Documentation Index
Fetch the complete documentation index at: https://docs.veri.studio/llms.txt
Use this file to discover all available pages before exploring further.
Spend Summary
Get an overview of attributed job spend for the last N days.
Reporting window in days.
Request
curl "https://api.veri.studio/v1/cost/summary?days=30" \
-H "Authorization: Bearer vk_your_api_key"
Response
{
"period_days": 30,
"job_count": 12,
"total_cost_usd": 185.25,
"total_gpu_hours": 47.5,
"avg_cost_per_job_usd": 15.44
}
Spend by Provider
Request
curl "https://api.veri.studio/v1/cost/by_provider?days=30" \
-H "Authorization: Bearer vk_your_api_key"
Response
[
{
"provider": "prime_intellect",
"job_count": 12,
"cost_usd": 185.25
}
]
Spend by GPU Type
Request
curl "https://api.veri.studio/v1/cost/by_gpu?days=30" \
-H "Authorization: Bearer vk_your_api_key"
Response
[
{
"gpu_type": "A100-80GB",
"job_count": 10,
"cost_usd": 154.0,
"gpu_hours": 39.2
}
]
Estimate Job Cost
Estimate the cost of a run from GPU shape, duration, provider, and markup.
gpu_type
string
default:"A100-80GB"
GPU type to price.
Runtime used for the estimate.
provider
string
default:"prime_intellect"
Provider key from the pricing table.
User-facing markup multiplier.
Request
curl "https://api.veri.studio/v1/cost/estimate?gpu_type=A100-80GB&gpu_count=1&duration_minutes=60&provider=prime_intellect&markup=1.3" \
-H "Authorization: Bearer vk_your_api_key"
Response
{
"cost_usd": 4.5136,
"gpu_cost_usd": 3.4,
"storage_cost_usd": 0.0,
"overhead_cost_usd": 0.072,
"duration_seconds": 3600.0,
"gpu_type": "A100-80GB",
"gpu_count": 1,
"provider": "prime_intellect",
"markup_multiplier": 1.3
}
Monthly Projection
Request
curl "https://api.veri.studio/v1/cost/monthly_projection?jobs_per_day=100&avg_duration_minutes=30&gpu_type=A100-80GB&gpu_count=1&provider=prime_intellect" \
-H "Authorization: Bearer vk_your_api_key"
Response
{
"total_jobs": 3000,
"avg_cost_per_job_usd": 1.736,
"total_monthly_usd": 5208.0,
"keep_warm_monthly_usd": 216.0
}
Compare Provider Costs
Compare GPU costs across providers for a given job configuration.
Request
curl "https://api.veri.studio/v1/cost/compare?gpu_type=A100-80GB&gpu_count=1&duration_minutes=60" \
-H "Authorization: Bearer vk_your_api_key"
Response
{
"prime_intellect": 3.4,
"aws": 5.12,
"aws_savings_1y": 3.33
}
Current GPU Rates
Get the raw pricing table keyed by provider and GPU type.
Request
curl https://api.veri.studio/v1/cost/rates \
-H "Authorization: Bearer vk_your_api_key"
Response
{
"prime_intellect": {
"A100-40GB": 2.78,
"A100-80GB": 3.4,
"H100": 6.0,
"H200": 7.2,
"L40S": 1.95,
"MI300X": 0.0
},
"aws": {
"A100-40GB": 4.1,
"A100-80GB": 5.12,
"H100": 12.29,
"H200": 14.5,
"L40S": 2.05,
"MI300X": 0.0
}
}
