Gemma 3 4B: API Pricing, Context Window & Benchmarks
Gemma 3 4B is a language model from Google, released in March 2025, with multimodal input.
Gemma 3 4B is a 4-billion-parameter vision-language model from Google, handling text and image input and generating text output. It features a 128K context window, multilingual support, and open weights. Suitable for question answering,
Gemma 3 4B benchmarks
Rankings
Quality Tracker
Gemma 3 4B Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Mon Jul 20 2026Gemma 3 4B pricing
Providers
Gemma 3 4B starts at $0.0200 per million input tokens and $0.0400 per million output tokens via DeepInfra.
| Provider | Input $/M | Output $/M | Workload 1M + 100K | Context in / out | TTFT p50 / p95 s | Output avg / p5 c/s | Success 7d | Modalities in / out |
|---|---|---|---|---|---|---|---|---|
 DeepInfra | $0.0200 | $0.0400 | $0.0240 | 131.1K/131.1K | —/0.20 | 33/— | — | / |
Workload cost uses 1M input tokens plus 100K output tokens at published list prices without assuming a cache hit. Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests. Success is calculated from completed versus failed requests over the trailing seven days.
Gemma 3 4B model size
Gemma 3 4B has 4 billion parameters and was trained on 4 trillion tokens. See how it compares to other models in the same parameter range.
Gemma 3 4B context window
Input and output token limits for Gemma 3 4B, plus how it ranks on long-context understanding.
Gemma 3 4B latency
Gemma 3 4B time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.
Gemma 3 4B examples
Recent arena outputs from Gemma 3 4B, picked from the highest-ranked matchups.
Gemma 3 4B license
Gemma 3 4B is released under the Gemma license, which permits commercial use, has 4.0B parameters, has a knowledge cutoff of August 2024.
- License
- Gemma
- Commercial use allowed
- Parameters
- 4.0B
- Knowledge cutoff
- August 2024
Google Gemma Terms of Use
Gemma 3 4B resources
Official sources for Gemma 3 4B: paper or system card, official launch post, model weights.
Gemma 3 4B vs other models
The most-compared alternatives to Gemma 3 4B are GPT-4o, Grok-2, DeepSeek-V2.5. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like Gemma 3 4B
Models ranked just above and below Gemma 3 4B by LLM Stats score.
FAQ
Common questions about Gemma 3 4B.