Compare two models, field by field
Pick any two models in the catalog. Every number is read from the catalog at request time: the list price and what you pay after a routing discount, cache rates, context and output limits, modalities, and the endpoint that serves each one.
Model A
Model B
Overview
Provider
Anthropic
Particle-ai
MODEL ID
claude-haiku-5-5particle-1Endpoint
/api/v1/messages/api/v1/messagesProtocol
messages
messages
Model kind
chatchatReleased
Capability
Context
1,000,000
1,048,576
Max output
128,000
131,072
Input types
Text · Image · File
Text · Image
Output types
Text
Text
Pricing
Input tokens
$0.1/ 1M tokens
$0.25/ 1M tokens
Output tokens
$0.5/ 1M tokens
$1/ 1M tokens
Cache read
$0.01/ 1M tokens
$0.03/ 1M tokens
Cache write
$0.125/ 1M tokens
—
Web search
$0.01/ request
—
Best discount
45% off
claude-ccNo discount available
Claude Haiku 5.5 costs 2.5× less per input token
Rates are the catalog's published prices at request time, per 1M tokens unless the unit says otherwise. The discounted price is what you pay through that channel; the struck-through price is the provider's list price.