Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.priorlabs.ai/llms.txt

Use this file to discover all available pages before exploring further.

Every API prediction consumes tokens from your account’s daily and monthly pools. Thinking fits have a separate monthly quota. This page covers how costs are calculated, what the limits are, and what happens when you hit them.

​
Token cost

Each prediction request is charged based on the number of rows, columns, and estimators used. TabPFN v3 uses a sublinear cost function — doubling your data does not double the cost. Because TabPFN-3 is fundamentally more efficient at handling larger datasets, large-scale workloads are significantly cheaper than on v2.x. TabPFN v2.x uses a linear cost function: 
tokens = max(5,000, (train_rows + test_rows) × columns × n_estimators)
n_estimators defaults to 8 when not specified. The floor of 5,000 tokens applies to every request regardless of size. You can check your current usage with the get_api_usage() function in tabpfn-client, or monitor it in your account dashboard at ux.priorlabs.ai.

​
Usage pools

PoolDefault limitReset schedule
Daily prediction tokens50,000,000Midnight UTC
Monthly prediction tokens200,000,0001st of each month, midnight UTC
Thinking fits (monthly)201st of each month, midnight UTC
When a pool is exhausted, the API returns HTTP 429 with a message indicating which limit was hit and when it resets. A warning email is sent when either daily or monthly usage crosses 70% of the limit.

​
Thinking fit quota

Thinking mode fits are metered separately from prediction tokens. Each call to POST /tabpfn/fit with thinking enabled counts against the monthly thinking fit quota, regardless of dataset size or fit duration. When the thinking fit limit is reached, /tabpfn/fit returns HTTP 429. Prediction requests are unaffected — you can still predict using previously fitted models.

​
Dataset limits

Limits vary by model version. Use GET /tabpfn/get_model_limits to retrieve the current values for your account.
Constraintv3v2.6v2.5
Max train rows1,000,000100,00050,000
Max train cells (rows × columns)100,000,00020,000,00020,000,000
Max test rows200,000100,00050,000
Max classes1601010
Max columns2,0002,0002,000
Max upload size5 GB5 GB5 GB
Regression full output: output_type="full" is limited to 400 test rows. Use "mean", "median", or "quantiles" for larger test sets.

​
HTTP error codes

StatusCondition
429Daily, monthly, or thinking fit limit exceeded. The response body includes the specific limit, current usage, and reset time.
401 / 403Authentication failure — missing, invalid, or expired token.
422Validation error — dataset exceeds model limits, invalid parameters, or upload issues.

​
Higher limits

If you need higher token budgets or more thinking fits, contact hello@priorlabs.ai with your projected daily token volume and peak thinking usage.

Thinking mode

Configure fit-time optimization and understand thinking parameters.

REST quickstart

Full upload → fit → predict walkthrough.

TabPFN-3 changelog

What’s new in v3 — scale, capabilities, and migration.

Security

Encryption, data isolation, and access controls.