Gemma 3 4B
- Input / output
- $0.04 / $0.05
- Providers
- 2
- Spread
- 2.2×
- 7 days
- 0%
- 30 days
- 0%
- Context
- 128K
Providers
| Provider | Input | Output | Blended | vs ref | Context | Uptime 1d | Price since |
|---|---|---|---|---|---|---|---|
ParasailCheapest bf16 | $0.04 | $0.05 | $0.0425 | ref | |||
DeepInfrabf16/flex bf16 | $0.04 | $0.08 | $0.05 | +18% | |||
| bf16 | $0.05 | $0.10 | $0.0625 | +47% | |||
DeepInfrabf16/priority bf16 | $0.075 | $0.15 | $0.0938 | +121% |
- ParasailCheapest$0.0425$0.04 in · $0.05 outref vs ref128K ctx99.9% uptimebf16
- bf16/flex$0.05$0.04 in · $0.08 out+18% vs ref128K ctx100% uptimebf16
- $0.0625$0.05 in · $0.10 out+47% vs ref128K ctx100% uptimebf16
- bf16/priority$0.0938$0.075 in · $0.15 out+121% vs ref128K ctx100% uptimebf16
Blended = (3 × input + output) / 4. Ref $0.0425 = median of cheapest 20%.
Price history
USD per 1M tokens · each step is a price change
Prices in USD / 1M tokens.
No provider has changed its price since tracking began on Oct 3, 2026.
Other pricing
| Offered by | Cache read |
|---|---|
| Parasail | $0.02 |
Changes
About
The cheapest provider for Gemma 3 4B is Parasail at $0.0425 per 1M tokens (blended), charging $0.04 per 1M input and $0.05 per 1M output tokens. 2 providers serve it; the most expensive charges 2.2× the typical price. Context window: 128K tokens. Prices tracked since Oct 3, 2026.
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,...
- Released
- Mar 13, 2025
- First tracked
- Oct 3, 2026
- Canonical slug
- google/gemma-3-4b-it
- Weights
- google/gemma-3-4b-it