Google: Gemma 4 26B A4B
The Google model in question is a 4 26B A4B language AI that supports input through various modalities, including text, image, and video. It also offers tools for reasoning and structured output capabilities are not listed. For users who prioritize flexibility in data types and require reasoning capabilities, this model may be worth considering due to its comprehensive input modalities and benchmarked performance with a blended score of 52.0 across two benchmarks. However, its price point is relatively high at $0.09 per million input tokens and $0.3 per million output tokens, which may deter those on a budget or with limited data requirements.
Benchmark results
Independent, published benchmarks. Blended score 50.9 across 2 benchmarks, last refreshed 2026-10-13. How scoring works →
| Benchmark | Measures | Score |
|---|---|---|
| AI Index | broad capability composite | 27.5 |
| EQ-Bench | emotional understanding in dialogue | 70.0 |
- Model ID
- google/gemma-4-26b-a4b-it
- Vendor
- Released
- April 2026
- Tokenizer
- Gemma
- Input Modalities
- image, text, video
- Output Modalities
- text
- Max Output
- 235,929 tokens
- Tool Calling
- ✓ supported
- Structured Output
- ✓ supported
- Reasoning Mode
- ✓ supported
- Vision
- ✓ accepts images
- Audio
- no
- Moderated
- no
What it costs in practice
Computed from the current $0.08/M input and $0.26/M output rates. Run your own numbers →
| Job | Tokens | Cost |
|---|---|---|
| Summarize a 50-page report | 30k in / 1.5k out | under $0.01 |
| Classify 1,000 customer emails | 500k in / 50k out | $0.05 |
| A month of a busy support chatbot | 5M in / 2M out | $0.89 |
Price & spec history
Tracked daily by PicksByModel since 2026-07-17.
| Date | Input /M | Output /M | Context |
|---|---|---|---|
| 2026-10-13 | $0.08 | $0.26 | 262,144 |
| 2026-10-12 | $0.04 | $0.22 | 262,144 |
| 2026-10-10 | $0.07 | $0.23 | 262,144 |
| 2026-10-06 | $0.08 | $0.26 | 262,144 |
| 2026-10-03 | $0.07 | $0.23 | 262,144 |
| 2026-09-29 | $0.08 | $0.26 | 262,144 |
| 2026-09-26 | $0.07 | $0.23 | 262,144 |
| 2026-09-13 | $0.09 | $0.30 | 262,144 |
| 2026-09-12 | $0.04 | $0.22 | 262,144 |
| 2026-09-11 | $0.04 | $0.22 | 1,000,000 |
| 2026-08-17 | $0.07 | $0.34 | 262,144 |
| 2026-08-10 | $0.12 | $0.40 | 262,144 |
| 2026-07-30 | $0.07 | $0.34 | 262,144 |
| 2026-07-28 | $0.14 | $0.42 | 262,144 |
| 2026-07-23 | $0.12 | $0.35 | 262,144 |
| 2026-07-19 | $0.07 | $0.34 | 262,144 |
| 2026-07-17 | $0.10 | $0.30 | 262,144 |
Category rankings
Where Google: Gemma 4 26B A4B places across the 7 categories it ranks in. How we rank →
| # | Category | Score |
|---|---|---|
| #15 | Real-Time ChatLatency · of 25 ranked | 118 |
| #17 | Self-Hosted / LocalCost · of 25 ranked | 117 |
| #21 | Cheap Bulk InferenceCost · of 25 ranked | 137 |
| #23 | Short-Form SummarizationWriting · of 25 ranked | 126 |
| #23 | Email DraftingWriting · of 25 ranked | 122 |
| #23 | Language LearningEducation · of 25 ranked | 122 |
| #23 | Chat CompanionPersonal · of 25 ranked | 126 |
Similar models
Google: Gemini 3.8 Flash
Google: Gemini 3.8 Flash (batch)
Google: Gemini 3.7 Flash
Google: Gemini 3.7 Flash (batch)
Google: Gemini 3.6 Flash
Google: Gemini 3.6 Flash (batch)
Quick answers
- How much does Google: Gemma 4 26B A4B cost?
- $0.08 per million input tokens and $0.26 per million output tokens.
- What is Google: Gemma 4 26B A4B 's context window?
- 262,144 tokens, roughly 393 pages of text in a single request.
- Does Google: Gemma 4 26B A4B support tool calling?
- It supports tool calling, structured output, a reasoning mode.
- Can Google: Gemma 4 26B A4B process images?
- Yes, it accepts image input.