Gemma 4 26B A4B
Google · google/gemma-4-26b-a4b-it
Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...
Gemma 4 26B A4B ranks #36 of 377 models in the default AI Benchmark Hub order (quality first, then cost). At $0.13 blended per million tokens, it is cheaper than 90% of models with published API pricing. Its 262,144-token context window is about the catalog median (262,144 tokens).
Context
Max output: 32768
Pricing
Output / 1M: 0.20
Blend / 1M: 0.13
Quality
Provider
Moderated: no
Monthly cost at this blended rate
Estimated API spend if every token is billed at $0.13per million (the blend of this model's input and output prices). Real bills depend on the input/output mix.
| Tokens / month | Est. cost (USD) |
|---|---|
| 1,000,000 | $0.13 |
| 10,000,000 | $1.32 |
| 100,000,000 | $13.25 |
Related models
Same lab, similar price, or similar quality — useful next comparisons.
More from Google
- Lyria 3 Pro Preview$0.00 / 1M
- Lyria 3 Clip Preview$0.00 / 1M
- Gemma 3 4B$0.07 / 1M
- Gemma 3 12B$0.10 / 1M
- Gemma 3 27B$0.21 / 1M
Closest API price
- Nemotron 3.5 Lightning$0.14 / 1M
- DeepSeek V4 Flash 0423$0.14 / 1M
- Mistral Small 3.2 24B$0.14 / 1M
- Solar Mini 4$0.12 / 1M
- Schematron V2 Small$0.14 / 1M