Claude Sonnet 5
Fresh input / cached input / output cost breakdown, active and scheduled rates, provenance, same-model deployment markup, and cost-comparable alternatives for this purchasable lane.
Illustrative workloads
Pick a useful starting shape, then fine-tune every input below.
Workload and pricing scenario
Adjust the token shape, cache behavior, time window, and service tier. Every number below updates immediately.
Workload cost calculator
Share of input tokens served from cache. Applied only to models with a cache meter.
Rows with a rate that changes by time of day, promo window or service tier are priced for this scenario instead of their flat listed rate; a brand-colored label under the model name names which one applies. Context size for band-priced rows uses the input-token count below.
Picking a specific hour also previews time-of-day rates that are scheduled but have not started billing yet; those rows are labelled · preview with their start instant. Now only ever shows rates that are billable at this moment.
What this lane charges right now
Priced under the workload and scenario above. The full published schedule below always shows every variant regardless of which scenario is selected.
Where this workload's cost goes
60M input tokens (90% cache hit) and 210K output tokens, at the resolved rate above.
$12.00 + $10.80 + $2.10 = $24.90
How much to trust these numbers
Azure-hosted Foundry Global Standard, billed via CCU. Microsoft's billing documentation confirms token usage converts at Anthropic's published model rates, so the standard token-equivalent rate is official; private marketplace discounts can change an individual invoice.
Microsoft Learn's CCU billing page, captured 2026-09-23, states that Foundry converts token usage using Anthropic's published per-model rates at $0.01 per CCU before any private-offer discount. Anthropic's official pricing page publishes Sonnet 5 at $2/M input, $0.20/M cache hit, and $10/M output and says its scheduled September 1 increase will not occur. Azure invoices aggregate usage under CCUs rather than per-model token meters; the official standard token-equivalent rate is unchanged.
Same-model deployment markup
How much this Foundry lane costs over the same model's Direct API rate.
| Lane | Deployment | Workload cost | Foundry markup |
|---|---|---|---|
| Claude Sonnet 5 | Direct API | $24.90 | $0.00 (0%) |
Other lanes within ±25% of this workload's cost
Same provider first, then ranked by cost proximity, for 60M in / 210K out. This is a cost ranking only — never a quality recommendation.
- Claude Sonnet 5ClaudeSame providerDirect API$24.90CHF 20.04$0.00 (0%) vs this lane
- Claude Sonnet 5.5ClaudeSame providerFoundry ·Data Zone$21.45CHF 17.27-$3.45 (-14%) vs this lane
- Claude Sonnet 5.5ClaudeSame providerDirect API$19.50CHF 15.70-$5.40 (-22%) vs this lane
- Claude Sonnet 5.5ClaudeSame providerFoundry ·Global$19.50CHF 15.70-$5.40 (-22%) vs this lane
- Kimi K3.1 ProKimi · Kimi direct APIDirect API$24.90CHF 20.04$0.00 (0%) vs this lane
- GPT-6 SolOpenAI / Azure OpenAI · OpenAI direct APIDirect API$24.90CHF 20.04$0.00 (0%) vs this lane