Gemma 4 26B A4B IT
by Charm Hyper · family gemma · listed Apr 2026TW
Open Gemma instruction model for efficient chat and self-hosted deployments
Current rates USD per 1M tokens
Input$0.13
Output$0.424
Cache read—
Cache write$0.065
Against the market
On the record
- Model id
gemma-4-26b-a4b-it- Context window
- 256K tokens
- Max output
- 26K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- no
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- —
- Released
- 2026-04-30
- Last updated
- 2026-07-22
- Provider docs
- hyper.charm.land
Back of the envelope
≈
Also listed at
- OrcaRouter$0.06 in · $0.33 out
- LLM Gateway$0.07 in · $0.34 out
- Deep Infra$0.07 in · $0.34 out
- Cloudflare Workers AI$0.10 in · $0.30 out
- SiliconFlow$0.12 in · $0.40 out
- Kilo Gateway$0.12 in · $0.40 out
- NanoGPT$0.13 in · $0.40 out
- NovitaAI$0.13 in · $0.40 out
- Hugging Face$0.13 in · $0.40 out
- OpenRouter$0.14 in · $0.42 out
- evroc$0.144 in · $0.575 out
- Vercel AI Gateway$0.15 in · $0.60 out
- Scaleway$0.25 in · $0.50 out
- Google— in · — out
- Merge Gateway— in · — out