Cost anatomy

Claude Sonnet 5

ClaudeFoundry ·Global

Fresh input / cached input / output cost breakdown, active and scheduled rates, provenance, same-model deployment markup, and cost-comparable alternatives for this purchasable lane.

Start with a pattern

Illustrative workloads

Pick a useful starting shape, then fine-tune every input below.

Fine-tune

Workload and pricing scenario

Adjust the token shape, cache behavior, time window, and service tier. Every number below updates immediately.

Interactive

Workload cost calculator

Input tokens (M)60M

Output tokens (K)210K

Cache hit rate90%

Share of input tokens served from cache. Applied only to models with a cache meter.

Time

Service tier

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.

Rate state

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.

Input / 1M

$2.00^‡

CHF 1.61

Cached input / 1M

$0.20^‡

CHF 0.161

Output / 1M

$10.00^‡

CHF 8.05

Cost anatomy

Where this workload's cost goes

60M input tokens (90% cache hit) and 210K output tokens, at the resolved rate above.

$12.00

Fresh input · CHF 9.66

$10.80

Cached input · CHF 8.69

$2.10

Output · CHF 1.69

$24.90

Workload total · CHF 20.04

$12.00 + $10.80 + $2.10 = $24.90

Provenance

How much to trust these numbers

InputestimateCached inputestimateOutputestimate

Hosted-on-Azure Foundry deployment, billed via CCU. Launched at this rate as introductory pricing through 2026-08-31; Anthropic cancelled the planned 2026-09-01 rise to $3/$0.30/$15 and confirmed this rate is now permanent.

Microsoft's CCU billing docs state the CCU price converts Anthropic's own published per-model rates; no Anthropic per-token meter exists in Azure's Retail Prices API, so this stays an estimate. Anthropic (@claudeai) on X, 2026-08-10: introductory pricing made permanent (see the Direct row above for the exact quote and URL) — the original announcement. Anthropic's pricing page (platform.claude.com/docs/en/about-claude/pricing) has since caught up: a 2026-08-12 raw-DOM read confirms the $2/$10 rate is now the standard price and the planned September 1 increase will not occur (see the Direct row above for the verbatim quote), captured 2026-08-12. Cache hit rate inherited from Anthropic's direct pricing ($0.20/MTok).

Direct vs Foundry

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%)

Cost-comparable

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 5
ClaudeSame provider
Direct API
$24.90
CHF 20.04
$0.00 (0%) vs this lane
GPT-5.2 / Codex
OpenAI / Azure OpenAI
Foundry ·Data Zone
$25.18
CHF 20.27
+$0.279 (+1%) vs this lane
GPT-5.6 Terra
OpenAI / Azure OpenAI
Foundry ·Global
$25.32
CHF 20.38
+$0.42 (+2%) vs this lane
GLM 5.1
GLM · Fireworks-hosted
Foundry ·Data Zone
$25.70
CHF 20.69
+$0.80 (+3%) vs this lane
GLM-5.1
GLM · Z.ai direct API
Direct API
$23.36
CHF 18.81
-$1.54 (-6%) vs this lane
GLM-5.2
GLM · Z.ai direct API
Direct API
$23.36
CHF 18.81
-$1.54 (-6%) vs this lane