# Gemma 4 26B A4B API prices

Gemma 4 26B A4B (gemma) — 262k context, 131k max output.
4 metered per-token offers from 5 provider(s), in USD per 1M tokens.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| EmpirioLabs AI | $0.05 | $0.29 | $0.025 | 262k |
| NanoGPT | $0.12 | $0.38 | $0.06 | 262k |
| Merge Gateway | $0.13 | $0.4 | — | 262k |
| NovitaAI | $0.13 | $0.4 | — | 262k |

## Summary

- Cheapest input: $0.05 per 1M tokens (EmpirioLabs AI)
- Cheapest output: $0.29 per 1M tokens (EmpirioLabs AI)
- First-party: not listed separately
- Free offers: OpenRouter
- Subscription plans (not per-token): none
- Released: 2026-04-02
- Inputs: image, text, video

HTML page: https://llmprice.gitlab.io/models/gemma-4-26b-a4b/
Full dataset: https://llmprice.gitlab.io/data/catalog.json