Models / Google / Gemma 4 26B A4B IT
Google · gemma
Gemma 4 26B A4B IT
Open Gemma instruction model for efficient chat and self-hosted deployments
$0.15 in · $0.60 out
per 1M tokens · first-party price. Reference price from Vertex, the lab's own listing.
Provider input prices run from $0.042 to $0.57 per 1M tokens. Output prices run from $0.22 to $1.71.
- Context
- 262,144
- Max output
- 32,768
- Cache read
- $0.015
- Cache write
- —
- Reasoning
- Yes
- Tool calls
- Yes
- Structured output
- Yes
- Vision
- Yes
- Open weights
- Yes
- License
- —
- Released
- Apr 2, 2026
- Updated in source
- Apr 2, 2026
- Knowledge
- —
- Providers
- 29
Providers
| Provider | Input | Output | Cache read | Cache write | Status |
|---|---|---|---|---|---|
| Kilo Gateway | $0.042 | $0.22 | $0.021 | — | — |
| EmpirioLabs AI | $0.05 | $0.29 | $0.025 | — | — |
| OrcaRouter | $0.06 | $0.33 | $0.008 | — | — |
| Deep Infra | $0.07 | $0.34 | — | — | — |
| DevPass | $0.07 | $0.34 | — | — | — |
| Requesty | $0.07 | $0.34 | $0.07 | — | — |
| OpenRouter | $0.09 | $0.30 | $0.05 | — | — |
| Charm Hyper | $0.098 | $0.33 | $0.049 | — | — |
| AKI.IO | $0.10 | $0.50 | — | — | — |
| Cloudflare Workers AI | $0.10 | $0.30 | $0.05 | — | — |
| CoreWeave | $0.10 | $0.30 | $0.05 | — | — |
| Cortecs | $0.11 | $0.56 | — | — | — |
| NanoGPT | $0.12 | $0.38 | $0.06 | — | — |
| SiliconFlow | $0.12 | $0.40 | — | — | — |
| Amazon Bedrock | $0.13 | $0.40 | — | — | — |
| Hugging Face | $0.13 | $0.40 | — | — | — |
| LLM Gateway | $0.13 | $0.40 | — | — | — |
| Merge Gateway | $0.13 | $0.40 | — | — | — |
| Novita AI | $0.13 | $0.40 | — | — | — |
| Venice AI | $0.13 | $0.40 | $0.05 | — | — |
| evroc | $0.14 | $0.58 | — | — | — |
| Vercel AI Gateway | $0.15 | $0.60 | $0.015 | — | — |
| Vertexreference | $0.15 | $0.60 | $0.015 | — | alpha |
| AI/ML API | $0.21 | $0.83 | $0.21 | — | — |
| Scaleway | $0.25 | $0.50 | — | — | beta |
| GreenPT | $0.57 | $1.71 | — | — | — |
| — | — | — | — | — | |
| NaN | $0 | $0 | — | — | — |
| Tempr Gateway | — | — | — | — | — |