AI Observatory / Model Radar
Google / google/gemma-3-4b-it
Google: 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,...
131,072
Context
16,384
Max output
$0.04 / 1M
Prompt price
2025-03-13
Created
01 / Snapshot
Pricing, context, modalities, and parameters.
Model Radar detail pages stay neutral and operator-readable: core metadata first, then workflow fit.
| Provider | Input modalities | text, image | |
|---|---|---|---|
| Output modalities | text | Prompt price | $0.04 / 1M |
| Completion price | $0.08 / 1M | Request price | N/A |
| Context length | 131,072 | Max completion tokens | 16,384 |
| Supported parameters | frequency_penalty, logit_bias, max_tokens, min_p, presence_penalty, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, top_k, top_p | ||
Best for
google/gemma-3-4b-it
Google: 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,...
Deep analysis
Cross-modal work
High-volume usage
vision
low-cost
03 / Colophon
Routes and exits.
Each model page stays simple: overview, compare, related models, then back to the public hub.