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-5 Dec 2024
Status
Current
Current
Open weightsNoNo
Hosts
APIs you can call it on
13
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atAmazon BedrockAmazon Nova
Input$0.20$0.06
Output$0.60$0.24
Cached input--
Batch
input / output
--
Cheapest anywhere
input / output
$0.20 / $0.60
Amazon Bedrock
$0.06 / $0.24
Amazon Nova
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
$105$36.00
RAG over documents
2,000 a day, 8K in, 600 out
$118$37.44
Coding agent
1,000 a day, 40K in, 2K out
$276$86.40
Overnight batch
20,000 a day, 4K in, 400 out
$624$202
Limits
Context window42K tokens300K tokens
Max output8K tokens10K tokens
Capabilities
Takes inTextText, Images, PDFs
ProducesTextText
Effort settings
as listed by the source
--
Streaming
Function calling
JSON mode
Structured outputs
Tool calling
Prompt caching