Skip to content
llm-spend
GitHub
Cost anatomy

Grok-4.3

GrokFoundry ·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

60M
210K
90%

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

Time

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
$1.25
CHF 1.01
Cached input / 1M
$0.20
CHF 0.161
Output / 1M
$2.50
CHF 2.01
Cost anatomy

Where this workload's cost goes

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

$7.50
Fresh input · CHF 6.04
$10.80
Cached input · CHF 8.69
$0.525
Output · CHF 0.423
$18.82
Workload total · CHF 15.15

$7.50 + $10.80 + $0.525 = $18.82

Provenance

How much to trust these numbers

InputofficialCached inputofficialOutputofficial

Newest Grok on Foundry; cached-input meter now published. Long-context (≥200K prompt) meters bill at 2x, including cached input at $0.40/M.

Input $1.25/M and output $2.50/M from the Foundry Models pricing page. Cached input from the Azure Retail Prices API meter named bare '4.3' — a 'grok' meterName search misses it — 'Cached Inp Glbl' at $0.0002/1K ($0.20/M), effective 2026-05-01, captured 2026-07-23; matches xAI's direct Grok 4.3 docs. Long-context 'L' meters exist at 2x ($2.50 in / $5.00 out / $0.40 cached).

Direct vs Foundry

Same-model deployment markup

How much this Foundry lane costs over the same model's Direct API rate.

Not available — no Direct API 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.

  • Grok-4.3
    GrokSame provider
    Foundry ·Data Zone
    $20.71
    CHF 16.67
    +$1.88 (+10%) vs this lane
  • Mistral Medium 3.5
    Mistral · Mistral direct API
    Direct API
    $18.68
    CHF 15.03
    -$0.15 (-1%) vs this lane
  • Gemini 3.5 Flash
    Gemini
    Foundry ·Global
    $18.99
    CHF 15.29
    +$0.165 (+1%) vs this lane
  • DeepSeek-V4 Pro
    DeepSeek
    Foundry ·Global
    $19.00
    CHF 15.30
    +$0.176 (+1%) vs this lane
  • GLM 5
    GLM · Fireworks-hosted
    Foundry ·Data Zone
    $19.22
    CHF 15.47
    +$0.394 (+2%) vs this lane
  • GLM 5.2
    GLM · Fireworks-hosted
    Foundry ·Data Zone
    $18.36
    CHF 14.78
    -$0.469 (-2%) vs this lane