Cost calculator

Describe your workload and see what every model would cost per month, cheapest first. Prices are USD from vendor price lists; quality filters use heuristic task scores, so shortlist here and then test on your own data.

Start from an example

≈ 50,000 requests per month

per request

per request

Repeated prompt parts (system prompt, documents). Only models with a cached-input price benefit.

Work that can wait hours. Only models with batch prices benefit; batch and cache discounts are not stacked.

487 of 490 models · hidden: 3 free ($0)

Cheapest

$1.83/ month

gpt-oss-120b

$0.0000366 per request

Median

$75.00/ month

Qwen2.5 VL 72B Instruct

$0.0015 per request

Most expensive

$4,950/ month

GPT-5.5 Pro

$0.099 per request

Spread

2705×

priciest vs cheapest

$4,948 / month apart

Estimated monthly cost per model, cheapest first
Compare#ModelPer requestPer monthvs cheapestDiscounts usedContextPrice in / out
1gpt-oss-120b
OpenAIfast
$0.0000366$1.83cheapest
—
131K$0.014 / $0.052
2Ling 3.0 Flash
Inclusionaifast
$0.0000504$2.521.4×
—
262K$0.021 / $0.063
3Mistral Nemo
Mistral AIfast
$0.0000525$2.631.4×
—
131K$0.029 / $0.030
4Extract
Scaledownfast
$0.00006$3.001.6×
—
1M$0.040 / $0
5Summarize
Scaledownfast
$0.00006$3.001.6×
—
1M$0.040 / $0
6Nex-N2.5-Mini
Nex Agifast
$0.0000675$3.381.8×
—
262K$0.025 / $0.10
7GLM Flash Latest
~z Aifast
$0.0000704$3.521.9×
—
1.05M$0.029 / $0.092
8Llama 3 8B Lunaris
Sao10kfast
$0.000075$3.752×
—
8K$0.040 / $0.050
9gpt-oss-20b
OpenAIfast
$0.000084$4.202.3×
—
131K$0.030 / $0.13
10Qwen3.7 Flash
Alibaba (Qwen)fast
$0.000084$4.202.3×
—
1M$0.030 / $0.13

Showing 1–10 of 487

Per page
Page 1 / 49

Cost = input tokens × input price + output tokens × output price, per request, times requests per month. Excludes taxes, volume discounts, fine-tuning, tool-call fees and any minimum commitments. Tick “Compare” on up to four rows to see them side by side.