Cost anatomy

Claude Fable 5.1

ClaudeDirect API

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

$10.00

CHF 8.05

Cached input / 1M

$0.25

CHF 0.201

Output / 1M

$50.00

CHF 40.25

Cost anatomy

Where this workload's cost goes

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

$60.00

Fresh input · CHF 48.30

$13.50

Cached input · CHF 10.87

$10.50

Output · CHF 8.45

$84.00

Workload total · CHF 67.62

$60.00 + $13.50 + $10.50 = $84.00

Provenance

How much to trust these numbers

InputofficialCached inputofficialOutputofficial

Latest generally available Claude model for demanding reasoning and long-horizon agentic work. Cache reads are priced at $0.25/M, one quarter of the predecessor's cache-read rate.

Anthropic's official Claude Fable 5.1 model page and pricing page, read 2026-09-02: $10/M input, $0.25/M cache read and $50/M output, with a 1M-token context and 128K max output. The release notes confirm availability on the Claude API and Microsoft Foundry. Azure's full Foundry Models Retail Prices API sweep on 2026-09-02 has no Anthropic per-token meter, so this is a Direct row rather than a token-priced Foundry row.

Direct vs Foundry

Same-model deployment markup

How much more Microsoft Foundry charges for this exact model, over this Direct rate.

Not available — no Microsoft Foundry listing exists for this exact model in the catalog.

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 Mythos 5.1
ClaudeSame provider
Direct API
$84.00
CHF 67.62
$0.00 (0%) vs this lane
Mistral Medium 3.5
Mistral
Foundry ·Global
$91.58
CHF 73.72
+$7.58 (+9%) vs this lane
GPT-5.5
OpenAI / Azure OpenAI
Foundry ·Data Zone
$69.63
CHF 56.05
-$14.37 (-17%) vs this lane
GPT-5.6 Sol
OpenAI / Azure OpenAI
Foundry ·Data Zone
$69.63
CHF 56.05
-$14.37 (-17%) vs this lane
Mistral Medium 3.5
Mistral
Foundry ·Data Zone
$100.73
CHF 81.09
+$16.73 (+20%) vs this lane
GPT-5.5
OpenAI / Azure OpenAI
Foundry ·Global
$63.30
CHF 50.96
-$20.70 (-25%) vs this lane