Google

Gemma 3 4B

Launched 2025-03-12 · Knowledge up to 2024-08 · Listed on OpenRouter 2025-03-13

Prices updated . Benchmarks updated .

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,...

You send / 1M

$0.050

tokens in

It replies / 1M

$0.100

tokens out

Context

131K

tokens it can read at once

Typical request

$0.0001

1,000 words in, 400 out

Benchmarks

BenchmarkScoreKindDateSource
Epoch Capabilities Index115.8Independent2025-03-12Epoch AI
GPQA Diamond23.2%Independent2026-08-28Epoch AI
OTIS Mock AIME7.5%Independent2026-08-28Epoch AI
Arena Elo (text)1,291Independent2026-10-28LMArena

Rankings on this site use the Epoch Capabilities Index, an independent composite. Lab-reported rows are the lab's own figures and are kept separate.

Data privacy

No training or retention: Yes. At least one provider serves it with zero data retention.

ProviderYou send / 1MIt replies / 1MUptimePrivacy policy
Parasail · bf16$0.040$0.05089%Read
DeepInfra · bf16$0.040$0.080n/aRead
DeepInfra · bf16$0.050$0.10099%Read
DeepInfra · bf16$0.075$0.15099%Read

Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.

What it can do

  • Reads: text, image
  • Writes: text
  • Weights: Open weights, restricted
  • Reasoning: No
  • Tool calling: No
  • Longest reply: 16K tokens

Compare with

Appears in

Estimate your monthly cost with Gemma 3 4B

Sources and licenses

  • OpenRouter: Prices, context windows, modalities and the model list come from the OpenRouter public API. Data: OpenRouter.
  • Vercel AI Gateway: The no-training flag comes from the Vercel AI Gateway model list.
  • models.dev: Lab launch dates, open-weights flags and knowledge cutoffs come from models.dev. Copyright (c) 2025 models.dev, MIT License.
  • Epoch AI: Independent benchmark scores and the Epoch Capabilities Index (ECI) come from Epoch AI's Benchmarking Hub, used under CC BY 4.0. Epoch AI, Capabilities & benchmarking, epoch.ai/benchmarks. Scores Epoch marks as external keep their original license, and the source is named on each score.
  • LMArena: Arena Elo (text, webdev and vision) comes from the LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset), CC BY 4.0, leaderboard date 2026-10-28.
  • Lab-reported scores, when an editor has added them, are the lab's own numbers. Each one links to the source and is labeled lab-reported. They are not used to rank the lists.
  • What a score measures: the benchmark guide.