Methodology: how every cost is calculated

No black boxes. Every number on this site comes from one of the formulas below. Each is plain arithmetic — verifiable once and stable forever — and is checked against known examples before release. Prices are convenience defaults; you can override every one of them.

1. API cost

Commercial APIs bill per token, input and output priced separately (output is typically 3–5× input). Prices are quoted per million tokens.

API/month = (input_tokens ÷ 1,000,000 × price_in) + (output_tokens ÷ 1,000,000 × price_out)

Example: 1,000,000 input at $3/1M plus 500,000 output at $15/1M = $3.00 + $7.50 = $10.50.

2. Self-hosting cost (rented GPU)

A rented GPU bills by the hour whether or not it is busy, so its cost is essentially fixed. We use a 730-hour month (365×24÷12).

Self-host/month = $/hour × 730 × utilization + overhead

Example: $1.50/hour × 730 × 30% = $328.50/month (before overhead). Overhead is your estimate of DevOps time, monitoring and redundancy.

3. Self-hosting cost (owned hardware)

Owned/month = capex ÷ amortization_months + (watts ÷ 1000 × 24 × 30 × utilization × $/kWh) + overhead

Example: a $15,000 server amortized over 36 months contributes $416.67/month before power and overhead.

4. Blended price per million tokens

To compare a mixed input/output workload against a fixed self-hosting cost, we collapse the two prices into one blended rate weighted by the token mix.

Blended price/1M = (input × price_in + output × price_out) ÷ (input + output)

5. Break-even volume

API cost is a straight line through the origin; self-hosting is a flat line. They cross where the two monthly costs are equal.

Break-even tokens/month = Self-host monthly ÷ blended price/1M × 1,000,000

Example: a $320/month GPU against a $3/1M blended price breaks even at $320 ÷ $3 × 1M ≈ 106.7M tokens/month. Below it the API wins; above it self-hosting wins on raw cost.

6. Self-hosting cost per million tokens

Self-host $/1M = ($/hour ÷ 3600) ÷ (tokens_per_second × utilization) × 1,000,000

Example: $1.50/hour at 2,000 tok/s and 100% utilization ≈ $0.21 per 1M tokens.

7. VRAM and model fit

Memory to hold the weights is parameters × bytes per parameter (set by quantization) plus headroom for the KV-cache and activations (~1.2×).

VRAM (GB) ≈ params(B) × bytes_per_param × 1.2 | fp16 = 2, int8 = 1, int4 = 0.5 bytes

Example: a 70B model needs ≈ 140 GB at fp16 (two 80 GB GPUs) but ≈ 42 GB at int4 (fits one 48 GB GPU).

Assumptions & limits

Token estimates from text use ≈ words × 1.33 (or characters ÷ 4) — a stated heuristic, not exact tokenization.
Self-hosting figures are infrastructure cost only. They exclude latency, reliability engineering, and idle waste beyond the utilization you enter — those are caveats, not dollars.
Prices are publicly listed list prices on their verification date; negotiated, committed-use, or regional pricing will differ.
FX (EUR/GBP) is fetched daily and cached, with a bundled fallback rate labelled "indicative" if the source is unavailable.

Found an error in a formula or a stale price? Tell me — corrections are welcome and credited.

Reference sources

Provider list prices come from each vendor's own public pricing page on the date shown next to the figure. For the measurement conventions behind tokens, throughput and hardware cost the reference bodies are NIST and ISO; they are linked at section level because their documents are revised over time.