Skip to main content

Speed tiers

Every request is billed per token. Choose the speed that fits your workload.
SpeedPrice / 1M tokensLatencyBest for
Fast$0.60<200ms P95Real-time UX, chatbots
Standard$0.20<1s P95Background processing
Fast Batch$0.08<15min P95Bulk analysis, exports
Fast and Standard are set via the speed parameter on /v1/classify and /v1/tag. Fast Batch pricing applies automatically when using the async batch endpoints.

Free tier

Every account gets 5M free tokens/month — no credit card required. Free tokens work on all speed tiers.

Rate limits

Rate limits depend on the tier configured for your API key.
TierRequests/minTokens/minConcurrent
Public30150,0002
Developer60500,0005
Production1,00010,000,00050
EnterpriseCustomCustomCustom
Cache hits do not consume rate limits. You can set custom per-key rate limits when creating an API key.

Validation limits

LimitValue
Max labels per request200
Max label length50 characters
Max text length100,000 characters
Max request body1MB
Max sync batch size1,000 texts
Max async batch file5GB

Cache

Responses are cached automatically based on your tier. Cache hits are free (zero tokens billed).
TierDefault TTL
Public5 minutes
Developer1 hour
Production24 hours
Set cache: false in your request to bypass caching, or configure a custom TTL per API key.

Enterprise

Need volume pricing, dedicated infrastructure, or custom rate limits? Contact us.