Google: Gemma 3 4B
google/gemma-3-4b-it
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
OpenRouter's catalog lists google/gemma-3-4b-it as a Google text-and-image to text model with a 131,072-token context window and text-only output. The catalog describes vision-language input, coverage of more than 140 languages, and gains in mathematics, reasoning, and conversational ability, but these are catalog claims rather than verified results. Sparse benchmark metadata reports only a coding index, and no independent model card was available in this source pack.[1]
Strengths
- The OpenRouter catalog reports text and image inputs with text outputs, positioning the variant for vision-language prompts.[1]
- A listed context length of 131,072 tokens may help with long documents or extended conversations.[1]
- The catalog claims support for more than 140 languages and lists structured-output and response-format parameters.[1]
Limitations
- Evidence is limited to OpenRouter's catalog; an independent model card was not available in this source pack.[1]
- Benchmark metadata is sparse: only a coding index is populated, while agentic and general intelligence fields are empty. Validate on the intended workload.[1]
- The catalog lists a knowledge cutoff of August 31, 2024, and does not establish safety behavior, licensing, or deployment requirements.[1]
Where to use it
- Multilingual chat, drafting, or question answering may be reasonable where the catalog's broad language claim can be validated for target languages.[1]
- Image-plus-text tasks such as captioning, visual question answering, or information extraction may fit, subject to task-specific testing.[1]
- Long-document summarization or structured-response workflows may benefit from the reported context window and supported output controls.[1]
Sources
- [1] OpenRouter catalog · Google: Gemma 3 4BSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
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,...
Specifications
- Model ID
- google/gemma-3-4b-it
- Creator
- Added to OpenRouter
- 13.03.2025
- Context length
- 131,072
- Modality
- text+image->text
- Input modalities
- text, image
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0.050 / out $0.100
- Knowledge cutoff
- 31.08.2024
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | — |
| Coding | CC — below the B band | — |
| Agents | No measurement | parameters: structured_outputs |
| Writing | No measurement | output: text |
| Reasoning | No measurement | — |
| Document analysis | No measurement | — |
| Vision | No measurement | input: image |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
| Source | Benchmark | Value | Grade | Data retrieved |
|---|---|---|---|---|
| Artificial Analysis | Coding index | 2.7 | CC — below the B band | 13.11.2026 |
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| Parasailbf16 | 131,072 | $0.040 | $0.050 | — | — | 96.67% |
| DeepInfrabf16 | 131,072 | $0.050 | $0.100 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.