DeepInfra
Qwen3.5-9B
Made by Alibaba. Released 2026-02-24. Accessibility not recorded. Cheapest standard rate we hold: $0.15 per million output tokens, no context split.
What it costs
| Tier | Kind | In | Out | Cached in | From |
|---|---|---|---|---|---|
| standard | text | $0.10 | $0.15 | — | 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 | 0.0±0.01 | 2026-08-27 | — |
| chess puzzles | Epoch AI | 0.1±0.03 | 2026-08-27 | none |
| gpqa diamond | Epoch AI | 0.8±0.02 | 2026-08-27 | — |
| gpqa diamond | Epoch AI | 0.8±0.02 | 2026-08-27 | none |
| otis mock aime 2024 2025near its ceiling | Epoch AI | 0.4±0.07 | 2026-08-27 | — |
| otis mock aime 2024 2025near its ceiling | Epoch AI | 0.6±0.06 | 2026-08-27 | none |
| critpt | collected by Epoch AI | 0.0 | — | — |
| dtbenchnear its ceiling | collected by Epoch AI | 0.7 | — | — |
| lmca | collected by Epoch AI | 24.5 | — | — |
| scicode | collected by Epoch AI | 0.3 | — | — |
| terminalbench | collected by Epoch AI | 0.1 | — | little-coder |
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