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| GPQA DiamondGoogle | 30.8% | Mar 12, 2025 |
Apps
Use Gemma 3 4B in the tools you already run. Each guide points the app at the Respan gateway.
Setup guides for more apps are in the integration docs.
Gemma 3 4B FAQ
Short answers, built from the data on this page.
Gemma 3 4B is a model from Google Gemini AI, released on Mar 12, 2025. Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling.
On the Respan gateway, Gemma 3 4B costs from $0.04 per 1M input tokens and $0.08 per 1M output tokens on Bedrock and Concentrate, after gateway discounts. Averaged across its 5 providers, it costs $0.05 per 1M input tokens and $0.09 per 1M output tokens.
Gemma 3 4B is available through 5 providers: Bedrock, Concentrate, DeepInfra, Inference.net, and OpenRouter.
Gemma 3 4B accepts up to 131K tokens of context on its largest provider route.
Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "gemma-3-4b-it". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
Gemma 3 4B has 5 published benchmark scores, including LiveCodeBench 12.6%, GPQA Diamond 30.8%, and IFEval 90.2%. Each score links to where it was published; the data is collected by Respan.
Certified where it counts.
Built to meet the security and privacy standards that enterprise and healthcare teams require.
ISO 27001
The internationally recognized standard for information security management.
SOC 2
Secure, compliant management of your data across all of our systems.
GDPR
Operated under GDPR, the world's strictest standard for data privacy.
HIPAA
HIPAA compliant, with a BAA available for healthcare teams.