Gemma 4 26B A4B
GoogleGemma 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...
In
$0.06
Out
$0.18
Blended
$0.09
Where to buy this model
15 access routes| Route | In | Out | Blended | vs |
|---|---|---|---|---|
| ● Darkbloom cheapest | $0.04 | $0.15 | $0.07 | - |
| ● Makora | $0.08 | $0.10 | $0.09 | +29% |
| ● PrimeIntellect bf16 | $0.06 | $0.18 | $0.09 | +29% |
| ● AkashML fp4 | $0.07 | $0.24 | $0.11 | +57% |
| ● DekaLLM bf16 | $0.06 | $0.33 | $0.13 | +86% |
| $0.07 | $0.34 | $0.14 | +100% | |
| ● NextBit bf16 | $0.09 | $0.30 | $0.14 | +100% |
| ● Io Net bf16 | $0.09 | $0.31 | $0.15 | +114% |
| ● CoreWeave bf16 | $0.10 | $0.30 | $0.15 | +114% |
| ● Cloudflare | $0.10 | $0.30 | $0.15 | +114% |
| ● Venice bf16 | $0.13 | $0.40 | $0.20 | +186% |
| $0.13 | $0.40 | $0.20 | +186% | |
| $0.13 | $0.40 | $0.20 | +186% | |
| ● SiliconFlow fp8 | $0.14 | $0.40 | $0.21 | +200% |
| $0.15 | $0.60 | $0.26 | +271% |
● official API · ● cloud platform · ● inference host · USD per 1M tokens. Same model, different providers - price and quantization vary.
- Ctx
- 262K
- max output
- 33K
- cache read /1M
- $0.03
- Family
- gemma
- Modalities
- image · text · video
- Features
- json · reasoning · tools
Live pricing, updated 2026-11-03.
Google models at a similar price
| Model | In | Out | Ctx |
|---|---|---|---|
| Gemma 4 26B A4B · this model | $0.059 | $0.178 | 262K |
| Gemma 3 27B | $0.08 | $0.35 | 131K |
| Gemini 2.5 Flash Lite | $0.1 | $0.4 | 1.048576M |
| Gemma 4 31B | $0.2 | $0.4 | 262K |
| Gemini 3.1 Flash Lite | $0.25 | $1.5 | 1.048576M |
| Gemini 2.5 Flash | $0.3 | $2.5 | 1.048576M |