impulse

Compare models

Up to 4 models side by side: list prices, what a month of real traffic costs, limits and capabilities. The best value in each row is marked with a check.

Clear
Model
Overview
Released19 Jan 20261 Apr 2026
Status
Older
in 131 days Leaves Amazon Bedrock on 30 Mar 2027
Current
Open weightsYes, MITNo
Hosts
APIs you can call it on
83
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atNot listedZ.ai
Input-$1.20
Output-$4.00
Cached input-$0.24
Batch
input / output
--
Cheapest anywhere
input / output
$0.024 / $0.16
CLF AI Gateway
$0.704 / $3.10
AIHubMix
Monthly bill · at the price above, 30 days, with each workload's cache and batch use
Chat assistant
5,000 a day, 2K in, 500 out
-$574
RAG over documents
2,000 a day, 8K in, 600 out
-$490
Coding agent
1,000 a day, 40K in, 2K out
-$874
Overnight batch
20,000 a day, 4K in, 400 out
-$3,840
Limits
Context window200K tokens200K tokens
Max output128K tokens128K tokens
Capabilities
Takes inTextText, Images
ProducesTextText
Effort settings
as listed by the source
--
Streaming
Function calling
Reasoning
Tool calling
Prompt caching