DeepInfra
gemma-4-26B-A4B-it
Made by Google DeepMind. Released 2026-04-02. Accessibility not recorded. Cheapest standard rate we hold: $0.34 per million output tokens, no context split.
What it costs
| Tier | Kind | In | Out | Cached in | From |
|---|---|---|---|---|---|
| standard | text | $0.07 | $0.34 | — | registry |
per million tokens, US dollars. * marks a rate from a single registry or two that disagree — the best available number rather than a confirmed one. Every other row is confirmed against a seller or a licensed index.
What it scores, by house
| Benchmark | House | Score | Evaluated | Scaffold |
|---|---|---|---|---|
| chess puzzles | Epoch AI | 0.1±0.02 | 2026-08-06 | minimal |
| gpqa diamond | Epoch AI | 0.7±0.03 | 2026-08-06 | minimal |
| otis mock aime 2024 2025near its ceiling | Epoch AI | 0.8±0.06 | 2026-08-28 | minimal |
These scores are not comparable between houses and are not added up. A score is dated by when it was evaluated, not when the model was released, and a score without its scaffold is not a measurement — which is why both are printed.
Every rate we hold · Why there is no single best model · Everything from DeepInfra