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 #46 of 348 models in the default AI Benchmark Hub order (quality first, then cost). At $0.20 blended per million tokens, it is cheaper than 81% of models with published API pricing. Its 262,144-token context window is about the catalog median (262,144 tokens). A quality index of 72.5 places it at #46 of 59 models with an Arena Elo signal.
Context
Max output: 16384
Pricing
Output / 1M: 0.34
Blend / 1M: 0.20
Quality
Provider
Moderated: no
Monthly cost at this blended rate
Estimated API spend if every token is billed at $0.20per 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 | $0.20 |
| 10,000,000 | $2.05 |
| 100,000,000 | $20.50 |
Related models
Same lab, similar price, or similar quality — useful next comparisons.
More from Google
- Gemini 3.7 Flash$2.25 / 1M · Q 86.7
- Gemini 3.8 Flash$2.25 / 1M · Q 85.5
- Gemini 3.6 Flash$2.25 / 1M · Q 83.7
- Gemini 3.5 Flash$5.25 / 1M · Q 81.2
- Gemini 3.1 Pro Preview$7.00 / 1M · Q 80.4
Closest API price
- Nemotron 3.5 Content Safety$0.20 / 1M
- Step 3.5 Flash$0.20 / 1M
- Ministral 3 14B 2512$0.20 / 1M
- Voxtral Small 24B 2507$0.20 / 1M
- Llama 4 Scout$0.20 / 1M
Closest quality index
- DeepSeek V3.2$0.33 / 1M · Q 72.4
- DeepSeek V3.2 Exp$0.34 / 1M · Q 72.4
- Qwen3.5-27B$0.88 / 1M · Q 72.3
- Qwen3.5-122B-A10B$1.34 / 1M · Q 72.3
- GLM 4.6$1.09 / 1M · Q 71.1