Skip to content
SOLVENCY
Request a demo

Account controls are loading.

Head to head

UI-TARS 7B vsLlama 3.1 70B Instruct

For tasks, about a month.

Verdict · measured basis

UI-TARS 7B costs $0.0003 per solved task against Llama 3.1 70B Instruct at $0.0005 — ▼ 2.0x cheaper. Over 200 tasks that is $0.05 a month.

On output token price alone UI-TARS 7B looks 2.0x cheaper. The ranking holds, but the margin changes.

Verified pricing, pass rate and cost per solved task for UI-TARS 7B and Llama 3.1 70B Instruct
FigureUI-TARS 7B Llama 3.1 70B Instruct
Input $/Mtok$0.1$0.4
Output $/Mtok$0.2$0.4
Cached input $/Mtok$0.1$0.4
Pass rate25%50%
Cost per solved task$0.0003measured$0.0005measured
Cost per month$0.05$0.11

Cost per month against tasks per month · drag the marker

Monthly cost against tasks per monthLog-log lines for UI-TARS 7B (measured, $0.0003 per solved task), Llama 3.1 70B Instruct (measured, $0.0005 per solved task) from 10 to 100,000 tasks a month. Marker at 200 tasks.101001k10k100k$0.01$0.1$1$10TASKS / MONTH (log) →200 tasksUI-TARS 7B · MEASURED · $0.0003 per solved task$0.05Llama 3.1 70B Instruct · MEASURED · $0.0005 per solved task$0.11— UI-TARS 7B · MEASURED— Llama 3.1 70B Instruct · MEASURED

Solid measured · dashed modeled · dotted stale. The gap is the verdict.

Solvency Bench (solvency.dev) — first-party measurement · verified 2026-08-26 · prices from each provider's pricing page; measured rows ignore the tier · Methodology · All models at these settings