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
Released--
Status
Older
in 11 days Leaves Amazon Bedrock on 30 Nov 2026
Current
Open weightsNoNo
Hosts
APIs you can call it on
12
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atNot listedGoogle AI Studio
Input-$0.20
Output-$0.00
Cached input--
Batch
input / output
-$0.10 / -
Cheapest anywhere
input / output
Not listed$0.20 / $0.00
Google AI Studio
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
-$60.00
RAG over documents
2,000 a day, 8K in, 600 out
-$96.00
Coding agent
1,000 a day, 40K in, 2K out
-$240
Overnight batch
20,000 a day, 4K in, 400 out
-$240
Limits
Context window77 tokens8K tokens
Max output--
Capabilities
Takes inTextText, Images, Audio
ProducesEmbeddingsEmbeddings
Effort settings
as listed by the source
--
Batch API