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-18 Jul 2024
Status
Current
in 131 days Leaves Amazon Bedrock on 30 Mar 2027
Current
in 56 days Leaves OpenAI on 14 Jan 2027
Open weightsYes, NVIDIA Open Model LicenseNo
Hosts
APIs you can call it on
15
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atAmazon BedrockOpenAI
Input$0.20$0.15
Output$0.60$0.60
Cached input-$0.075
Batch
input / output
$0.10 / $0.30$0.075 / $0.30
Cheapest anywhere
input / output
$0.20 / $0.60
Amazon Bedrock
$0.15 / $0.60
OpenAI
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$83.25
RAG over documents
2,000 a day, 8K in, 600 out
$118$75.60
Coding agent
1,000 a day, 40K in, 2K out
$276$153
Overnight batch
20,000 a day, 4K in, 400 out
$312$252
Limits
Context window128K tokens128K tokens
Max output8K tokens16K tokens
Capabilities
Takes inText, ImagesText, Images, PDFs
ProducesTextText
Effort settings
as listed by the source
--
Streaming
Function calling
JSON mode
Structured outputs
Tool calling
Prompt caching
Batch API
Parallel tool calls