OpenAI Computer Use pricing & cost inputs
Verified pricing for OpenAI Computer Use, including unit definitions, freshness and estimation limits.
$10 / 1M input tokens · gpt-6-astra
gpt-6-astra · Standard · short context
Selected example model, not a category-wide price. Excludes execution infrastructure, tool/image-specific accounting, long-context and other processing tiers.
usage pricing · USD · Verified Sep 27, 2026
What this price does and does not cover
The decision layer. Your application supplies a browser or desktop, executes returned actions, captures the next screenshot, and enforces approval boundaries. Pair it with execution infrastructure or a local sandbox.
The entry amount is a plan or licensing snapshot, not a guarantee of the cost to complete a task. Browser runtime, model tokens, proxy bandwidth and retries can add separate charges. Check the source for included credits, billing intervals and regional taxes before purchasing.
We suppress current price displays once verification is more than 14 days old. We do not replace missing rates with zero.
Price the assumptions.
Estimate documented components with current price records. Change the workload assumptions to match your pilot; this is not a vendor quote.
Plan $20.00 · Browser $0.00 · Proxy $0.00
Model $7.50 · Model markup $0.00 · Other $0.00
8.3 browser hours / 0.0 billable · 0.00 billable proxy GB
Included browser and proxy allowances are deducted where documented. Retries, caching, long-context tiers, tax and credit-based overages are not modeled. Model selection prices an assumption; it does not verify integration compatibility.
Usage rates are overages after included monthly allowances. Model, search/fetch, and agent usage can add cost.
Selected example model, not a category-wide price. Excludes execution infrastructure, tool/image-specific accounting, long-context and other processing tiers.
Decide on fit before cost
- Custom browser and desktop agent loops
- Teams already using the Responses API